mirror of
https://github.com/Yuvi9587/Kemono-Downloader.git
synced 2025-12-29 16:14:44 +00:00
Compare commits
41 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
a9b210b2ba | ||
|
|
ec94417569 | ||
|
|
0a902895a8 | ||
|
|
7217bfdb39 | ||
|
|
24880b5042 | ||
|
|
510ae5e1d1 | ||
|
|
65b4759bad | ||
|
|
6e993d88de | ||
|
|
cc3565b12b | ||
|
|
f8b150dfdb | ||
|
|
5f7b526852 | ||
|
|
b0a6c264e1 | ||
|
|
d9364f4f91 | ||
|
|
9cd48bb63a | ||
|
|
d0f11c4a06 | ||
|
|
26fa3b9bc1 | ||
|
|
f7c4d892a8 | ||
|
|
661b97aa16 | ||
|
|
3704fece2b | ||
|
|
bdb7ac93c4 | ||
|
|
76d4a3ea8a | ||
|
|
ccc7804505 | ||
|
|
4ee750c5d4 | ||
|
|
e9be13c4e3 | ||
|
|
a5cb04ea6f | ||
|
|
842f18d70d | ||
|
|
fb3f0e8913 | ||
|
|
0758887154 | ||
|
|
e752d881e7 | ||
|
|
a776d1abe9 | ||
|
|
21d1ce4fa9 | ||
|
|
d5112a25ee | ||
|
|
791ce503ff | ||
|
|
e5b519d5ce | ||
|
|
9888ed0862 | ||
|
|
9e996bf682 | ||
|
|
e7a6a91542 | ||
|
|
d7faccce18 | ||
|
|
a78c01c4f6 | ||
|
|
6de9967e0b | ||
|
|
e3dd0e70b6 |
286
features.md
286
features.md
@@ -1,147 +1,159 @@
|
||||
<div>
|
||||
<h1>Kemono Downloader - Comprehensive Feature Guide</h1>
|
||||
<p>This guide provides a detailed overview of all user interface elements, input fields, buttons, popups, and functionalities available in the application.</p>
|
||||
<hr>
|
||||
<h2><strong>Main Window: Core Functionality</strong></h2>
|
||||
<p>The application is divided into a configuration panel on the left and a status/log panel on the right.</p>
|
||||
<h3><strong>Primary Inputs (Top-Left)</strong></h3>
|
||||
<h1>Kemono Downloader - Comprehensive Feature Guide</h1>
|
||||
<p>This guide provides a detailed overview of all user interface elements, input fields, buttons, popups, and functionalities available in the application.</p>
|
||||
<hr>
|
||||
<h2>1. Core Concepts & Supported Sites</h2>
|
||||
<h3>URL Input (🔗)</h3>
|
||||
<p>This is the primary input field where you specify the content you want to download.</p>
|
||||
<p><strong>Supported URL Types:</strong></p>
|
||||
<ul>
|
||||
<li><strong>Creator URL</strong>: A link to a creator's main page. Downloads all posts from that creator.</li>
|
||||
<li><strong>Post URL</strong>: A direct link to a specific post. Downloads only that single post.</li>
|
||||
<li><strong>Batch Command</strong>: Special keywords to trigger bulk downloading from a text file (see Batch Downloading section).</li>
|
||||
</ul>
|
||||
<p><strong>Supported Websites:</strong></p>
|
||||
<ul>
|
||||
<li>Kemono (<code>kemono.su</code>, <code>kemono.party</code>, etc.)</li>
|
||||
<li>Coomer (<code>coomer.su</code>, <code>coomer.party</code>, etc.)</li>
|
||||
<li>Discord (via Kemono/Coomer API)</li>
|
||||
<li>Bunkr</li>
|
||||
<li>Erome</li>
|
||||
<li>Saint2.su</li>
|
||||
<li>nhentai</li>
|
||||
</ul>
|
||||
<hr>
|
||||
<h2>2. Main Download Controls & Inputs</h2>
|
||||
<h3>Download Location (📁)</h3>
|
||||
<p>This input defines the main folder where your files will be saved.</p>
|
||||
<ul>
|
||||
<li><strong>Browse Button</strong>: Opens a system dialog to choose a folder.</li>
|
||||
<li><strong>Directory Creation</strong>: If the folder doesn't exist, the app will ask for confirmation to create it.</li>
|
||||
</ul>
|
||||
<h3>Filter by Character(s) & Scope</h3>
|
||||
<p>Used to download content for specific characters or series and organize them into subfolders.</p>
|
||||
<ul>
|
||||
<li><strong>Input Field</strong>: Enter comma-separated names (e.g., <code>Tifa, Aerith</code>). Group aliases using parentheses for folder naming (e.g., <code>(Cloud, Zack)</code>).</li>
|
||||
<li><strong>Scope Button</strong>: Cycles through where to look for name matches:
|
||||
<ul>
|
||||
<li><strong>URL Input Field</strong>: This is the starting point for most downloads. You can paste a URL for a specific post or for an entire creator's feed. The application's behavior adapts based on the URL type.</li>
|
||||
<li><strong>🎨 Creator Selection Popup</strong>: This button opens a powerful dialog listing all known creators. From here, you can:
|
||||
<ul>
|
||||
<li><strong>Search and Queue</strong>: Search for creators and check multiple names. Clicking "Add Selected" populates the main input field, preparing a batch download.</li>
|
||||
<li><strong>Check for Updates</strong>: Select a single creator's saved profile. This loads their information and switches the main download button to "Check for Updates" mode, allowing you to download only new content since your last session.</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li><strong>Download Location</strong>: The primary folder where all content will be saved. The <strong>Browse...</strong> button lets you select this folder from your computer.</li>
|
||||
<li><strong>Page Range (Start/End)</strong>: These fields activate only for creator feed URLs. They allow you to download a specific slice of a creator's history (e.g., pages 5 through 10) instead of their entire feed.</li>
|
||||
<li><strong>Filter: Title</strong>: Matches names in the post title.</li>
|
||||
<li><strong>Filter: Files</strong>: Matches names in the filenames.</li>
|
||||
<li><strong>Filter: Both</strong>: Checks the title first, then filenames.</li>
|
||||
<li><strong>Filter: Comments</strong>: Checks filenames first, then post comments.</li>
|
||||
</ul>
|
||||
<hr>
|
||||
<h2><strong>Filtering & Naming (Left Panel)</strong></h2>
|
||||
<p>These features give you precise control over what gets downloaded and how it's named and organized.</p>
|
||||
</li>
|
||||
</ul>
|
||||
<h3>Skip with Words & Scope</h3>
|
||||
<p>Prevents downloading content based on keywords or file size.</p>
|
||||
<ul>
|
||||
<li><strong>Input Field</strong>: Enter comma-separated keywords (e.g., <code>WIP, sketch, preview</code>).</li>
|
||||
<li><strong>Skip by Size</strong>: Enter a number in square brackets to skip any file <strong>smaller than</strong> that size in MB. For example, <code>WIP, [200]</code> skips files with "WIP" in the name AND any file smaller than 200 MB.</li>
|
||||
<li><strong>Scope Button</strong>: Cycles through where to apply keyword filters:
|
||||
<ul>
|
||||
<li><strong>Filter by Character(s)</strong>: A powerful tool to download content featuring specific characters. You can enter multiple names separated by commas.
|
||||
<ul>
|
||||
<li><strong>Filter: [Scope] Button</strong>: This button changes how the character filter works:
|
||||
<ul>
|
||||
<li><strong>Title</strong>: Downloads posts only if a character's name is in the post title.</li>
|
||||
<li><strong>Files</strong>: Downloads posts if a character's name is in any of the filenames within the post.</li>
|
||||
<li><strong>Both</strong>: Combines the "Title" and "Files" logic.</li>
|
||||
<li><strong>Comments (Beta)</strong>: Downloads a post if a character's name is mentioned in the comments section.</li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li><strong>Skip with Words</strong>: A keyword-based filter to avoid unwanted content (e.g., <code>WIP</code>, <code>sketch</code>).
|
||||
<ul>
|
||||
<li><strong>Scope: [Type] Button</strong>: This button changes how the skip filter works:
|
||||
<ul>
|
||||
<li><strong>Posts</strong>: Skips the entire post if a keyword is found in the title.</li>
|
||||
<li><strong>Files</strong>: Skips only individual files if a keyword is found in the filename.</li>
|
||||
<li><strong>Both</strong>: Applies both levels of skipping.</li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li><strong>Remove Words from name</strong>: Automatically cleans downloaded filenames by removing any specified words (e.g., "patreon," "HD").</li>
|
||||
<li><strong>Scope: Posts</strong>: Skips the entire post if the title matches.</li>
|
||||
<li><strong>Scope: Files</strong>: Skips individual files if the filename matches.</li>
|
||||
<li><strong>Scope: Both</strong>: Checks the post title first, then individual files.</li>
|
||||
</ul>
|
||||
<h3><strong>File Type Filter (Radio Buttons)</strong></h3>
|
||||
<p>This section lets you choose the kind of content you want:</p>
|
||||
</li>
|
||||
</ul>
|
||||
<h3>Remove Words from Name (✂️)</h3>
|
||||
<p>Enter comma-separated words to remove from final filenames (e.g., <code>patreon, [HD]</code>). This helps clean up file naming.</p>
|
||||
<hr>
|
||||
<h2>3. Primary Download Modes (Filter File Section)</h2>
|
||||
<p>This section uses radio buttons to set the main download mode. Only one can be active at a time.</p>
|
||||
<ul>
|
||||
<li><strong>All</strong>: Default mode. Downloads every file and attachment.</li>
|
||||
<li><strong>Images/GIFs</strong>: Downloads only common image formats.</li>
|
||||
<li><strong>Videos</strong>: Downloads only common video formats.</li>
|
||||
<li><strong>Only Archives</strong>: Downloads only <code>.zip</code>, <code>.rar</code>, etc.</li>
|
||||
<li><strong>Only Audio</strong>: Downloads only common audio formats.</li>
|
||||
<li><strong>Only Links</strong>: Extracts external hyperlinks (e.g., Mega, Google Drive) from post descriptions instead of downloading files. <strong>This mode unlocks special features</strong> (see section 6).</li>
|
||||
<li><strong>More</strong>: Opens a dialog to download text-based content.
|
||||
<ul>
|
||||
<li><strong>All, Images/GIFs, Videos, 🎧 Only Audio, 📦 Only Archives</strong>: These options filter the downloads to only include the selected file types.</li>
|
||||
<li><strong>🔗 Only Links</strong>: This special mode doesn't download any files. Instead, it scans post descriptions and lists all external links (like Mega, Google Drive) in the log panel.</li>
|
||||
<li><strong>More</strong>: Opens a dialog for text-only downloads. You can choose to save post <strong>descriptions</strong> or <strong>comments</strong> as formatted <strong>PDF, DOCX, or TXT</strong> files. A key feature here is the <strong>"Single PDF"</strong> option, which compiles the text from all downloaded posts into one continuous, sorted PDF document.</li>
|
||||
<li><strong>Scope</strong>: Choose to extract text from the post description or comments.</li>
|
||||
<li><strong>Export Format</strong>: Save as PDF, DOCX, or TXT.</li>
|
||||
<li><strong>Single PDF</strong>: Compile all text from the session into one consolidated PDF file.</li>
|
||||
</ul>
|
||||
<hr>
|
||||
<h2><strong>Download Options & Advanced Settings (Checkboxes)</strong></h2>
|
||||
</li>
|
||||
</ul>
|
||||
<hr>
|
||||
<h2>4. Advanced Features & Toggles (Checkboxes)</h2>
|
||||
<h3>Folder Organization</h3>
|
||||
<ul>
|
||||
<li><strong>Separate folders by Known.txt</strong>: Automatically organizes downloads into subfolders based on name matches from your <code>Known.txt</code> list or the "Filter by Character(s)" input.</li>
|
||||
<li><strong>Subfolder per post</strong>: Creates a unique folder for each post, named after the post's title. This prevents files from different posts from mixing.</li>
|
||||
<li><strong>Date prefix</strong>: (Only available with "Subfolder per post") Prepends the post date to the folder name (e.g., <code>2025-08-03 My Post Title</code>) for chronological sorting.</li>
|
||||
</ul>
|
||||
<h3>Special Modes</h3>
|
||||
<ul>
|
||||
<li><strong>⭐ Favorite Mode</strong>: Switches the UI to download from your personal favorites list instead of using the URL input.</li>
|
||||
<li><strong>Manga/Comic mode</strong>: Sorts a creator's posts from oldest to newest before downloading, ensuring correct page order. A scope button appears to control the filename style (e.g., using post title, date, or a global number).</li>
|
||||
</ul>
|
||||
<h3>File Handling</h3>
|
||||
<ul>
|
||||
<li><strong>Skip Archives</strong>: Ignores <code>.zip</code> and <code>.rar</code> files during downloads.</li>
|
||||
<li><strong>Download Thumbnail Only</strong>: Saves only the small preview images instead of full-resolution files.</li>
|
||||
<li><strong>Scan Content for Images</strong>: Parses post HTML to find embedded images that may not be listed in the API data.</li>
|
||||
<li><strong>Compress to WebP</strong>: Converts large images (over 1.5 MB) to the space-saving WebP format.</li>
|
||||
<li><strong>Keep Duplicates</strong>: Opens a dialog to control how duplicate files are handled (skip by default, keep all, or keep a specific number of copies).</li>
|
||||
</ul>
|
||||
<h3>General Functionality</h3>
|
||||
<ul>
|
||||
<li><strong>Use cookie</strong>: Enables login-based access. You can paste a cookie string or browse for a <code>cookies.txt</code> file.</li>
|
||||
<li><strong>Use Multithreading</strong>: Enables parallel processing of posts for faster downloads. You can set the number of concurrent worker threads.</li>
|
||||
<li><strong>Show external links in log</strong>: Opens a secondary log panel that displays external links found in post descriptions.</li>
|
||||
</ul>
|
||||
<hr>
|
||||
<h2>5. Specialized Downloaders & Batch Mode</h2>
|
||||
<h3>Discord Features</h3>
|
||||
<ul>
|
||||
<li>When a Discord URL is entered, a <strong>Scope</strong> button appears.
|
||||
<ul>
|
||||
<li><strong>Skip .zip</strong>: A simple toggle to ignore archive files during downloads.</li>
|
||||
<li><strong>Download Thumbnails Only</strong>: Downloads only the small preview images instead of the full-resolution files.</li>
|
||||
<li><strong>Scan Content for Images</strong>: A crucial feature that scans the post's text content for embedded images that may not be listed in the API, ensuring a more complete download.</li>
|
||||
<li><strong>Compress to WebP</strong>: Saves disk space by automatically converting large images into the efficient WebP format.</li>
|
||||
<li><strong>Keep Duplicates</strong>: Opens a dialog to control how files with identical content are handled. The default is to skip duplicates, but you can choose to keep all of them or set a specific limit (e.g., "keep up to 2 copies of the same file").</li>
|
||||
<li><strong>Subfolder per Post</strong>: Organizes downloads by creating a unique folder for each post, named after the post's title.</li>
|
||||
<li><strong>Date Prefix</strong>: When "Subfolder per Post" is on, this adds the post's date to the beginning of the folder name (e.g., <code>2025-07-25 Post Title</code>).</li>
|
||||
<li><strong>Separate Folders by Known.txt</strong>: This enables the automatic folder organization system based on your "Known Names" list.</li>
|
||||
<li><strong>Use Cookie</strong>: Allows the application to use browser cookies to access content that might be behind a paywall or login. You can paste a cookie string directly or use <strong>Browse...</strong> to select a <code>cookies.txt</code> file.</li>
|
||||
<li><strong>Use Multithreading</strong>: Greatly speeds up downloads of creator feeds by processing multiple posts at once. The number of <strong>Threads</strong> can be configured.</li>
|
||||
<li><strong>Show External Links in Log</strong>: When checked, a secondary log panel appears at the bottom of the right side, dedicated to listing any external links found.</li>
|
||||
<li><strong>Scope: Files</strong>: Downloads all files from the channel/server.</li>
|
||||
<li><strong>Scope: Messages</strong>: Saves the entire message history of the channel/server as a formatted PDF.</li>
|
||||
</ul>
|
||||
<hr>
|
||||
<h2><strong>Known Names Management (Bottom-Left)</strong></h2>
|
||||
<p>This powerful feature automates the creation of organized, named folders.</p>
|
||||
</li>
|
||||
<li>A <strong>"Save as PDF"</strong> button also appears as a shortcut for the message saving feature.</li>
|
||||
</ul>
|
||||
<h3>Batch Downloading (<code>nhentai</code> & <code>saint2.su</code>)</h3>
|
||||
<p>This feature allows you to download hundreds of galleries or videos from a simple text file.</p>
|
||||
<ol>
|
||||
<li>In the <code>appdata</code> folder, create <code>nhentai.txt</code> or <code>saint2.su.txt</code>.</li>
|
||||
<li>Add one full URL per line to the corresponding file.</li>
|
||||
<li>In the app's URL input, type either <code>nhentai.net</code> or <code>saint2.su</code> and click "Start Download".</li>
|
||||
<li>The app will read the file and process every URL in the queue.</li>
|
||||
</ol>
|
||||
<hr>
|
||||
<h2>6. "Only Links" Mode: Extraction & Direct Download</h2>
|
||||
<p>When you select the <strong>"Only Links"</strong> radio button, the application's behavior changes significantly.</p>
|
||||
<ul>
|
||||
<li><strong>Link Extraction</strong>: Instead of downloading files, the main log panel will fill with all external links found (Mega, Google Drive, Dropbox, etc.).</li>
|
||||
<li><strong>Export Links</strong>: An "Export Links" button appears, allowing you to save the full list of extracted URLs to a <code>.txt</code> file.</li>
|
||||
<li><strong>Direct Cloud Download</strong>: A <strong>"Download"</strong> button appears next to the export button.
|
||||
<ul>
|
||||
<li><strong>Known Shows/Characters List</strong>: Displays all the names and groups you've saved.</li>
|
||||
<li><strong>Search...</strong>: Filters the list to quickly find a name.</li>
|
||||
<li><strong>Open Known.txt</strong>: Opens the source file in a text editor for advanced manual editing.</li>
|
||||
<li><strong>Add New Name</strong>:
|
||||
<ul>
|
||||
<li><strong>Single Name</strong>: Typing <code>Tifa Lockhart</code> and clicking <strong>➕ Add</strong> creates an entry that will match "Tifa Lockhart".</li>
|
||||
<li><strong>Group</strong>: Typing <code>(Boa, Hancock, Snake Princess)~</code> and clicking <strong>➕ Add</strong> creates a single entry named "Boa Hancock Snake Princess". The application will then look for "Boa," "Hancock," OR "Snake Princess" in titles/filenames and save any matches into that combined folder.</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li><strong>⤵️ Add to Filter</strong>: Opens a dialog with your full Known Names list, allowing you to check multiple entries and add them all to the "Filter by Character(s)" field at once.</li>
|
||||
<li><strong>🗑️ Delete Selected</strong>: Removes highlighted names from your list.</li>
|
||||
<li>Clicking this opens a new dialog listing all supported cloud links (Mega, G-Drive, Dropbox).</li>
|
||||
<li>You can select which files you want to download from this list.</li>
|
||||
<li>The application will then download the selected files directly from the cloud service to your chosen download location.</li>
|
||||
</ul>
|
||||
<hr>
|
||||
<h2><strong>Action Buttons & Status Controls</strong></h2>
|
||||
<ul>
|
||||
<li><strong>⬇️ Start Download / 🔗 Extract Links</strong>: The main action button. Its function is dynamic:
|
||||
<ul>
|
||||
<li><strong>Normal Mode</strong>: Starts the download based on the current settings.</li>
|
||||
<li><strong>Update Mode</strong>: After selecting a creator profile, this button changes to <strong>🔄 Check for Updates</strong>.</li>
|
||||
<li><strong>Update Confirmation</strong>: After new posts are found, it changes to <strong>⬇️ Start Download (X new)</strong>.</li>
|
||||
<li><strong>Link Extraction Mode</strong>: The text changes to <strong>🔗 Extract Links</strong>.</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li><strong>⏸️ Pause / ▶️ Resume Download</strong>: Pauses the ongoing download, allowing you to change certain settings (like filters) on the fly. Click again to resume.</li>
|
||||
<li><strong>❌ Cancel & Reset UI</strong>: Immediately stops all download activity and resets the UI to a clean state, preserving your URL and Download Location inputs.</li>
|
||||
<li><strong>Error Button</strong>: If files fail to download, they are logged. This button opens a dialog listing all failed files and will show a count of errors (e.g., <strong>(5) Error</strong>). From the dialog, you can:
|
||||
<ul>
|
||||
<li>Select specific files to <strong>Retry</strong> downloading.</li>
|
||||
<li><strong>Export</strong> the list of failed URLs to a <code>.txt</code> file.</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li><strong>🔄 Reset (Top-Right)</strong>: A hard reset that clears all logs and returns every single UI element to its default state.</li>
|
||||
<li><strong>⚙️ (Settings)</strong>: Opens the main Settings dialog.</li>
|
||||
<li><strong>📜 (History)</strong>: Opens the Download History dialog.</li>
|
||||
<li><strong>? (Help)</strong>: Opens a helpful guide explaining the application's features.</li>
|
||||
<li><strong>❤️ Support</strong>: Opens a dialog with information on how to support the developer.</li>
|
||||
</ul>
|
||||
<hr>
|
||||
<h2><strong>Specialized Modes & Features</strong></h2>
|
||||
<h3><strong>⭐ Favorite Mode</strong></h3>
|
||||
<p>Activating this mode transforms the UI for managing saved collections:</p>
|
||||
<ul>
|
||||
<li>The URL input is disabled.</li>
|
||||
<li>The main action buttons are replaced with:
|
||||
<ul>
|
||||
<li><strong>🖼️ Favorite Artists</strong>: Opens a dialog to browse and queue downloads from your saved favorite creators.</li>
|
||||
<li><strong>📄 Favorite Posts</strong>: Opens a dialog to browse and queue downloads for specific saved favorite posts.</li>
|
||||
</ul>
|
||||
</li>
|
||||
<li><strong>Scope: [Location] Button</strong>: Toggles where the favorited content is saved:
|
||||
<ul>
|
||||
<li><strong>Selected Location</strong>: Saves all content directly into the main "Download Location".</li>
|
||||
<li><strong>Artist Folders</strong>: Creates a subfolder for each artist inside the main "Download Location".</li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
<h3><strong>📖 Manga/Comic Mode</strong></h3>
|
||||
<p>This mode is designed for sequential content and has several effects:</p>
|
||||
<ul>
|
||||
<li><strong>Reverses Download Order</strong>: It fetches and downloads posts from <strong>oldest to newest</strong>.</li>
|
||||
<li><strong>Enables Special Naming</strong>: A <strong><code>Name: [Style]</code></strong> button appears, allowing you to choose how files are named to maintain their correct order (e.g., by Post Title, by Date, or simple sequential numbering like <code>001, 002, 003...</code>).</li>
|
||||
<li><strong>Disables Multithreading (for certain styles)</strong>: To guarantee perfect sequential numbering, multithreading for posts is automatically disabled for certain naming styles.</li>
|
||||
</ul>
|
||||
<h3><strong>Session & Error Management</strong></h3>
|
||||
<ul>
|
||||
<li><strong>Session Restore</strong>: If the application is closed unexpectedly during a download, it will detect the incomplete session on the next launch. The UI will present a <strong>🔄 Restore Download</strong> button to resume exactly where you left off. You can also choose to discard the session.</li>
|
||||
<li><strong>Update Checking</strong>: By selecting a creator profile via the <strong>🎨 Creator Selection Popup</strong>, you can run an update check. The application compares the posts on the server with your download history for that creator and will prompt you to download only the new content.</li>
|
||||
</ul>
|
||||
<h3><strong>Logging & Monitoring</strong></h3>
|
||||
<ul>
|
||||
<li><strong>Progress Log</strong>: The main log provides real-time feedback on the download process, including status messages, file saves, skips, and errors.</li>
|
||||
<li><strong>👁️ Log View Toggle</strong>: Switches the log view between the standard <strong>Progress Log</strong> and a <strong>Missed Character Log</strong>, which shows potential character names from posts that were skipped by your filters, helping you discover new names to add to your list.</li>
|
||||
</ul>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
<hr>
|
||||
<h2>7. Session & Process Management</h2>
|
||||
<h3>Main Action Buttons</h3>
|
||||
<ul>
|
||||
<li><strong>Start Download</strong>: Begins the download process. This button's text changes contextually (e.g., "Extract Links", "Check for Updates").</li>
|
||||
<li><strong>Pause / Resume</strong>: Pauses or resumes the ongoing download. When paused, you can safely change some settings.</li>
|
||||
<li><strong>Cancel & Reset UI</strong>: Stops the current download and performs a soft reset of the UI, preserving your URL and download location.</li>
|
||||
</ul>
|
||||
<h3>Restore Interrupted Download</h3>
|
||||
<p>If the application is closed unexpectedly during a download, it will save its progress.</p>
|
||||
<ul>
|
||||
<li>On the next launch, the UI will be pre-filled with the settings from the interrupted session.</li>
|
||||
<li>The <strong>Pause</strong> button will change to <strong>"🔄 Restore Download"</strong>. Clicking it will resume the download exactly where it left off, skipping already processed posts.</li>
|
||||
<li>The <strong>Cancel</strong> button will change to <strong>"🗑️ Discard Session"</strong>, allowing you to clear the saved state and start fresh.</li>
|
||||
</ul>
|
||||
<h3>Other UI Controls</h3>
|
||||
<ul>
|
||||
<li><strong>Error Button</strong>: Shows a count of failed files. Clicking it opens a dialog where you can view, export, or retry the failed downloads.</li>
|
||||
<li><strong>History Button</strong>: Shows a log of recently downloaded files and processed posts.</li>
|
||||
<li><strong>Settings Button</strong>: Opens the settings dialog where you can change the theme, language, and <strong>check for application updates</strong>.</li>
|
||||
<li><strong>Support Button</strong>: Opens a dialog with links to the project's source code and developer support pages.</li>
|
||||
</ul>
|
||||
|
||||
303
readme.md
303
readme.md
@@ -1,217 +1,116 @@
|
||||
<h1 align="center">Kemono Downloader v6.0.0</h1>
|
||||
<h1 align="center">Kemono Downloader</h1>
|
||||
|
||||
<div align="center">
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<td align="center">
|
||||
<img src="Read/Read.png" alt="Default Mode" width="400"><br>
|
||||
<strong>Default</strong>
|
||||
</td>
|
||||
<td align="center">
|
||||
<img src="Read/Read1.png" alt="Favorite Mode" width="400"><br>
|
||||
<strong>Favorite Mode</strong>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">
|
||||
<img src="Read/Read2.png" alt="Single Post" width="400"><br>
|
||||
<strong>Single Post</strong>
|
||||
</td>
|
||||
<td align="center">
|
||||
<img src="Read/Read3.png" alt="Manga/Comic Mode" width="400"><br>
|
||||
<strong>Manga/Comic Mode</strong>
|
||||
</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
<table>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td align="center">
|
||||
<img src="Read/Read.png" alt="Default Mode" width="400"><br>
|
||||
<strong>Default Mode</strong>
|
||||
</td>
|
||||
<td align="center">
|
||||
<img src="Read/Read1.png" alt="Favorite Mode" width="400"><br>
|
||||
<strong>Favorite Mode</strong>
|
||||
</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td align="center">
|
||||
<img src="Read/Read2.png" alt="Single Post" width="400"><br>
|
||||
<strong>Single Post</strong>
|
||||
</td>
|
||||
<td align="center">
|
||||
<img src="Read/Read3.png" alt="Manga/Comic Mode" width="400"><br>
|
||||
<strong>Manga/Comic Mode</strong>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</div>
|
||||
|
||||
---
|
||||
<hr>
|
||||
|
||||
A powerful, feature-rich GUI application for downloading content from **[Kemono.su](https://kemono.su)** (and its mirrors like kemono.party) and **[Coomer.party](https://coomer.party)** (and its mirrors like coomer.su).
|
||||
|
||||
Built with PyQt5, this tool is designed for users who want deep filtering capabilities, customizable folder structures, efficient downloads, and intelligent automation — all within a modern and user-friendly graphical interface.
|
||||
<p>A powerful, feature-rich GUI application for downloading content from a wide array of sites, including <strong>Kemono</strong>, <strong>Coomer</strong>, <strong>Bunkr</strong>, <strong>Erome</strong>, <strong>Saint2.su</strong>, and <strong>nhentai</strong>.</p>
|
||||
<p>Built with PyQt5, this tool is designed for users who want deep filtering capabilities, customizable folder structures, efficient downloads, and intelligent automation — all within a modern and user-friendly graphical interface.</p>
|
||||
|
||||
<div align="center">
|
||||
|
||||
[](features.md)
|
||||
[](LICENSE)
|
||||
[](note.md)
|
||||
|
||||
<a href="features.md"><img src="https://img.shields.io/badge/📚%20Full%20Feature%20List-FFD700?style=for-the-badge&logoColor=black&color=FFD700" alt="Full Feature List"></a>
|
||||
<a href="LICENSE"><img src="https://img.shields.io/badge/📝%20License-90EE90?style=for-the-badge&logoColor=black&color=90EE90" alt="License"></a>
|
||||
<a href="note.md"><img src="https://img.shields.io/badge/⚠️%20Important%20Note-FFCCCB?style=for-the-badge&logoColor=black&color=FFCCCB" alt="Important Note"></a>
|
||||
</div>
|
||||
|
||||
|
||||
---
|
||||
|
||||
## Feature Overview
|
||||
|
||||
Kemono Downloader offers a range of features to streamline your content downloading experience:
|
||||
|
||||
- **User-Friendly Interface:** A modern PyQt5 GUI for easy navigation and operation.
|
||||
|
||||
- **Flexible Downloading:**
|
||||
- Download content from Kemono.su (and mirrors) and Coomer.party (and mirrors).
|
||||
- Supports creator pages (with page range selection) and individual post URLs.
|
||||
- Standard download controls: Start, Pause, Resume, and Cancel.
|
||||
|
||||
- **Powerful Filtering:**
|
||||
- **Character Filtering:** Filter content by character names. Supports simple comma-separated names and grouped names for shared folders.
|
||||
- **Keyword Skipping:** Skip posts or files based on specified keywords.
|
||||
- **Filename Cleaning:** Remove unwanted words or phrases from downloaded filenames.
|
||||
- **File Type Selection:** Choose to download all files, or limit to images/GIFs, videos, audio, or archives. Can also extract external links only.
|
||||
|
||||
- **Customizable Downloads:**
|
||||
- **Thumbnails Only:** Option to download only small preview images.
|
||||
- **Content Scanning:** Scan post HTML for `<img>` tags and direct image links, useful for images embedded in descriptions.
|
||||
- **WebP Conversion:** Convert images to WebP format for smaller file sizes (requires Pillow library).
|
||||
|
||||
- **Organized Output:**
|
||||
- **Automatic Subfolders:** Create subfolders based on character names (from filters or `Known.txt`) or post titles.
|
||||
- **Per-Post Subfolders:** Option to create an additional subfolder for each individual post.
|
||||
|
||||
- **Manga/Comic Mode:**
|
||||
- Downloads posts from a creator's feed in chronological order (oldest to newest).
|
||||
- Offers various filename styling options for sequential reading (e.g., post title, original name, global numbering).
|
||||
|
||||
- **⭐ Favorite Mode:**
|
||||
- Directly download from your favorited artists and posts on Kemono.su.
|
||||
- Requires a valid cookie and adapts the UI for easy selection from your favorites.
|
||||
- Supports downloading into a single location or artist-specific subfolders.
|
||||
|
||||
- **Performance & Advanced Options:**
|
||||
- **Cookie Support:** Use cookies (paste string or load from `cookies.txt`) to access restricted content.
|
||||
- **Multithreading:** Configure the number of simultaneous downloads/post processing threads for improved speed.
|
||||
|
||||
- **Logging:**
|
||||
- A detailed progress log displays download activity, errors, and summaries.
|
||||
|
||||
- **Multi-language Interface:** Choose from several languages for the UI (English, Japanese, French, Spanish, German, Russian, Korean, Chinese Simplified).
|
||||
|
||||
- **Theme Customization:** Selectable Light and Dark themes for user comfort.
|
||||
|
||||
---
|
||||
|
||||
## ✨ What's New in v6.0.0
|
||||
|
||||
This release focuses on providing more granular control over file organization and improving at-a-glance status monitoring.
|
||||
|
||||
### New Features
|
||||
|
||||
- **Live Error Count on Button**
|
||||
The **"Error" button** now dynamically displays the number of failed files during a download. Instead of opening the dialog, you can quickly see a live count like `(3) Error`, helping you track issues at a glance.
|
||||
|
||||
- **Date Prefix for Post Subfolders**
|
||||
A new checkbox labeled **"Date Prefix"** is now available in the advanced settings.
|
||||
When enabled alongside **"Subfolder per Post"**, it prepends the post's upload date to the folder name (e.g., `2025-07-11 Post Title`).
|
||||
This makes your downloads sortable and easier to browse chronologically.
|
||||
|
||||
- **Keep Duplicates Within a Post**
|
||||
A **"Keep Duplicates"** option has been added to preserve all files from a post — even if some have the same name.
|
||||
Instead of skipping or overwriting, the downloader will save duplicates with numbered suffixes (e.g., `image.jpg`, `image_1.jpg`, etc.), which is especially useful when the same file name points to different media.
|
||||
|
||||
### Bug Fixes
|
||||
|
||||
- The downloader now correctly renames large `.part` files when completed, avoiding leftover temp files.
|
||||
- The list of failed files shown in the Error Dialog is now saved and restored with your session — so no errors get lost if you close the app.
|
||||
- Your selected download location is remembered, even after pressing the **Reset** button.
|
||||
- The **Cancel** button is now enabled when restoring a pending session, so you can abort stuck jobs more easily.
|
||||
- Internal cleanup logs (like "Deleting post cache") are now excluded from the final download summary for clarity.
|
||||
|
||||
---
|
||||
|
||||
## 📅 Next Update Plans
|
||||
|
||||
### 🔖 Post Tag Filtering (Planned for v6.1.0)
|
||||
|
||||
A powerful new **"Filter by Post Tags"** feature is planned:
|
||||
|
||||
- Filter and download content based on specific post tags.
|
||||
- Combine tag filtering with current filters (character, file type, etc.).
|
||||
- Use tag presets to automate frequent downloads.
|
||||
|
||||
This will provide **much greater control** over what gets downloaded, especially for creators who use tags consistently.
|
||||
|
||||
### 📁 Creator Download History (.json Save)
|
||||
|
||||
To streamline incremental downloads, a new system will allow the app to:
|
||||
|
||||
- Save a `.json` file with metadata about already-downloaded posts.
|
||||
- Compare that file on future runs, so only **new** posts are downloaded.
|
||||
- Avoids duplication and makes regular syncs fast and efficient.
|
||||
|
||||
Ideal for users managing large collections or syncing favorites regularly.
|
||||
|
||||
---
|
||||
|
||||
## 💻 Installation
|
||||
|
||||
### Requirements
|
||||
|
||||
- Python 3.6 or higher
|
||||
- pip (Python package installer)
|
||||
|
||||
### Install Dependencies
|
||||
|
||||
```bash
|
||||
pip install PyQt5 requests Pillow mega.py
|
||||
```
|
||||
|
||||
### Running the Application
|
||||
Navigate to the application's directory in your terminal and run:
|
||||
```bash
|
||||
python main.py
|
||||
```
|
||||
|
||||
### Optional Setup
|
||||
- **Main Inputs:**
|
||||
- Place your `cookies.txt` in the root directory (if using cookies).
|
||||
- Prepare your `Known.txt` and `creators.json` in the same directory for advanced filtering and selection features.
|
||||
|
||||
---
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### AttributeError: module 'asyncio' has no attribute 'coroutine'
|
||||
|
||||
If you encounter an error message similar to:
|
||||
```
|
||||
AttributeError: module 'asyncio' has no attribute 'coroutine'. Did you mean: 'coroutines'?
|
||||
```
|
||||
This usually means that a dependency, often `tenacity` (used by `mega.py`), is an older version that's incompatible with your Python version (typically Python 3.10+).
|
||||
|
||||
To fix this, activate your virtual environment and run the following commands to upgrade the libraries:
|
||||
|
||||
```bash
|
||||
pip install --upgrade tenacity
|
||||
pip install --upgrade mega.py
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Contribution
|
||||
|
||||
Feel free to fork this repo and submit pull requests for bug fixes, new features, or UI improvements!
|
||||
|
||||
---
|
||||
|
||||
## License
|
||||
|
||||
This project is under the Custom Licence
|
||||
|
||||
## Star History
|
||||
|
||||
<h2>Core Capabilities Overview</h2>
|
||||
<h3>High-Performance & Resilient Downloading</h3>
|
||||
<ul>
|
||||
<li><strong>Multi-threading:</strong> Processes multiple posts simultaneously to greatly accelerate downloads from large creator profiles.</li>
|
||||
<li><strong>Multi-part Downloading:</strong> Splits large files into chunks and downloads them in parallel to maximize speed.</li>
|
||||
<li><strong>Session Management:</strong> Supports pausing, resuming, and <strong>restoring downloads</strong> after crashes or interruptions, so you never lose your progress.</li>
|
||||
</ul>
|
||||
<h3>Expanded Site Support</h3>
|
||||
<ul>
|
||||
<li><strong>Direct Downloading:</strong> Full support for Kemono, Coomer, Bunkr, Erome, Saint2.su, and nhentai.</li>
|
||||
<li><strong>Batch Mode:</strong> Download hundreds of URLs at once from <code>nhentai.txt</code> or <code>saint2.su.txt</code> files.</li>
|
||||
<li><strong>Discord Support:</strong> Download files or save entire channel histories as PDFs directly through the API.</li>
|
||||
</ul>
|
||||
<h3>Advanced Filtering & Content Control</h3>
|
||||
<ul>
|
||||
<li><strong>Content Type Filtering:</strong> Select whether to download all files or limit to images, videos, audio, or archives only.</li>
|
||||
<li><strong>Keyword Skipping:</strong> Automatically skips posts or files containing certain keywords (e.g., "WIP", "sketch").</li>
|
||||
<li><strong>Skip by Size:</strong> Avoid small files by setting a minimum size threshold in MB (e.g., <code>[200]</code>).</li>
|
||||
<li><strong>Character Filtering:</strong> Restricts downloads to posts that match specific character or series names, with scope controls for title, filename, or comments.</li>
|
||||
</ul>
|
||||
<h3>Intelligent File Organization</h3>
|
||||
<ul>
|
||||
<li><strong>Automated Subfolders:</strong> Automatically organizes downloaded files into subdirectories based on character names or per post.</li>
|
||||
<li><strong>Advanced File Renaming:</strong> Flexible renaming options, especially in Manga Mode, including by post title, date, sequential numbering, or post ID.</li>
|
||||
<li><strong>Filename Cleaning:</strong> Automatically removes unwanted text from filenames.</li>
|
||||
</ul>
|
||||
<h3>Specialized Modes</h3>
|
||||
<ul>
|
||||
<li><strong>Manga/Comic Mode:</strong> Sorts posts chronologically before downloading to ensure pages appear in the correct sequence.</li>
|
||||
<li><strong>Favorite Mode:</strong> Connects to your account and downloads from your favorites list (artists or posts).</li>
|
||||
<li><strong>Link Extraction Mode:</strong> Extracts external links (Mega, Google Drive) from posts for export or <strong>direct in-app downloading</strong>.</li>
|
||||
<li><strong>Text Extraction Mode:</strong> Saves post descriptions or comment sections as <code>PDF</code>, <code>DOCX</code>, or <code>TXT</code> files.</li>
|
||||
</ul>
|
||||
<h3>Utility & Advanced Features</h3>
|
||||
<ul>
|
||||
<li><strong>In-App Updater:</strong> Check for new versions directly from the settings menu.</li>
|
||||
<li><strong>Cookie Support:</strong> Enables access to subscriber-only content via browser session cookies.</li>
|
||||
<li><strong>Duplicate Detection:</strong> Prevents saving duplicate files using content-based comparison, with configurable limits.</li>
|
||||
<li><strong>Image Compression:</strong> Automatically converts large images to <code>.webp</code> to reduce disk usage.</li>
|
||||
<li><strong>Creator Management:</strong> Built-in creator browser and update checker for downloading only new posts from saved profiles.</li>
|
||||
<li><strong>Error Handling:</strong> Tracks failed downloads and provides a retry dialog with options to export or redownload missing files.</li>
|
||||
</ul>
|
||||
<h2>💻 Installation</h2>
|
||||
<h3>Requirements</h3>
|
||||
<ul>
|
||||
<li>Python 3.6 or higher</li>
|
||||
<li>pip (Python package installer)</li>
|
||||
</ul>
|
||||
<h3>Install Dependencies</h3>
|
||||
<pre><code>pip install PyQt5 requests cloudscraper Pillow fpdf2 python-docx
|
||||
</code></pre>
|
||||
<h3>Running the Application</h3>
|
||||
<p>Navigate to the application's directory in your terminal and run:</p>
|
||||
<pre><code>python main.py
|
||||
</code></pre>
|
||||
<h2>Contribution</h2>
|
||||
<p>Feel free to fork this repo and submit pull requests for bug fixes, new features, or UI improvements!</p>
|
||||
<h2>License</h2>
|
||||
<p>This project is under the MIT Licence</p>
|
||||
<h2>Star History</h2>
|
||||
<table align="center" style="border-collapse: collapse; border: none; margin-left: auto; margin-right: auto;">
|
||||
<tr>
|
||||
<td align="center" valign="middle" style="padding: 10px; border: none;">
|
||||
<a href="https://www.star-history.com/#Yuvi9587/Kemono-Downloader&Date">
|
||||
<img src="https://api.star-history.com/svg?repos=Yuvi9587/Kemono-Downloader&type=Date" alt="Star History Chart" width="650">
|
||||
</a>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td align="center" valign="middle" style="padding: 10px; border: none;">
|
||||
<a href="https://www.star-history.com/#Yuvi9587/Kemono-Downloader&Date">
|
||||
<img src="https://api.star-history.com/svg?repos=Yuvi9587/Kemono-Downloader&type=Date" alt="Star History Chart" width="650">
|
||||
</a>
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
<p align="center">
|
||||
<a href="https://buymeacoffee.com/yuvi9587">
|
||||
<img src="https://img.shields.io/badge/🍺%20Buy%20Me%20a%20Coffee-FFCCCB?style=for-the-badge&logoColor=black&color=FFDD00" alt="Buy Me a Coffee">
|
||||
<img src="https://img.shields.io/badge/🍺%20Buy%20Me%20a%20Coffee-FFCCCB?style=for-the-badge&logoColor=black&color=FFDD00" alt="Buy Me a Coffee">
|
||||
</a>
|
||||
</p>
|
||||
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
# --- Application Metadata ---
|
||||
CONFIG_ORGANIZATION_NAME = "KemonoDownloader"
|
||||
CONFIG_APP_NAME_MAIN = "ApplicationSettings"
|
||||
CONFIG_APP_NAME_TOUR = "ApplicationTour"
|
||||
@@ -9,7 +8,7 @@ STYLE_ORIGINAL_NAME = "original_name"
|
||||
STYLE_DATE_BASED = "date_based"
|
||||
STYLE_DATE_POST_TITLE = "date_post_title"
|
||||
STYLE_POST_TITLE_GLOBAL_NUMBERING = "post_title_global_numbering"
|
||||
STYLE_POST_ID = "post_id" # Add this line
|
||||
STYLE_POST_ID = "post_id"
|
||||
MANGA_DATE_PREFIX_DEFAULT = ""
|
||||
|
||||
# --- Download Scopes ---
|
||||
@@ -60,6 +59,10 @@ DOWNLOAD_LOCATION_KEY = "downloadLocationV1"
|
||||
RESOLUTION_KEY = "window_resolution"
|
||||
UI_SCALE_KEY = "ui_scale_factor"
|
||||
SAVE_CREATOR_JSON_KEY = "saveCreatorJsonProfile"
|
||||
FETCH_FIRST_KEY = "fetchAllPostsFirst"
|
||||
DISCORD_TOKEN_KEY = "discord/token"
|
||||
|
||||
POST_DOWNLOAD_ACTION_KEY = "postDownloadAction"
|
||||
|
||||
# --- UI Constants and Identifiers ---
|
||||
HTML_PREFIX = "<!HTML!>"
|
||||
@@ -97,7 +100,7 @@ FOLDER_NAME_STOP_WORDS = {
|
||||
"for", "he", "her", "his", "i", "im", "in", "is", "it", "its",
|
||||
"me", "my", "net", "not", "of", "on", "or", "org", "our",
|
||||
"s", "she", "so", "the", "their", "they", "this",
|
||||
"to", "ve", "was", "we", "were", "with", "www", "you", "your",
|
||||
"to", "ve", "was", "we", "were", "with", "www", "you", "your", "nsfw", "sfw",
|
||||
# add more according to need
|
||||
}
|
||||
|
||||
@@ -111,10 +114,12 @@ CREATOR_DOWNLOAD_DEFAULT_FOLDER_IGNORE_WORDS = {
|
||||
"may", "jun", "june", "jul", "july", "aug", "august", "sep", "september",
|
||||
"oct", "october", "nov", "november", "dec", "december",
|
||||
"mon", "monday", "tue", "tuesday", "wed", "wednesday", "thu", "thursday",
|
||||
"fri", "friday", "sat", "saturday", "sun", "sunday"
|
||||
"fri", "friday", "sat", "saturday", "sun", "sunday", "Pack", "tier", "spoiler",
|
||||
|
||||
|
||||
# add more according to need
|
||||
}
|
||||
|
||||
# --- Duplicate Handling Modes ---
|
||||
DUPLICATE_HANDLING_HASH = "hash"
|
||||
DUPLICATE_HANDLING_KEEP_ALL = "keep_all"
|
||||
DUPLICATE_HANDLING_KEEP_ALL = "keep_all"
|
||||
72
src/core/Hentai2read_client.py
Normal file
72
src/core/Hentai2read_client.py
Normal file
@@ -0,0 +1,72 @@
|
||||
# src/core/Hentai2read_client.py
|
||||
|
||||
import re
|
||||
import os
|
||||
import json
|
||||
import requests
|
||||
import cloudscraper
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
def fetch_hentai2read_data(url, logger, session):
|
||||
"""
|
||||
Scrapes a SINGLE Hentai2Read chapter page using a provided session.
|
||||
"""
|
||||
logger(f"Attempting to fetch chapter data from: {url}")
|
||||
|
||||
try:
|
||||
response = session.get(url, timeout=30)
|
||||
response.raise_for_status()
|
||||
|
||||
page_content_text = response.text
|
||||
soup = BeautifulSoup(page_content_text, 'html.parser')
|
||||
|
||||
album_title = ""
|
||||
title_tags = soup.select('span[itemprop="name"]')
|
||||
if title_tags:
|
||||
album_title = title_tags[-1].text.strip()
|
||||
|
||||
if not album_title:
|
||||
title_tag = soup.select_one('h1.title')
|
||||
if title_tag:
|
||||
album_title = title_tag.text.strip()
|
||||
|
||||
if not album_title:
|
||||
logger("❌ Could not find album title on page.")
|
||||
return None, None
|
||||
|
||||
image_urls = []
|
||||
try:
|
||||
start_index = page_content_text.index("'images' : ") + len("'images' : ")
|
||||
end_index = page_content_text.index(",\n", start_index)
|
||||
images_json_str = page_content_text[start_index:end_index]
|
||||
image_paths = json.loads(images_json_str)
|
||||
image_urls = ["https://hentaicdn.com/hentai" + part for part in image_paths]
|
||||
except (ValueError, json.JSONDecodeError):
|
||||
logger("❌ Could not find or parse image JSON data for this chapter.")
|
||||
return None, None
|
||||
|
||||
if not image_urls:
|
||||
logger("❌ No image URLs found for this chapter.")
|
||||
return None, None
|
||||
|
||||
logger(f" Found {len(image_urls)} images for album '{album_title}'.")
|
||||
|
||||
files_to_download = []
|
||||
for i, img_url in enumerate(image_urls):
|
||||
page_num = i + 1
|
||||
extension = os.path.splitext(img_url)[1].split('?')[0]
|
||||
if not extension: extension = ".jpg"
|
||||
filename = f"{page_num:03d}{extension}"
|
||||
files_to_download.append({'url': img_url, 'filename': filename})
|
||||
|
||||
return album_title, files_to_download
|
||||
|
||||
except requests.exceptions.HTTPError as e:
|
||||
if e.response.status_code == 404:
|
||||
logger(f" Chapter not found (404 Error). This likely marks the end of the series.")
|
||||
else:
|
||||
logger(f"❌ An HTTP error occurred: {e}")
|
||||
return None, None
|
||||
except Exception as e:
|
||||
logger(f"❌ An unexpected error occurred while fetching data: {e}")
|
||||
return None, None
|
||||
@@ -1,8 +1,9 @@
|
||||
import time
|
||||
import traceback
|
||||
from urllib.parse import urlparse
|
||||
import json # Ensure json is imported
|
||||
import json
|
||||
import requests
|
||||
import cloudscraper
|
||||
from ..utils.network_utils import extract_post_info, prepare_cookies_for_request
|
||||
from ..config.constants import (
|
||||
STYLE_DATE_POST_TITLE
|
||||
@@ -12,7 +13,6 @@ from ..config.constants import (
|
||||
def fetch_posts_paginated(api_url_base, headers, offset, logger, cancellation_event=None, pause_event=None, cookies_dict=None):
|
||||
"""
|
||||
Fetches a single page of posts from the API with robust retry logic.
|
||||
NEW: Requests only essential fields to keep the response size small and reliable.
|
||||
"""
|
||||
if cancellation_event and cancellation_event.is_set():
|
||||
raise RuntimeError("Fetch operation cancelled by user.")
|
||||
@@ -33,7 +33,7 @@ def fetch_posts_paginated(api_url_base, headers, offset, logger, cancellation_ev
|
||||
if cancellation_event and cancellation_event.is_set():
|
||||
raise RuntimeError("Fetch operation cancelled by user during retry loop.")
|
||||
|
||||
log_message = f" Fetching post list: {api_url_base}?o={offset} (Page approx. {offset // 50 + 1})"
|
||||
log_message = f" Fetching post list: {paginated_url} (Page approx. {offset // 50 + 1})"
|
||||
if attempt > 0:
|
||||
log_message += f" (Attempt {attempt + 1}/{max_retries})"
|
||||
logger(log_message)
|
||||
@@ -41,9 +41,23 @@ def fetch_posts_paginated(api_url_base, headers, offset, logger, cancellation_ev
|
||||
try:
|
||||
response = requests.get(paginated_url, headers=headers, timeout=(15, 60), cookies=cookies_dict)
|
||||
response.raise_for_status()
|
||||
response.encoding = 'utf-8'
|
||||
return response.json()
|
||||
|
||||
except requests.exceptions.RequestException as e:
|
||||
# Handle 403 error on the FIRST page as a rate limit/block
|
||||
if e.response is not None and e.response.status_code == 403 and offset == 0:
|
||||
logger(" ❌ Access Denied (403 Forbidden) on the first page.")
|
||||
logger(" This is likely a rate limit or a Cloudflare block.")
|
||||
logger(" 💡 SOLUTION: Wait a while, use a VPN, or provide a valid session cookie.")
|
||||
return [] # Stop the process gracefully
|
||||
|
||||
# Handle 400 error as the end of pages
|
||||
if e.response is not None and e.response.status_code == 400:
|
||||
logger(f" ✅ Reached end of posts (API returned 400 Bad Request for offset {offset}).")
|
||||
return []
|
||||
|
||||
# Handle all other network errors with a retry
|
||||
logger(f" ⚠️ Retryable network error on page fetch (Attempt {attempt + 1}): {e}")
|
||||
if attempt < max_retries - 1:
|
||||
delay = retry_delay * (2 ** attempt)
|
||||
@@ -65,26 +79,28 @@ def fetch_posts_paginated(api_url_base, headers, offset, logger, cancellation_ev
|
||||
|
||||
raise RuntimeError(f"Failed to fetch page {paginated_url} after all attempts.")
|
||||
|
||||
|
||||
def fetch_single_post_data(api_domain, service, user_id, post_id, headers, logger, cookies_dict=None):
|
||||
"""
|
||||
--- NEW FUNCTION ---
|
||||
Fetches the full data, including the 'content' field, for a single post.
|
||||
--- MODIFIED FUNCTION ---
|
||||
Fetches the full data, including the 'content' field, for a single post using cloudscraper.
|
||||
"""
|
||||
post_api_url = f"https://{api_domain}/api/v1/{service}/user/{user_id}/post/{post_id}"
|
||||
logger(f" Fetching full content for post ID {post_id}...")
|
||||
|
||||
scraper = cloudscraper.create_scraper()
|
||||
|
||||
try:
|
||||
with requests.get(post_api_url, headers=headers, timeout=(15, 300), cookies=cookies_dict, stream=True) as response:
|
||||
response.raise_for_status()
|
||||
response_body = b""
|
||||
for chunk in response.iter_content(chunk_size=8192):
|
||||
response_body += chunk
|
||||
|
||||
full_post_data = json.loads(response_body)
|
||||
if isinstance(full_post_data, list) and full_post_data:
|
||||
return full_post_data[0]
|
||||
return full_post_data
|
||||
|
||||
response = scraper.get(post_api_url, headers=headers, timeout=(15, 300), cookies=cookies_dict)
|
||||
response.raise_for_status()
|
||||
|
||||
full_post_data = response.json()
|
||||
|
||||
if isinstance(full_post_data, list) and full_post_data:
|
||||
return full_post_data[0]
|
||||
if isinstance(full_post_data, dict) and 'post' in full_post_data:
|
||||
return full_post_data['post']
|
||||
return full_post_data
|
||||
|
||||
except Exception as e:
|
||||
logger(f" ❌ Failed to fetch full content for post {post_id}: {e}")
|
||||
return None
|
||||
@@ -101,6 +117,7 @@ def fetch_post_comments(api_domain, service, user_id, post_id, headers, logger,
|
||||
try:
|
||||
response = requests.get(comments_api_url, headers=headers, timeout=(10, 30), cookies=cookies_dict)
|
||||
response.raise_for_status()
|
||||
response.encoding = 'utf-8'
|
||||
return response.json()
|
||||
except requests.exceptions.RequestException as e:
|
||||
raise RuntimeError(f"Error fetching comments for post {post_id}: {e}")
|
||||
@@ -120,12 +137,18 @@ def download_from_api(
|
||||
selected_cookie_file=None,
|
||||
app_base_dir=None,
|
||||
manga_filename_style_for_sort_check=None,
|
||||
processed_post_ids=None # --- ADD THIS ARGUMENT ---
|
||||
):
|
||||
processed_post_ids=None,
|
||||
fetch_all_first=False
|
||||
):
|
||||
parsed_input_url_for_domain = urlparse(api_url_input)
|
||||
api_domain = parsed_input_url_for_domain.netloc
|
||||
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0',
|
||||
'Accept': 'application/json'
|
||||
'User-Agent': 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)',
|
||||
'Referer': f'https://{api_domain}/',
|
||||
'Accept': 'text/css'
|
||||
}
|
||||
|
||||
if processed_post_ids is None:
|
||||
processed_post_ids = set()
|
||||
else:
|
||||
@@ -137,11 +160,12 @@ def download_from_api(
|
||||
logger(" Download_from_api cancelled at start.")
|
||||
return
|
||||
|
||||
parsed_input_url_for_domain = urlparse(api_url_input)
|
||||
api_domain = parsed_input_url_for_domain.netloc
|
||||
if not any(d in api_domain.lower() for d in ['kemono.su', 'kemono.party', 'coomer.su', 'coomer.party']):
|
||||
# The code that defined api_domain was moved from here to the top of the function
|
||||
|
||||
if not any(d in api_domain.lower() for d in ['kemono.su', 'kemono.party', 'kemono.cr', 'coomer.su', 'coomer.party', 'coomer.st']):
|
||||
logger(f"⚠️ Unrecognized domain '{api_domain}' from input URL. Defaulting to kemono.su for API calls.")
|
||||
api_domain = "kemono.su"
|
||||
|
||||
cookies_for_api = None
|
||||
if use_cookie and app_base_dir:
|
||||
cookies_for_api = prepare_cookies_for_request(use_cookie, cookie_text, selected_cookie_file, app_base_dir, logger, target_domain=api_domain)
|
||||
@@ -154,6 +178,7 @@ def download_from_api(
|
||||
try:
|
||||
direct_response = requests.get(direct_post_api_url, headers=headers, timeout=(10, 30), cookies=cookies_for_api)
|
||||
direct_response.raise_for_status()
|
||||
direct_response.encoding = 'utf-8'
|
||||
direct_post_data = direct_response.json()
|
||||
if isinstance(direct_post_data, list) and direct_post_data:
|
||||
direct_post_data = direct_post_data[0]
|
||||
@@ -178,7 +203,8 @@ def download_from_api(
|
||||
logger("⚠️ Page range (start/end page) is ignored when a specific post URL is provided (searching all pages for the post).")
|
||||
|
||||
is_manga_mode_fetch_all_and_sort_oldest_first = manga_mode and (manga_filename_style_for_sort_check != STYLE_DATE_POST_TITLE) and not target_post_id
|
||||
api_base_url = f"https://{api_domain}/api/v1/{service}/user/{user_id}"
|
||||
should_fetch_all = fetch_all_first or is_manga_mode_fetch_all_and_sort_oldest_first
|
||||
api_base_url = f"https://{api_domain}/api/v1/{service}/user/{user_id}/posts"
|
||||
page_size = 50
|
||||
if is_manga_mode_fetch_all_and_sort_oldest_first:
|
||||
logger(f" Manga Mode (Style: {manga_filename_style_for_sort_check if manga_filename_style_for_sort_check else 'Default'} - Oldest First Sort Active): Fetching all posts to sort by date...")
|
||||
@@ -220,6 +246,9 @@ def download_from_api(
|
||||
logger(f" Manga Mode: No posts found within the specified page range ({start_page or 1}-{end_page}).")
|
||||
break
|
||||
all_posts_for_manga_mode.extend(posts_batch_manga)
|
||||
|
||||
logger(f"MANGA_FETCH_PROGRESS:{len(all_posts_for_manga_mode)}:{current_page_num_manga}")
|
||||
|
||||
current_offset_manga += page_size
|
||||
time.sleep(0.6)
|
||||
except RuntimeError as e:
|
||||
@@ -232,7 +261,12 @@ def download_from_api(
|
||||
logger(f"❌ Unexpected error during manga mode fetch: {e}")
|
||||
traceback.print_exc()
|
||||
break
|
||||
|
||||
if cancellation_event and cancellation_event.is_set(): return
|
||||
|
||||
if all_posts_for_manga_mode:
|
||||
logger(f"MANGA_FETCH_COMPLETE:{len(all_posts_for_manga_mode)}")
|
||||
|
||||
if all_posts_for_manga_mode:
|
||||
if processed_post_ids:
|
||||
original_count = len(all_posts_for_manga_mode)
|
||||
@@ -341,3 +375,4 @@ def download_from_api(
|
||||
time.sleep(0.6)
|
||||
if target_post_id and not processed_target_post_flag and not (cancellation_event and cancellation_event.is_set()):
|
||||
logger(f"❌ Target post {target_post_id} could not be found after checking all relevant pages (final check after loop).")
|
||||
|
||||
|
||||
241
src/core/bunkr_client.py
Normal file
241
src/core/bunkr_client.py
Normal file
@@ -0,0 +1,241 @@
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import requests
|
||||
import html
|
||||
import time
|
||||
import datetime
|
||||
import urllib.parse
|
||||
import json
|
||||
import random
|
||||
import binascii
|
||||
import itertools
|
||||
|
||||
class MockMessage:
|
||||
Directory = 1
|
||||
Url = 2
|
||||
Version = 3
|
||||
|
||||
class AlbumException(Exception): pass
|
||||
class ExtractionError(AlbumException): pass
|
||||
class HttpError(ExtractionError):
|
||||
def __init__(self, message="", response=None):
|
||||
self.response = response
|
||||
self.status = response.status_code if response is not None else 0
|
||||
super().__init__(message)
|
||||
class ControlException(AlbumException): pass
|
||||
class AbortExtraction(ExtractionError, ControlException): pass
|
||||
|
||||
try:
|
||||
re_compile = re._compiler.compile
|
||||
except AttributeError:
|
||||
re_compile = re.sre_compile.compile
|
||||
HTML_RE = re_compile(r"<[^>]+>")
|
||||
def extr(txt, begin, end, default=""):
|
||||
try:
|
||||
first = txt.index(begin) + len(begin)
|
||||
return txt[first:txt.index(end, first)]
|
||||
except Exception: return default
|
||||
def extract_iter(txt, begin, end, pos=None):
|
||||
try:
|
||||
index = txt.index
|
||||
lbeg = len(begin)
|
||||
lend = len(end)
|
||||
while True:
|
||||
first = index(begin, pos) + lbeg
|
||||
last = index(end, first)
|
||||
pos = last + lend
|
||||
yield txt[first:last]
|
||||
except Exception: return
|
||||
def split_html(txt):
|
||||
try: return [html.unescape(x).strip() for x in HTML_RE.split(txt) if x and not x.isspace()]
|
||||
except TypeError: return []
|
||||
def parse_datetime(date_string, format="%Y-%m-%dT%H:%M:%S%z", utcoffset=0):
|
||||
try:
|
||||
d = datetime.datetime.strptime(date_string, format)
|
||||
o = d.utcoffset()
|
||||
if o is not None: d = d.replace(tzinfo=None, microsecond=0) - o
|
||||
else:
|
||||
if d.microsecond: d = d.replace(microsecond=0)
|
||||
if utcoffset: d += datetime.timedelta(0, utcoffset * -3600)
|
||||
return d
|
||||
except (TypeError, IndexError, KeyError, ValueError, OverflowError): return None
|
||||
unquote = urllib.parse.unquote
|
||||
unescape = html.unescape
|
||||
|
||||
def decrypt_xor(encrypted, key, base64=True, fromhex=False):
|
||||
if base64: encrypted = binascii.a2b_base64(encrypted)
|
||||
if fromhex: encrypted = bytes.fromhex(encrypted.decode())
|
||||
div = len(key)
|
||||
return bytes([encrypted[i] ^ key[i % div] for i in range(len(encrypted))]).decode()
|
||||
def advance(iterable, num):
|
||||
iterator = iter(iterable)
|
||||
next(itertools.islice(iterator, num, num), None)
|
||||
return iterator
|
||||
def json_loads(s): return json.loads(s)
|
||||
def json_dumps(obj): return json.dumps(obj, separators=(",", ":"))
|
||||
|
||||
class Extractor:
|
||||
def __init__(self, match, logger):
|
||||
self.log = logger
|
||||
self.url = match.string
|
||||
self.match = match
|
||||
self.groups = match.groups()
|
||||
self.session = requests.Session()
|
||||
self.session.headers["User-Agent"] = "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:102.0) Gecko/20100101 Firefox/102.0"
|
||||
@classmethod
|
||||
def from_url(cls, url, logger):
|
||||
if isinstance(cls.pattern, str): cls.pattern = re.compile(cls.pattern)
|
||||
match = cls.pattern.match(url)
|
||||
return cls(match, logger) if match else None
|
||||
def __iter__(self): return self.items()
|
||||
def items(self): yield MockMessage.Version, 1
|
||||
def request(self, url, method="GET", fatal=True, **kwargs):
|
||||
tries = 1
|
||||
while True:
|
||||
try:
|
||||
response = self.session.request(method, url, **kwargs)
|
||||
if response.status_code < 400: return response
|
||||
msg = f"'{response.status_code} {response.reason}' for '{response.url}'"
|
||||
except requests.exceptions.RequestException as exc:
|
||||
msg = str(exc)
|
||||
|
||||
self.log.info("%s (retrying...)", msg)
|
||||
if tries > 4: break
|
||||
time.sleep(tries)
|
||||
tries += 1
|
||||
if not fatal: return None
|
||||
raise HttpError(msg)
|
||||
def request_json(self, url, **kwargs):
|
||||
response = self.request(url, **kwargs)
|
||||
try: return json_loads(response.text)
|
||||
except Exception as exc:
|
||||
self.log.warning("%s: %s", exc.__class__.__name__, exc)
|
||||
if not kwargs.get("fatal", True): return {}
|
||||
raise
|
||||
|
||||
BASE_PATTERN_BUNKR = r"(?:https?://)?(?:[a-zA-Z0-9-]+\.)?(bunkr\.(?:si|la|ws|red|black|media|site|is|to|ac|cr|ci|fi|pk|ps|sk|ph|su)|bunkrr\.ru)"
|
||||
DOMAINS = ["bunkr.si", "bunkr.ws", "bunkr.la", "bunkr.red", "bunkr.black", "bunkr.media", "bunkr.site"]
|
||||
CF_DOMAINS = set()
|
||||
|
||||
class BunkrAlbumExtractor(Extractor):
|
||||
category = "bunkr"
|
||||
root = "https://bunkr.si"
|
||||
root_dl = "https://get.bunkrr.su"
|
||||
root_api = "https://apidl.bunkr.ru"
|
||||
pattern = re.compile(BASE_PATTERN_BUNKR + r"/a/([^/?#]+)")
|
||||
|
||||
def __init__(self, match, logger):
|
||||
super().__init__(match, logger)
|
||||
domain_match = re.search(BASE_PATTERN_BUNKR, match.string)
|
||||
if domain_match:
|
||||
self.root = "https://" + domain_match.group(1)
|
||||
self.endpoint = self.root_api + "/api/_001_v2"
|
||||
self.album_id = self.groups[-1]
|
||||
|
||||
def items(self):
|
||||
page = self.request(self.url).text
|
||||
title = unescape(unescape(extr(page, 'property="og:title" content="', '"')))
|
||||
items_html = list(extract_iter(page, '<div class="grid-images_box', "</a>"))
|
||||
|
||||
album_data = {
|
||||
"album_id": self.album_id,
|
||||
"album_name": title,
|
||||
"count": len(items_html),
|
||||
}
|
||||
yield MockMessage.Directory, album_data, {}
|
||||
|
||||
for item_html in items_html:
|
||||
try:
|
||||
webpage_url = unescape(extr(item_html, ' href="', '"'))
|
||||
if webpage_url.startswith("/"):
|
||||
webpage_url = self.root + webpage_url
|
||||
|
||||
file_data = self._extract_file(webpage_url)
|
||||
info = split_html(item_html)
|
||||
|
||||
if not file_data.get("name"):
|
||||
file_data["name"] = info[-3]
|
||||
|
||||
yield MockMessage.Url, file_data, {}
|
||||
except Exception as exc:
|
||||
self.log.error("%s: %s", exc.__class__.__name__, exc)
|
||||
|
||||
def _extract_file(self, webpage_url):
|
||||
page = self.request(webpage_url).text
|
||||
data_id = extr(page, 'data-file-id="', '"')
|
||||
referer = self.root_dl + "/file/" + data_id
|
||||
headers = {"Referer": referer, "Origin": self.root_dl}
|
||||
data = self.request_json(self.endpoint, method="POST", headers=headers, json={"id": data_id})
|
||||
|
||||
file_url = decrypt_xor(data["url"], f"SECRET_KEY_{data['timestamp'] // 3600}".encode()) if data.get("encrypted") else data["url"]
|
||||
file_name = extr(page, "<h1", "<").rpartition(">")[2]
|
||||
|
||||
return {
|
||||
"url": file_url,
|
||||
"name": unescape(file_name),
|
||||
"_http_headers": {"Referer": referer}
|
||||
}
|
||||
|
||||
class BunkrMediaExtractor(BunkrAlbumExtractor):
|
||||
pattern = re.compile(BASE_PATTERN_BUNKR + r"(/[fvid]/[^/?#]+)")
|
||||
def items(self):
|
||||
try:
|
||||
media_path = self.groups[-1]
|
||||
file_data = self._extract_file(self.root + media_path)
|
||||
album_data = {"album_name": file_data.get("name", "bunkr_media"), "count": 1}
|
||||
|
||||
yield MockMessage.Directory, album_data, {}
|
||||
yield MockMessage.Url, file_data, {}
|
||||
|
||||
except Exception as exc:
|
||||
self.log.error("%s: %s", exc.__class__.__name__, exc)
|
||||
yield MockMessage.Directory, {"album_name": "error", "count": 0}, {}
|
||||
|
||||
def get_bunkr_extractor(url, logger):
|
||||
"""Selects the correct Bunkr extractor based on the URL pattern."""
|
||||
if BunkrAlbumExtractor.pattern.match(url):
|
||||
logger.info("Bunkr Album URL detected.")
|
||||
return BunkrAlbumExtractor.from_url(url, logger)
|
||||
elif BunkrMediaExtractor.pattern.match(url):
|
||||
logger.info("Bunkr Media URL detected.")
|
||||
return BunkrMediaExtractor.from_url(url, logger)
|
||||
else:
|
||||
logger.error(f"No suitable Bunkr extractor found for URL: {url}")
|
||||
return None
|
||||
|
||||
def fetch_bunkr_data(url, logger):
|
||||
"""
|
||||
Main function to be called from the GUI.
|
||||
It extracts all file information from a Bunkr URL.
|
||||
|
||||
Returns:
|
||||
A tuple of (album_name, list_of_files)
|
||||
- album_name (str): The name of the album.
|
||||
- list_of_files (list): A list of dicts, each containing 'url', 'name', and '_http_headers'.
|
||||
Returns (None, None) on failure.
|
||||
"""
|
||||
extractor = get_bunkr_extractor(url, logger)
|
||||
if not extractor:
|
||||
return None, None
|
||||
|
||||
try:
|
||||
album_name = "default_bunkr_album"
|
||||
files_to_download = []
|
||||
for msg_type, data, metadata in extractor:
|
||||
if msg_type == MockMessage.Directory:
|
||||
raw_album_name = data.get('album_name', 'untitled')
|
||||
album_name = re.sub(r'[<>:"/\\|?*]', '_', raw_album_name).strip() or "untitled"
|
||||
logger.info(f"Processing Bunkr album: {album_name}")
|
||||
elif msg_type == MockMessage.Url:
|
||||
files_to_download.append(data)
|
||||
|
||||
if not files_to_download:
|
||||
logger.warning("No files found to download from the Bunkr URL.")
|
||||
return None, None
|
||||
|
||||
return album_name, files_to_download
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"An error occurred while extracting Bunkr info: {e}", exc_info=True)
|
||||
return None, None
|
||||
88
src/core/discord_client.py
Normal file
88
src/core/discord_client.py
Normal file
@@ -0,0 +1,88 @@
|
||||
import time
|
||||
import cloudscraper
|
||||
import json
|
||||
|
||||
def fetch_server_channels(server_id, logger=print, cookies_dict=None):
|
||||
"""
|
||||
Fetches all channels for a given Discord server ID from the API.
|
||||
Uses cloudscraper to bypass Cloudflare.
|
||||
"""
|
||||
api_url = f"https://kemono.cr/api/v1/discord/server/{server_id}"
|
||||
logger(f" Fetching channels for server: {api_url}")
|
||||
|
||||
scraper = cloudscraper.create_scraper()
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
|
||||
'Referer': f'https://kemono.cr/discord/server/{server_id}',
|
||||
'Accept': 'text/css'
|
||||
}
|
||||
|
||||
try:
|
||||
response = scraper.get(api_url, headers=headers, cookies=cookies_dict, timeout=30)
|
||||
response.raise_for_status()
|
||||
channels = response.json()
|
||||
if isinstance(channels, list):
|
||||
logger(f" ✅ Found {len(channels)} channels for server {server_id}.")
|
||||
return channels
|
||||
return None
|
||||
except Exception as e:
|
||||
logger(f" ❌ Error fetching server channels for {server_id}: {e}")
|
||||
return None
|
||||
|
||||
def fetch_channel_messages(channel_id, logger=print, cancellation_event=None, pause_event=None, cookies_dict=None):
|
||||
"""
|
||||
A generator that fetches all messages for a specific Discord channel, handling pagination.
|
||||
Uses cloudscraper and proper headers to bypass server protection.
|
||||
"""
|
||||
scraper = cloudscraper.create_scraper()
|
||||
base_url = f"https://kemono.cr/api/v1/discord/channel/{channel_id}"
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
|
||||
'Referer': f'https://kemono.cr/discord/channel/{channel_id}',
|
||||
'Accept': 'text/css'
|
||||
}
|
||||
|
||||
offset = 0
|
||||
page_size = 150
|
||||
|
||||
while True:
|
||||
if cancellation_event and cancellation_event.is_set():
|
||||
logger(" Discord message fetching cancelled.")
|
||||
break
|
||||
if pause_event and pause_event.is_set():
|
||||
logger(" Discord message fetching paused...")
|
||||
while pause_event.is_set():
|
||||
if cancellation_event and cancellation_event.is_set():
|
||||
break
|
||||
time.sleep(0.5)
|
||||
if not (cancellation_event and cancellation_event.is_set()):
|
||||
logger(" Discord message fetching resumed.")
|
||||
|
||||
paginated_url = f"{base_url}?o={offset}"
|
||||
logger(f" Fetching messages from API: page starting at offset {offset}")
|
||||
|
||||
try:
|
||||
response = scraper.get(paginated_url, headers=headers, cookies=cookies_dict, timeout=30)
|
||||
response.raise_for_status()
|
||||
messages_batch = response.json()
|
||||
|
||||
if not messages_batch:
|
||||
logger(f" ✅ Reached end of messages for channel {channel_id}.")
|
||||
break
|
||||
|
||||
logger(f" Fetched {len(messages_batch)} messages...")
|
||||
yield messages_batch
|
||||
|
||||
if len(messages_batch) < page_size:
|
||||
logger(f" ✅ Last page of messages received for channel {channel_id}.")
|
||||
break
|
||||
|
||||
offset += page_size
|
||||
time.sleep(0.5) # Be respectful to the API
|
||||
|
||||
except (cloudscraper.exceptions.CloudflareException, json.JSONDecodeError) as e:
|
||||
logger(f" ❌ Error fetching messages at offset {offset}: {e}")
|
||||
break
|
||||
except Exception as e:
|
||||
logger(f" ❌ An unexpected error occurred while fetching messages: {e}")
|
||||
break
|
||||
131
src/core/erome_client.py
Normal file
131
src/core/erome_client.py
Normal file
@@ -0,0 +1,131 @@
|
||||
|
||||
import os
|
||||
import re
|
||||
import html
|
||||
import time
|
||||
import urllib.parse
|
||||
import requests
|
||||
from datetime import datetime
|
||||
import cloudscraper
|
||||
|
||||
|
||||
def extr(txt, begin, end, default=""):
|
||||
"""Stripped-down version of 'extract()' to find text between two delimiters."""
|
||||
try:
|
||||
first = txt.index(begin) + len(begin)
|
||||
return txt[first:txt.index(end, first)]
|
||||
except (ValueError, IndexError):
|
||||
return default
|
||||
|
||||
def extract_iter(txt, begin, end):
|
||||
"""Yields all occurrences of text between two delimiters."""
|
||||
try:
|
||||
index = txt.index
|
||||
lbeg = len(begin)
|
||||
lend = len(end)
|
||||
pos = 0
|
||||
while True:
|
||||
first = index(begin, pos) + lbeg
|
||||
last = index(end, first)
|
||||
pos = last + lend
|
||||
yield txt[first:last]
|
||||
except (ValueError, IndexError):
|
||||
return
|
||||
|
||||
def nameext_from_url(url):
|
||||
"""Extracts filename and extension from a URL."""
|
||||
data = {}
|
||||
filename = urllib.parse.unquote(url.partition("?")[0].rpartition("/")[2])
|
||||
name, _, ext = filename.rpartition(".")
|
||||
if name and len(ext) <= 16:
|
||||
data["filename"], data["extension"] = name, ext.lower()
|
||||
else:
|
||||
data["filename"], data["extension"] = filename, ""
|
||||
return data
|
||||
|
||||
def parse_timestamp(ts, default=None):
|
||||
"""Creates a datetime object from a Unix timestamp."""
|
||||
try:
|
||||
return datetime.fromtimestamp(int(ts))
|
||||
except (ValueError, TypeError):
|
||||
return default
|
||||
|
||||
|
||||
def fetch_erome_data(url, logger):
|
||||
"""
|
||||
Identifies and extracts all media files from an Erome album URL.
|
||||
|
||||
Args:
|
||||
url (str): The Erome album URL (e.g., https://www.erome.com/a/albumID).
|
||||
logger (function): A function to log progress messages.
|
||||
|
||||
Returns:
|
||||
tuple: A tuple containing (album_folder_name, list_of_file_dicts).
|
||||
Returns (None, []) if data extraction fails.
|
||||
"""
|
||||
album_id_match = re.search(r"/a/(\w+)", url)
|
||||
if not album_id_match:
|
||||
logger(f"Error: The URL '{url}' does not appear to be a valid Erome album link.")
|
||||
return None, []
|
||||
|
||||
album_id = album_id_match.group(1)
|
||||
page_url = f"https://www.erome.com/a/{album_id}"
|
||||
|
||||
session = cloudscraper.create_scraper()
|
||||
|
||||
try:
|
||||
logger(f" Fetching Erome album page: {page_url}")
|
||||
for attempt in range(5):
|
||||
response = session.get(page_url, timeout=30)
|
||||
response.raise_for_status()
|
||||
page_content = response.text
|
||||
if "<title>Please wait a few moments</title>" in page_content:
|
||||
logger(f" Cloudflare check detected. Waiting 5 seconds... (Attempt {attempt + 1}/5)")
|
||||
time.sleep(5)
|
||||
continue
|
||||
break
|
||||
else:
|
||||
logger(" Error: Could not bypass Cloudflare check after several attempts.")
|
||||
return None, []
|
||||
|
||||
title = html.unescape(extr(page_content, 'property="og:title" content="', '"'))
|
||||
user = urllib.parse.unquote(extr(page_content, 'href="https://www.erome.com/', '"', default="unknown_user"))
|
||||
|
||||
sanitized_title = re.sub(r'[<>:"/\\|?*]', '_', title).strip()
|
||||
sanitized_user = re.sub(r'[<>:"/\\|?*]', '_', user).strip()
|
||||
|
||||
album_folder_name = f"Erome - {sanitized_user} - {sanitized_title} [{album_id}]"
|
||||
|
||||
urls = []
|
||||
media_groups = page_content.split('<div class="media-group"')
|
||||
for group in media_groups[1:]:
|
||||
video_url = extr(group, '<source src="', '"') or extr(group, 'data-src="', '"')
|
||||
if video_url:
|
||||
urls.append(video_url)
|
||||
|
||||
if not urls:
|
||||
logger(" Warning: No media URLs found on the album page.")
|
||||
return album_folder_name, []
|
||||
|
||||
logger(f" Found {len(urls)} media files in album '{title}'.")
|
||||
|
||||
file_list = []
|
||||
for i, file_url in enumerate(urls, 1):
|
||||
filename_info = nameext_from_url(file_url)
|
||||
filename = f"{album_id}_{sanitized_title}_{i:03d}.{filename_info.get('extension', 'mp4')}"
|
||||
|
||||
file_data = {
|
||||
"url": file_url,
|
||||
"filename": filename,
|
||||
"headers": {"Referer": page_url},
|
||||
}
|
||||
file_list.append(file_data)
|
||||
|
||||
return album_folder_name, file_list
|
||||
|
||||
except requests.exceptions.RequestException as e:
|
||||
logger(f" Error fetching Erome page: {e}")
|
||||
return None, []
|
||||
except Exception as e:
|
||||
logger(f" An unexpected error occurred during Erome extraction: {e}")
|
||||
return None, []
|
||||
@@ -5,11 +5,10 @@ import json
|
||||
import traceback
|
||||
from concurrent.futures import ThreadPoolExecutor, as_completed, Future
|
||||
from .api_client import download_from_api
|
||||
from .workers import PostProcessorWorker, DownloadThread
|
||||
from .workers import PostProcessorWorker
|
||||
from ..config.constants import (
|
||||
STYLE_DATE_BASED, STYLE_POST_TITLE_GLOBAL_NUMBERING,
|
||||
MAX_THREADS, POST_WORKER_BATCH_THRESHOLD, POST_WORKER_NUM_BATCHES,
|
||||
POST_WORKER_BATCH_DELAY_SECONDS
|
||||
MAX_THREADS
|
||||
)
|
||||
from ..utils.file_utils import clean_folder_name
|
||||
|
||||
@@ -44,6 +43,7 @@ class DownloadManager:
|
||||
self.creator_profiles_dir = None
|
||||
self.current_creator_name_for_profile = None
|
||||
self.current_creator_profile_path = None
|
||||
self.session_file_path = None
|
||||
|
||||
def _log(self, message):
|
||||
"""Puts a progress message into the queue for the UI."""
|
||||
@@ -61,12 +61,16 @@ class DownloadManager:
|
||||
if self.is_running:
|
||||
self._log("❌ Cannot start a new session: A session is already in progress.")
|
||||
return
|
||||
|
||||
|
||||
self.session_file_path = config.get('session_file_path')
|
||||
creator_profile_data = self._setup_creator_profile(config)
|
||||
creator_profile_data['settings'] = config
|
||||
creator_profile_data.setdefault('processed_post_ids', [])
|
||||
self._save_creator_profile(creator_profile_data)
|
||||
self._log(f"✅ Loaded/created profile for '{self.current_creator_name_for_profile}'. Settings saved.")
|
||||
|
||||
# Save settings to profile at the start of the session
|
||||
if self.current_creator_profile_path:
|
||||
creator_profile_data['settings'] = config
|
||||
creator_profile_data.setdefault('processed_post_ids', [])
|
||||
self._save_creator_profile(creator_profile_data)
|
||||
self._log(f"✅ Loaded/created profile for '{self.current_creator_name_for_profile}'. Settings saved.")
|
||||
|
||||
self.is_running = True
|
||||
self.cancellation_event.clear()
|
||||
@@ -77,6 +81,7 @@ class DownloadManager:
|
||||
self.total_downloads = 0
|
||||
self.total_skips = 0
|
||||
self.all_kept_original_filenames = []
|
||||
|
||||
is_single_post = bool(config.get('target_post_id_from_initial_url'))
|
||||
use_multithreading = config.get('use_multithreading', True)
|
||||
is_manga_sequential = config.get('manga_mode_active') and config.get('manga_filename_style') in [STYLE_DATE_BASED, STYLE_POST_TITLE_GLOBAL_NUMBERING]
|
||||
@@ -86,72 +91,99 @@ class DownloadManager:
|
||||
if should_use_multithreading_for_posts:
|
||||
fetcher_thread = threading.Thread(
|
||||
target=self._fetch_and_queue_posts_for_pool,
|
||||
args=(config, restore_data, creator_profile_data), # Add argument here
|
||||
args=(config, restore_data, creator_profile_data),
|
||||
daemon=True
|
||||
)
|
||||
fetcher_thread.start()
|
||||
else:
|
||||
self._start_single_threaded_session(config)
|
||||
# Single-threaded mode does not use the manager's complex logic
|
||||
self._log("ℹ️ Manager is handing off to a single-threaded worker...")
|
||||
# The single-threaded worker will manage its own lifecycle and signals.
|
||||
# The manager's role for this session is effectively over.
|
||||
self.is_running = False # Allow another session to start if needed
|
||||
self.progress_queue.put({'type': 'handoff_to_single_thread', 'payload': (config,)})
|
||||
|
||||
def _start_single_threaded_session(self, config):
|
||||
"""Handles downloads that are best processed by a single worker thread."""
|
||||
self._log("ℹ️ Initializing single-threaded download process...")
|
||||
self.worker_thread = threading.Thread(
|
||||
target=self._run_single_worker,
|
||||
args=(config,),
|
||||
daemon=True
|
||||
)
|
||||
self.worker_thread.start()
|
||||
|
||||
def _run_single_worker(self, config):
|
||||
"""Target function for the single-worker thread."""
|
||||
try:
|
||||
worker = DownloadThread(config, self.progress_queue)
|
||||
worker.run() # This is the main blocking call for this thread
|
||||
except Exception as e:
|
||||
self._log(f"❌ CRITICAL ERROR in single-worker thread: {e}")
|
||||
self._log(traceback.format_exc())
|
||||
finally:
|
||||
self.is_running = False
|
||||
|
||||
def _fetch_and_queue_posts_for_pool(self, config, restore_data):
|
||||
def _fetch_and_queue_posts_for_pool(self, config, restore_data, creator_profile_data):
|
||||
"""
|
||||
Fetches all posts from the API and submits them as tasks to a thread pool.
|
||||
This method runs in its own dedicated thread to avoid blocking.
|
||||
Fetches posts from the API in batches and submits them as tasks to a thread pool.
|
||||
This method runs in its own dedicated thread to avoid blocking the UI.
|
||||
It provides immediate feedback as soon as the first batch of posts is found.
|
||||
"""
|
||||
try:
|
||||
num_workers = min(config.get('num_threads', 4), MAX_THREADS)
|
||||
self.thread_pool = ThreadPoolExecutor(max_workers=num_workers, thread_name_prefix='PostWorker_')
|
||||
|
||||
session_processed_ids = set(restore_data['processed_post_ids']) if restore_data else set()
|
||||
session_processed_ids = set(restore_data.get('processed_post_ids', [])) if restore_data else set()
|
||||
profile_processed_ids = set(creator_profile_data.get('processed_post_ids', []))
|
||||
processed_ids = session_processed_ids.union(profile_processed_ids)
|
||||
|
||||
if restore_data:
|
||||
if restore_data and 'all_posts_data' in restore_data:
|
||||
# This logic for session restore remains as it relies on a pre-fetched list
|
||||
all_posts = restore_data['all_posts_data']
|
||||
processed_ids = set(restore_data['processed_post_ids'])
|
||||
posts_to_process = [p for p in all_posts if p.get('id') not in processed_ids]
|
||||
self.total_posts = len(all_posts)
|
||||
self.processed_posts = len(processed_ids)
|
||||
self._log(f"🔄 Restoring session. {len(posts_to_process)} posts remaining.")
|
||||
self.progress_queue.put({'type': 'overall_progress', 'payload': (self.total_posts, self.processed_posts)})
|
||||
|
||||
if not posts_to_process:
|
||||
self._log("✅ No new posts to process from restored session.")
|
||||
return
|
||||
|
||||
for post_data in posts_to_process:
|
||||
if self.cancellation_event.is_set(): break
|
||||
worker = PostProcessorWorker(post_data, config, self.progress_queue)
|
||||
future = self.thread_pool.submit(worker.process)
|
||||
future.add_done_callback(self._handle_future_result)
|
||||
self.active_futures.append(future)
|
||||
else:
|
||||
posts_to_process = self._get_all_posts(config)
|
||||
self.total_posts = len(posts_to_process)
|
||||
# --- START: REFACTORED STREAMING LOGIC ---
|
||||
post_generator = download_from_api(
|
||||
api_url_input=config['api_url'],
|
||||
logger=self._log,
|
||||
start_page=config.get('start_page'),
|
||||
end_page=config.get('end_page'),
|
||||
manga_mode=config.get('manga_mode_active', False),
|
||||
cancellation_event=self.cancellation_event,
|
||||
pause_event=self.pause_event,
|
||||
use_cookie=config.get('use_cookie', False),
|
||||
cookie_text=config.get('cookie_text', ''),
|
||||
selected_cookie_file=config.get('selected_cookie_file'),
|
||||
app_base_dir=config.get('app_base_dir'),
|
||||
manga_filename_style_for_sort_check=config.get('manga_filename_style'),
|
||||
processed_post_ids=list(processed_ids)
|
||||
)
|
||||
|
||||
self.total_posts = 0
|
||||
self.processed_posts = 0
|
||||
|
||||
self.progress_queue.put({'type': 'overall_progress', 'payload': (self.total_posts, self.processed_posts)})
|
||||
|
||||
if not posts_to_process:
|
||||
self._log("✅ No new posts to process.")
|
||||
return
|
||||
for post_data in posts_to_process:
|
||||
if self.cancellation_event.is_set():
|
||||
break
|
||||
worker = PostProcessorWorker(post_data, config, self.progress_queue)
|
||||
future = self.thread_pool.submit(worker.process)
|
||||
future.add_done_callback(self._handle_future_result)
|
||||
self.active_futures.append(future)
|
||||
|
||||
# Process posts in batches as they are yielded by the API client
|
||||
for batch in post_generator:
|
||||
if self.cancellation_event.is_set():
|
||||
self._log(" Post fetching cancelled.")
|
||||
break
|
||||
|
||||
# Filter out any posts that might have been processed since the start
|
||||
posts_in_batch_to_process = [p for p in batch if p.get('id') not in processed_ids]
|
||||
|
||||
if not posts_in_batch_to_process:
|
||||
continue
|
||||
|
||||
# Update total count and immediately inform the UI
|
||||
self.total_posts += len(posts_in_batch_to_process)
|
||||
self.progress_queue.put({'type': 'overall_progress', 'payload': (self.total_posts, self.processed_posts)})
|
||||
|
||||
for post_data in posts_in_batch_to_process:
|
||||
if self.cancellation_event.is_set(): break
|
||||
worker = PostProcessorWorker(post_data, config, self.progress_queue)
|
||||
future = self.thread_pool.submit(worker.process)
|
||||
future.add_done_callback(self._handle_future_result)
|
||||
self.active_futures.append(future)
|
||||
|
||||
if self.total_posts == 0 and not self.cancellation_event.is_set():
|
||||
self._log("✅ No new posts found to process.")
|
||||
|
||||
except Exception as e:
|
||||
self._log(f"❌ CRITICAL ERROR in post fetcher thread: {e}")
|
||||
self._log(traceback.format_exc())
|
||||
@@ -164,28 +196,6 @@ class DownloadManager:
|
||||
'type': 'finished',
|
||||
'payload': (self.total_downloads, self.total_skips, self.cancellation_event.is_set(), self.all_kept_original_filenames)
|
||||
})
|
||||
|
||||
def _get_all_posts(self, config):
|
||||
"""Helper to fetch all posts using the API client."""
|
||||
all_posts = []
|
||||
post_generator = download_from_api(
|
||||
api_url_input=config['api_url'],
|
||||
logger=self._log,
|
||||
start_page=config.get('start_page'),
|
||||
end_page=config.get('end_page'),
|
||||
manga_mode=config.get('manga_mode_active', False),
|
||||
cancellation_event=self.cancellation_event,
|
||||
pause_event=self.pause_event,
|
||||
use_cookie=config.get('use_cookie', False),
|
||||
cookie_text=config.get('cookie_text', ''),
|
||||
selected_cookie_file=config.get('selected_cookie_file'),
|
||||
app_base_dir=config.get('app_base_dir'),
|
||||
manga_filename_style_for_sort_check=config.get('manga_filename_style'),
|
||||
processed_post_ids=config.get('processed_post_ids', [])
|
||||
)
|
||||
for batch in post_generator:
|
||||
all_posts.extend(batch)
|
||||
return all_posts
|
||||
|
||||
def _handle_future_result(self, future: Future):
|
||||
"""Callback executed when a worker task completes."""
|
||||
@@ -261,9 +271,15 @@ class DownloadManager:
|
||||
"""Cancels the current running session."""
|
||||
if not self.is_running:
|
||||
return
|
||||
|
||||
if self.cancellation_event.is_set():
|
||||
self._log("ℹ️ Cancellation already in progress.")
|
||||
return
|
||||
|
||||
self._log("⚠️ Cancellation requested by user...")
|
||||
self.cancellation_event.set()
|
||||
|
||||
if self.thread_pool:
|
||||
self.thread_pool.shutdown(wait=False, cancel_futures=True)
|
||||
|
||||
self.is_running = False
|
||||
self._log(" Signaling all worker threads to stop and shutting down pool...")
|
||||
self.thread_pool.shutdown(wait=False)
|
||||
|
||||
|
||||
44
src/core/nhentai_client.py
Normal file
44
src/core/nhentai_client.py
Normal file
@@ -0,0 +1,44 @@
|
||||
import requests
|
||||
import cloudscraper
|
||||
import json
|
||||
|
||||
def fetch_nhentai_gallery(gallery_id, logger=print):
|
||||
"""
|
||||
Fetches the metadata for a single nhentai gallery using cloudscraper to bypass Cloudflare.
|
||||
|
||||
Args:
|
||||
gallery_id (str or int): The ID of the nhentai gallery.
|
||||
logger (function): A function to log progress and error messages.
|
||||
|
||||
Returns:
|
||||
dict: A dictionary containing the gallery's metadata if successful, otherwise None.
|
||||
"""
|
||||
api_url = f"https://nhentai.net/api/gallery/{gallery_id}"
|
||||
|
||||
scraper = cloudscraper.create_scraper()
|
||||
|
||||
logger(f" Fetching nhentai gallery metadata from: {api_url}")
|
||||
|
||||
try:
|
||||
# Use the scraper to make the GET request
|
||||
response = scraper.get(api_url, timeout=20)
|
||||
|
||||
if response.status_code == 404:
|
||||
logger(f" ❌ Gallery not found (404): ID {gallery_id}")
|
||||
return None
|
||||
|
||||
response.raise_for_status()
|
||||
|
||||
gallery_data = response.json()
|
||||
|
||||
if "id" in gallery_data and "media_id" in gallery_data and "images" in gallery_data:
|
||||
logger(f" ✅ Successfully fetched metadata for '{gallery_data['title']['english']}'")
|
||||
gallery_data['pages'] = gallery_data.pop('images')['pages']
|
||||
return gallery_data
|
||||
else:
|
||||
logger(" ❌ API response is missing essential keys (id, media_id, or images).")
|
||||
return None
|
||||
|
||||
except Exception as e:
|
||||
logger(f" ❌ An error occurred while fetching gallery {gallery_id}: {e}")
|
||||
return None
|
||||
163
src/core/saint2_client.py
Normal file
163
src/core/saint2_client.py
Normal file
@@ -0,0 +1,163 @@
|
||||
import os
|
||||
import re as re_module
|
||||
import html
|
||||
import urllib.parse
|
||||
import requests
|
||||
|
||||
|
||||
PATTERN_CACHE = {}
|
||||
|
||||
def re(pattern):
|
||||
"""Compile a regular expression pattern and cache it."""
|
||||
try:
|
||||
return PATTERN_CACHE[pattern]
|
||||
except KeyError:
|
||||
p = PATTERN_CACHE[pattern] = re_module.compile(pattern)
|
||||
return p
|
||||
|
||||
def extract_from(txt, pos=None, default=""):
|
||||
"""Returns a function that extracts text between two delimiters from 'txt'."""
|
||||
def extr(begin, end, index=txt.find, txt=txt):
|
||||
nonlocal pos
|
||||
try:
|
||||
start_pos = pos if pos is not None else 0
|
||||
first = index(begin, start_pos) + len(begin)
|
||||
last = index(end, first)
|
||||
if pos is not None:
|
||||
pos = last + len(end)
|
||||
return txt[first:last]
|
||||
except (ValueError, IndexError):
|
||||
return default
|
||||
return extr
|
||||
|
||||
def nameext_from_url(url):
|
||||
"""Extract filename and extension from a URL."""
|
||||
data = {}
|
||||
filename = urllib.parse.unquote(url.partition("?")[0].rpartition("/")[2])
|
||||
name, _, ext = filename.rpartition(".")
|
||||
if name and len(ext) <= 16:
|
||||
data["filename"], data["extension"] = name, ext.lower()
|
||||
else:
|
||||
data["filename"], data["extension"] = filename, ""
|
||||
return data
|
||||
|
||||
class BaseExtractor:
|
||||
"""A simplified base class for extractors."""
|
||||
def __init__(self, match, session, logger):
|
||||
self.match = match
|
||||
self.groups = match.groups()
|
||||
self.session = session
|
||||
self.log = logger
|
||||
|
||||
def request(self, url, **kwargs):
|
||||
"""Makes an HTTP request using the session."""
|
||||
try:
|
||||
response = self.session.get(url, **kwargs)
|
||||
response.raise_for_status()
|
||||
return response
|
||||
except requests.exceptions.RequestException as e:
|
||||
self.log(f"Error making request to {url}: {e}")
|
||||
return None
|
||||
|
||||
class SaintAlbumExtractor(BaseExtractor):
|
||||
"""Extractor for saint.su albums."""
|
||||
root = "https://saint2.su"
|
||||
pattern = re(r"(?:https?://)?saint\d*\.(?:su|pk|cr|to)/a/([^/?#]+)")
|
||||
|
||||
def items(self):
|
||||
"""Generator that yields all files from an album."""
|
||||
album_id = self.groups[0]
|
||||
response = self.request(f"{self.root}/a/{album_id}")
|
||||
if not response:
|
||||
return None, []
|
||||
|
||||
extr = extract_from(response.text)
|
||||
title = extr("<title>", "<").rpartition(" - ")[0]
|
||||
self.log(f"Downloading album: {title}")
|
||||
|
||||
files_html = re_module.findall(r'<a class="image".*?</a>', response.text, re_module.DOTALL)
|
||||
file_list = []
|
||||
for i, file_html in enumerate(files_html, 1):
|
||||
file_extr = extract_from(file_html)
|
||||
file_url = html.unescape(file_extr("onclick=\"play('", "'"))
|
||||
if not file_url:
|
||||
continue
|
||||
|
||||
filename_info = nameext_from_url(file_url)
|
||||
filename = f"{filename_info['filename']}.{filename_info['extension']}"
|
||||
|
||||
file_data = {
|
||||
"url": file_url,
|
||||
"filename": filename,
|
||||
"headers": {"Referer": response.url},
|
||||
}
|
||||
file_list.append(file_data)
|
||||
|
||||
return title, file_list
|
||||
|
||||
class SaintMediaExtractor(BaseExtractor):
|
||||
"""Extractor for single saint.su media links."""
|
||||
root = "https://saint2.su"
|
||||
pattern = re(r"(?:https?://)?saint\d*\.(?:su|pk|cr|to)(/(embe)?d/([^/?#]+))")
|
||||
|
||||
def items(self):
|
||||
"""Generator that yields the single file from a media page."""
|
||||
path, embed, media_id = self.groups
|
||||
url = self.root + path
|
||||
response = self.request(url)
|
||||
if not response:
|
||||
return None, []
|
||||
|
||||
extr = extract_from(response.text)
|
||||
file_url = ""
|
||||
title = extr("<title>", "<").rpartition(" - ")[0] or media_id
|
||||
|
||||
if embed: # /embed/ link
|
||||
file_url = html.unescape(extr('<source src="', '"'))
|
||||
else: # /d/ link
|
||||
file_url = html.unescape(extr('<a href="', '"'))
|
||||
|
||||
if not file_url:
|
||||
self.log("Could not find video URL on the page.")
|
||||
return title, []
|
||||
|
||||
filename_info = nameext_from_url(file_url)
|
||||
filename = f"{filename_info['filename'] or media_id}.{filename_info['extension'] or 'mp4'}"
|
||||
|
||||
file_data = {
|
||||
"url": file_url,
|
||||
"filename": filename,
|
||||
"headers": {"Referer": response.url}
|
||||
}
|
||||
|
||||
return title, [file_data]
|
||||
|
||||
|
||||
def fetch_saint2_data(url, logger):
|
||||
"""
|
||||
Identifies the correct extractor for a saint2.su URL and returns the data.
|
||||
|
||||
Args:
|
||||
url (str): The saint2.su URL.
|
||||
logger (function): A function to log progress messages.
|
||||
|
||||
Returns:
|
||||
tuple: A tuple containing (album_title, list_of_file_dicts).
|
||||
Returns (None, []) if no data could be fetched.
|
||||
"""
|
||||
extractors = [SaintMediaExtractor, SaintAlbumExtractor]
|
||||
session = requests.Session()
|
||||
session.headers.update({
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
|
||||
})
|
||||
|
||||
for extractor_cls in extractors:
|
||||
match = extractor_cls.pattern.match(url)
|
||||
if match:
|
||||
extractor = extractor_cls(match, session, logger)
|
||||
album_title, files = extractor.items()
|
||||
sanitized_title = re_module.sub(r'[<>:"/\\|?*]', '_', album_title) if album_title else "saint2_download"
|
||||
return sanitized_title, files
|
||||
|
||||
logger(f"Error: The URL '{url}' does not match a known saint2 pattern.")
|
||||
return None, []
|
||||
@@ -1,4 +1,5 @@
|
||||
import os
|
||||
import sys
|
||||
import queue
|
||||
import re
|
||||
import threading
|
||||
@@ -14,6 +15,8 @@ from concurrent.futures import ThreadPoolExecutor, as_completed, CancelledError,
|
||||
from io import BytesIO
|
||||
from urllib .parse import urlparse
|
||||
import requests
|
||||
import cloudscraper
|
||||
|
||||
try:
|
||||
from PIL import Image
|
||||
except ImportError:
|
||||
@@ -36,7 +39,7 @@ try:
|
||||
except ImportError:
|
||||
Document = None
|
||||
from PyQt5 .QtCore import Qt ,QThread ,pyqtSignal ,QMutex ,QMutexLocker ,QObject ,QTimer ,QSettings ,QStandardPaths ,QCoreApplication ,QUrl ,QSize ,QProcess
|
||||
from .api_client import download_from_api, fetch_post_comments
|
||||
from .api_client import download_from_api, fetch_post_comments, fetch_single_post_data
|
||||
from ..services.multipart_downloader import download_file_in_parts, MULTIPART_DOWNLOADER_AVAILABLE
|
||||
from ..services.drive_downloader import (
|
||||
download_mega_file, download_gdrive_file, download_dropbox_file
|
||||
@@ -53,6 +56,19 @@ from ..utils.text_utils import (
|
||||
)
|
||||
from ..config.constants import *
|
||||
|
||||
def robust_clean_name(name):
|
||||
"""A more robust function to remove illegal characters for filenames and folders."""
|
||||
if not name:
|
||||
return ""
|
||||
illegal_chars_pattern = r'[\x00-\x1f<>:"/\\|?*\']'
|
||||
cleaned_name = re.sub(illegal_chars_pattern, '', name)
|
||||
|
||||
cleaned_name = cleaned_name.strip(' .')
|
||||
|
||||
if not cleaned_name:
|
||||
return "untitled_folder"
|
||||
return cleaned_name
|
||||
|
||||
class PostProcessorSignals (QObject ):
|
||||
progress_signal =pyqtSignal (str )
|
||||
file_download_status_signal =pyqtSignal (bool )
|
||||
@@ -63,7 +79,6 @@ class PostProcessorSignals (QObject ):
|
||||
worker_finished_signal = pyqtSignal(tuple)
|
||||
|
||||
class PostProcessorWorker:
|
||||
|
||||
def __init__(self, post_data, download_root, known_names,
|
||||
filter_character_list, emitter,
|
||||
unwanted_keywords, filter_mode, skip_zip,
|
||||
@@ -103,7 +118,11 @@ class PostProcessorWorker:
|
||||
text_export_format='txt',
|
||||
single_pdf_mode=False,
|
||||
project_root_dir=None,
|
||||
processed_post_ids=None
|
||||
processed_post_ids=None,
|
||||
multipart_scope='both',
|
||||
multipart_parts_count=4,
|
||||
multipart_min_size_mb=100,
|
||||
skip_file_size_mb=None
|
||||
):
|
||||
self.post = post_data
|
||||
self.download_root = download_root
|
||||
@@ -165,7 +184,10 @@ class PostProcessorWorker:
|
||||
self.single_pdf_mode = single_pdf_mode
|
||||
self.project_root_dir = project_root_dir
|
||||
self.processed_post_ids = processed_post_ids if processed_post_ids is not None else []
|
||||
|
||||
self.multipart_scope = multipart_scope
|
||||
self.multipart_parts_count = multipart_parts_count
|
||||
self.multipart_min_size_mb = multipart_min_size_mb
|
||||
self.skip_file_size_mb = skip_file_size_mb
|
||||
if self.compress_images and Image is None:
|
||||
self.logger("⚠️ Image compression disabled: Pillow library not found.")
|
||||
self.compress_images = False
|
||||
@@ -199,8 +221,38 @@ class PostProcessorWorker:
|
||||
if self .dynamic_filter_holder :
|
||||
return self .dynamic_filter_holder .get_filters ()
|
||||
return self .filter_character_list_objects_initial
|
||||
|
||||
def _download_single_file(self, file_info, target_folder_path, headers, original_post_id_for_log, skip_event,
|
||||
|
||||
def _find_valid_subdomain(self, url: str, max_subdomains: int = 4) -> str:
|
||||
"""
|
||||
Attempts to find a working subdomain for a Kemono/Coomer URL that returned a 403 error.
|
||||
Returns the original URL if no other valid subdomain is found.
|
||||
"""
|
||||
self.logger(f" probing for a valid subdomain...")
|
||||
parsed_url = urlparse(url)
|
||||
original_domain = parsed_url.netloc
|
||||
|
||||
for i in range(1, max_subdomains + 1):
|
||||
domain_parts = original_domain.split('.')
|
||||
if len(domain_parts) > 1:
|
||||
base_domain = ".".join(domain_parts[-2:])
|
||||
new_domain = f"n{i}.{base_domain}"
|
||||
else:
|
||||
continue
|
||||
|
||||
new_url = parsed_url._replace(netloc=new_domain).geturl()
|
||||
|
||||
try:
|
||||
with requests.head(new_url, headers={'User-Agent': 'Mozilla/5.0'}, timeout=5, allow_redirects=True) as resp:
|
||||
if resp.status_code == 200:
|
||||
self.logger(f" ✅ Valid subdomain found: {new_domain}")
|
||||
return new_url
|
||||
except requests.RequestException:
|
||||
continue
|
||||
|
||||
self.logger(f" ⚠️ No other valid subdomain found. Sticking with the original.")
|
||||
return url
|
||||
|
||||
def _download_single_file(self, file_info, target_folder_path, post_page_url, original_post_id_for_log, skip_event,
|
||||
post_title="", file_index_in_post=0, num_files_in_this_post=1,
|
||||
manga_date_file_counter_ref=None,
|
||||
forced_filename_override=None,
|
||||
@@ -214,11 +266,36 @@ class PostProcessorWorker:
|
||||
if self.check_cancel() or (skip_event and skip_event.is_set()):
|
||||
return 0, 1, "", False, FILE_DOWNLOAD_STATUS_SKIPPED, None
|
||||
|
||||
file_download_headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)',
|
||||
'Referer': post_page_url,
|
||||
'Accept': 'text/css'
|
||||
|
||||
}
|
||||
|
||||
file_url = file_info.get('url')
|
||||
cookies_to_use_for_file = None
|
||||
if self.use_cookie:
|
||||
cookies_to_use_for_file = prepare_cookies_for_request(self.use_cookie, self.cookie_text, self.selected_cookie_file, self.app_base_dir, self.logger)
|
||||
|
||||
|
||||
if self.skip_file_size_mb is not None:
|
||||
api_original_filename_for_size_check = file_info.get('_original_name_for_log', file_info.get('name'))
|
||||
try:
|
||||
# Use a stream=True HEAD request to get headers without downloading the body
|
||||
with requests.head(file_url, headers=file_download_headers, timeout=15, cookies=cookies_to_use_for_file, allow_redirects=True) as head_response:
|
||||
head_response.raise_for_status()
|
||||
content_length = head_response.headers.get('Content-Length')
|
||||
if content_length:
|
||||
file_size_bytes = int(content_length)
|
||||
file_size_mb = file_size_bytes / (1024 * 1024)
|
||||
if file_size_mb < self.skip_file_size_mb:
|
||||
self.logger(f" -> Skip File (Size): '{api_original_filename_for_size_check}' is {file_size_mb:.2f} MB, which is smaller than the {self.skip_file_size_mb} MB limit.")
|
||||
return 0, 1, api_original_filename_for_size_check, False, FILE_DOWNLOAD_STATUS_SKIPPED, None
|
||||
else:
|
||||
self.logger(f" ⚠️ Could not determine file size for '{api_original_filename_for_size_check}' to check against size limit. Proceeding with download.")
|
||||
except requests.RequestException as e:
|
||||
self.logger(f" ⚠️ Could not fetch file headers to check size for '{api_original_filename_for_size_check}': {e}. Proceeding with download.")
|
||||
|
||||
api_original_filename = file_info.get('_original_name_for_log', file_info.get('name'))
|
||||
filename_to_save_in_main_path = ""
|
||||
if forced_filename_override:
|
||||
@@ -232,34 +309,28 @@ class PostProcessorWorker:
|
||||
self.logger(f" -> Skip File (Keyword in Original Name '{skip_word}'): '{api_original_filename}'. Scope: {self.skip_words_scope}")
|
||||
return 0, 1, api_original_filename, False, FILE_DOWNLOAD_STATUS_SKIPPED, None
|
||||
|
||||
cleaned_original_api_filename = clean_filename(api_original_filename)
|
||||
cleaned_original_api_filename = robust_clean_name(api_original_filename)
|
||||
original_filename_cleaned_base, original_ext = os.path.splitext(cleaned_original_api_filename)
|
||||
if not original_ext.startswith('.'): original_ext = '.' + original_ext if original_ext else ''
|
||||
|
||||
if self.manga_mode_active:
|
||||
if self.manga_filename_style == STYLE_ORIGINAL_NAME:
|
||||
# Get the post's publication or added date
|
||||
published_date_str = self.post.get('published')
|
||||
added_date_str = self.post.get('added')
|
||||
formatted_date_str = "nodate" # Fallback if no date is found
|
||||
|
||||
formatted_date_str = "nodate"
|
||||
date_to_use_str = published_date_str or added_date_str
|
||||
|
||||
if date_to_use_str:
|
||||
try:
|
||||
# Extract just the YYYY-MM-DD part from the timestamp
|
||||
formatted_date_str = date_to_use_str.split('T')[0]
|
||||
except Exception:
|
||||
self.logger(f" ⚠️ Could not parse date '{date_to_use_str}'. Using 'nodate' prefix.")
|
||||
else:
|
||||
self.logger(f" ⚠️ Post ID {original_post_id_for_log} has no date. Using 'nodate' prefix.")
|
||||
|
||||
# Combine the date with the cleaned original filename
|
||||
filename_to_save_in_main_path = f"{formatted_date_str}_{cleaned_original_api_filename}"
|
||||
was_original_name_kept_flag = True
|
||||
elif self.manga_filename_style == STYLE_POST_TITLE:
|
||||
if post_title and post_title.strip():
|
||||
cleaned_post_title_base = clean_filename(post_title.strip())
|
||||
cleaned_post_title_base = robust_clean_name(post_title.strip())
|
||||
if num_files_in_this_post > 1:
|
||||
if file_index_in_post == 0:
|
||||
filename_to_save_in_main_path = f"{cleaned_post_title_base}{original_ext}"
|
||||
@@ -280,7 +351,7 @@ class PostProcessorWorker:
|
||||
manga_date_file_counter_ref[0] += 1
|
||||
base_numbered_name = f"{counter_val_for_filename:03d}"
|
||||
if self.manga_date_prefix and self.manga_date_prefix.strip():
|
||||
cleaned_prefix = clean_filename(self.manga_date_prefix.strip())
|
||||
cleaned_prefix = robust_clean_name(self.manga_date_prefix.strip())
|
||||
if cleaned_prefix:
|
||||
filename_to_save_in_main_path = f"{cleaned_prefix} {base_numbered_name}{original_ext}"
|
||||
else:
|
||||
@@ -297,7 +368,7 @@ class PostProcessorWorker:
|
||||
with counter_lock:
|
||||
counter_val_for_filename = manga_global_file_counter_ref[0]
|
||||
manga_global_file_counter_ref[0] += 1
|
||||
cleaned_post_title_base_for_global = clean_filename(post_title.strip() if post_title and post_title.strip() else "post")
|
||||
cleaned_post_title_base_for_global = robust_clean_name(post_title.strip() if post_title and post_title.strip() else "post")
|
||||
filename_to_save_in_main_path = f"{cleaned_post_title_base_for_global}_{counter_val_for_filename:03d}{original_ext}"
|
||||
else:
|
||||
self.logger(f"⚠️ Manga Title+GlobalNum Mode: Counter ref not provided or malformed for '{api_original_filename}'. Using original. Ref: {manga_global_file_counter_ref}")
|
||||
@@ -329,8 +400,8 @@ class PostProcessorWorker:
|
||||
self.logger(f" ⚠️ Post ID {original_post_id_for_log} missing both 'published' and 'added' dates for STYLE_DATE_POST_TITLE. Using 'nodate'.")
|
||||
|
||||
if post_title and post_title.strip():
|
||||
temp_cleaned_title = clean_filename(post_title.strip())
|
||||
if not temp_cleaned_title or temp_cleaned_title.startswith("untitled_file"):
|
||||
temp_cleaned_title = robust_clean_name(post_title.strip())
|
||||
if not temp_cleaned_title or temp_cleaned_title.startswith("untitled_folder"):
|
||||
self.logger(f"⚠️ Manga mode (Date+PostTitle Style): Post title for post {original_post_id_for_log} ('{post_title}') was empty or generic after cleaning. Using 'post' as title part.")
|
||||
cleaned_post_title_for_filename = "post"
|
||||
else:
|
||||
@@ -357,8 +428,26 @@ class PostProcessorWorker:
|
||||
self.logger(f"⚠️ Manga mode: Generated filename was empty. Using generic fallback: '{filename_to_save_in_main_path}'.")
|
||||
was_original_name_kept_flag = False
|
||||
else:
|
||||
filename_to_save_in_main_path = cleaned_original_api_filename
|
||||
was_original_name_kept_flag = True
|
||||
is_url_like = 'http' in api_original_filename.lower()
|
||||
is_too_long = len(cleaned_original_api_filename) > 100
|
||||
|
||||
if is_url_like or is_too_long:
|
||||
self.logger(f" ⚠️ Original filename is a URL or too long. Generating a shorter name.")
|
||||
name_hash = hashlib.md5(api_original_filename.encode()).hexdigest()[:12]
|
||||
_, ext = os.path.splitext(cleaned_original_api_filename)
|
||||
if not ext:
|
||||
try:
|
||||
path = urlparse(api_original_filename).path
|
||||
ext = os.path.splitext(path)[1] or ".file"
|
||||
except Exception:
|
||||
ext = ".file"
|
||||
|
||||
cleaned_post_title = robust_clean_name(post_title.strip() if post_title else "post")[:40]
|
||||
filename_to_save_in_main_path = f"{cleaned_post_title}_{name_hash}{ext}"
|
||||
was_original_name_kept_flag = False
|
||||
else:
|
||||
filename_to_save_in_main_path = cleaned_original_api_filename
|
||||
was_original_name_kept_flag = True
|
||||
|
||||
if self.remove_from_filename_words_list and filename_to_save_in_main_path:
|
||||
base_name_for_removal, ext_for_removal = os.path.splitext(filename_to_save_in_main_path)
|
||||
@@ -408,43 +497,109 @@ class PostProcessorWorker:
|
||||
temp_file_base_for_unique_part, temp_file_ext_for_unique_part = os.path.splitext(filename_to_save_in_main_path if filename_to_save_in_main_path else api_original_filename)
|
||||
unique_id_for_part_file = uuid.uuid4().hex[:8]
|
||||
unique_part_file_stem_on_disk = f"{temp_file_base_for_unique_part}_{unique_id_for_part_file}"
|
||||
max_retries = 3
|
||||
if not self.keep_in_post_duplicates:
|
||||
final_save_path_check = os.path.join(target_folder_path, filename_to_save_in_main_path)
|
||||
if os.path.exists(final_save_path_check):
|
||||
try:
|
||||
with requests.head(file_url, headers=file_download_headers, timeout=15, cookies=cookies_to_use_for_file, allow_redirects=True) as head_response:
|
||||
head_response.raise_for_status()
|
||||
expected_size = int(head_response.headers.get('Content-Length', -1))
|
||||
|
||||
actual_size = os.path.getsize(final_save_path_check)
|
||||
|
||||
if expected_size != -1 and actual_size == expected_size:
|
||||
self.logger(f" -> Skip (File Exists & Complete): '{filename_to_save_in_main_path}' is already on disk with the correct size.")
|
||||
try:
|
||||
md5_hasher = hashlib.md5()
|
||||
with open(final_save_path_check, 'rb') as f_verify:
|
||||
for chunk in iter(lambda: f_verify.read(8192), b""):
|
||||
md5_hasher.update(chunk)
|
||||
with self.downloaded_hash_counts_lock:
|
||||
self.downloaded_hash_counts[md5_hasher.hexdigest()] += 1
|
||||
except Exception as hash_exc:
|
||||
self.logger(f" ⚠️ Could not hash existing file '{filename_to_save_in_main_path}' for session: {hash_exc}")
|
||||
return 0, 1, filename_to_save_in_main_path, was_original_name_kept_flag, FILE_DOWNLOAD_STATUS_SKIPPED, None
|
||||
else:
|
||||
self.logger(f" ⚠️ File '{filename_to_save_in_main_path}' exists but is incomplete (Expected: {expected_size}, Actual: {actual_size}). Re-downloading.")
|
||||
except requests.RequestException as e:
|
||||
self.logger(f" ⚠️ Could not verify size of existing file '{filename_to_save_in_main_path}': {e}. Proceeding with download.")
|
||||
|
||||
max_retries = 3
|
||||
retry_delay = 5
|
||||
downloaded_size_bytes = 0
|
||||
calculated_file_hash = None
|
||||
downloaded_part_file_path = None
|
||||
total_size_bytes = 0
|
||||
download_successful_flag = False
|
||||
last_exception_for_retry_later = None
|
||||
is_permanent_error = False
|
||||
data_to_write_io = None
|
||||
|
||||
response_for_this_attempt = None
|
||||
for attempt_num_single_stream in range(max_retries + 1):
|
||||
response_for_this_attempt = None
|
||||
response = None
|
||||
if self._check_pause(f"File download attempt for '{api_original_filename}'"): break
|
||||
if self.check_cancel() or (skip_event and skip_event.is_set()): break
|
||||
try:
|
||||
if attempt_num_single_stream > 0:
|
||||
self.logger(f" Retrying download for '{api_original_filename}' (Overall Attempt {attempt_num_single_stream + 1}/{max_retries + 1})...")
|
||||
time.sleep(retry_delay * (2 ** (attempt_num_single_stream - 1)))
|
||||
|
||||
self._emit_signal('file_download_status', True)
|
||||
response = requests.get(file_url, headers=headers, timeout=(15, 300), stream=True, cookies=cookies_to_use_for_file)
|
||||
|
||||
current_url_to_try = file_url
|
||||
|
||||
response = requests.get(current_url_to_try, headers=file_download_headers, timeout=(30, 300), stream=True, cookies=cookies_to_use_for_file)
|
||||
|
||||
if response.status_code == 403 and ('kemono.cr' in current_url_to_try or 'coomer.st' in current_url_to_try):
|
||||
self.logger(f" ⚠️ Got 403 Forbidden for '{api_original_filename}'. Attempting subdomain rotation...")
|
||||
new_url = self._find_valid_subdomain(current_url_to_try)
|
||||
if new_url != current_url_to_try:
|
||||
self.logger(f" Retrying with new URL: {new_url}")
|
||||
file_url = new_url
|
||||
response.close() # Close the old response
|
||||
response = requests.get(new_url, headers=file_download_headers, timeout=(30, 300), stream=True, cookies=cookies_to_use_for_file)
|
||||
|
||||
response.raise_for_status()
|
||||
|
||||
# --- REVISED AND MOVED SIZE CHECK LOGIC ---
|
||||
total_size_bytes = int(response.headers.get('Content-Length', 0))
|
||||
num_parts_for_file = min(self.num_file_threads, MAX_PARTS_FOR_MULTIPART_DOWNLOAD)
|
||||
|
||||
if self.skip_file_size_mb is not None:
|
||||
if total_size_bytes > 0:
|
||||
file_size_mb = total_size_bytes / (1024 * 1024)
|
||||
if file_size_mb < self.skip_file_size_mb:
|
||||
self.logger(f" -> Skip File (Size): '{api_original_filename}' is {file_size_mb:.2f} MB, which is smaller than the {self.skip_file_size_mb} MB limit.")
|
||||
return 0, 1, api_original_filename, False, FILE_DOWNLOAD_STATUS_SKIPPED, None
|
||||
# If Content-Length is missing, we can't check, so we no longer log a warning here and just proceed.
|
||||
# --- END OF REVISED LOGIC ---
|
||||
|
||||
num_parts_for_file = min(self.multipart_parts_count, MAX_PARTS_FOR_MULTIPART_DOWNLOAD)
|
||||
|
||||
file_is_eligible_by_scope = False
|
||||
if self.multipart_scope == 'videos':
|
||||
if is_video(api_original_filename):
|
||||
file_is_eligible_by_scope = True
|
||||
elif self.multipart_scope == 'archives':
|
||||
if is_archive(api_original_filename):
|
||||
file_is_eligible_by_scope = True
|
||||
elif self.multipart_scope == 'both':
|
||||
if is_video(api_original_filename) or is_archive(api_original_filename):
|
||||
file_is_eligible_by_scope = True
|
||||
|
||||
min_size_in_bytes = self.multipart_min_size_mb * 1024 * 1024
|
||||
|
||||
attempt_multipart = (self.allow_multipart_download and MULTIPART_DOWNLOADER_AVAILABLE and
|
||||
num_parts_for_file > 1 and total_size_bytes > MIN_SIZE_FOR_MULTIPART_DOWNLOAD and
|
||||
file_is_eligible_by_scope and
|
||||
num_parts_for_file > 1 and total_size_bytes > min_size_in_bytes and
|
||||
'bytes' in response.headers.get('Accept-Ranges', '').lower())
|
||||
|
||||
if self._check_pause(f"Multipart decision for '{api_original_filename}'"): break
|
||||
|
||||
if attempt_multipart:
|
||||
if response_for_this_attempt:
|
||||
response_for_this_attempt.close()
|
||||
response_for_this_attempt = None
|
||||
response.close() # Close the initial connection before starting multipart
|
||||
mp_save_path_for_unique_part_stem_arg = os.path.join(target_folder_path, f"{unique_part_file_stem_on_disk}{temp_file_ext_for_unique_part}")
|
||||
mp_success, mp_bytes, mp_hash, mp_file_handle = download_file_in_parts(
|
||||
file_url, mp_save_path_for_unique_part_stem_arg, total_size_bytes, num_parts_for_file, headers, api_original_filename,
|
||||
file_url, mp_save_path_for_unique_part_stem_arg, total_size_bytes, num_parts_for_file, file_download_headers, api_original_filename,
|
||||
emitter_for_multipart=self.emitter, cookies_for_chunk_session=cookies_to_use_for_file,
|
||||
cancellation_event=self.cancellation_event, skip_event=skip_event, logger_func=self.logger,
|
||||
pause_event=self.pause_event
|
||||
@@ -453,7 +608,7 @@ class PostProcessorWorker:
|
||||
download_successful_flag = True
|
||||
downloaded_size_bytes = mp_bytes
|
||||
calculated_file_hash = mp_hash
|
||||
downloaded_part_file_path = mp_save_path_for_unique_part_stem_arg + ".part"
|
||||
downloaded_part_file_path = mp_save_path_for_unique_part_stem_arg
|
||||
if mp_file_handle: mp_file_handle.close()
|
||||
break
|
||||
else:
|
||||
@@ -467,7 +622,6 @@ class PostProcessorWorker:
|
||||
current_attempt_downloaded_bytes = 0
|
||||
md5_hasher = hashlib.md5()
|
||||
last_progress_time = time.time()
|
||||
single_stream_exception = None
|
||||
try:
|
||||
with open(current_single_stream_part_path, 'wb') as f_part:
|
||||
for chunk in response.iter_content(chunk_size=1 * 1024 * 1024):
|
||||
@@ -519,20 +673,23 @@ class PostProcessorWorker:
|
||||
if isinstance(e, requests.exceptions.ConnectionError) and ("Failed to resolve" in str(e) or "NameResolutionError" in str(e)):
|
||||
self.logger(" 💡 This looks like a DNS resolution problem. Please check your internet connection, DNS settings, or VPN.")
|
||||
except requests.exceptions.RequestException as e:
|
||||
self.logger(f" ❌ Download Error (Non-Retryable): {api_original_filename}. Error: {e}")
|
||||
last_exception_for_retry_later = e
|
||||
is_permanent_error = True
|
||||
if ("Failed to resolve" in str(e) or "NameResolutionError" in str(e)):
|
||||
self.logger(" 💡 This looks like a DNS resolution problem. Please check your internet connection, DNS settings, or VPN.")
|
||||
break
|
||||
if e.response is not None and e.response.status_code == 403:
|
||||
self.logger(f" ⚠️ Download Error (403 Forbidden): {api_original_filename}. This often requires valid cookies.")
|
||||
self.logger(f" Will retry... Check your 'Use Cookie' settings if this persists.")
|
||||
last_exception_for_retry_later = e
|
||||
else:
|
||||
self.logger(f" ❌ Download Error (Non-Retryable): {api_original_filename}. Error: {e}")
|
||||
last_exception_for_retry_later = e
|
||||
is_permanent_error = True
|
||||
break
|
||||
except Exception as e:
|
||||
self.logger(f" ❌ Unexpected Download Error: {api_original_filename}: {e}\n{traceback.format_exc(limit=2)}")
|
||||
last_exception_for_retry_later = e
|
||||
is_permanent_error = True
|
||||
break
|
||||
finally:
|
||||
if response_for_this_attempt:
|
||||
response_for_this_attempt.close()
|
||||
if response:
|
||||
response.close()
|
||||
self._emit_signal('file_download_status', False)
|
||||
|
||||
final_total_for_progress = total_size_bytes if download_successful_flag and total_size_bytes > 0 else downloaded_size_bytes
|
||||
@@ -601,26 +758,22 @@ class PostProcessorWorker:
|
||||
self.logger(f" 🔄 Compressing '{api_original_filename}' to WebP...")
|
||||
try:
|
||||
with Image.open(downloaded_part_file_path) as img:
|
||||
# Convert to RGB to avoid issues with paletted images or alpha channels in WebP
|
||||
if img.mode not in ('RGB', 'RGBA'):
|
||||
img = img.convert('RGBA')
|
||||
|
||||
# Use an in-memory buffer to save the compressed image
|
||||
output_buffer = BytesIO()
|
||||
img.save(output_buffer, format='WebP', quality=85)
|
||||
|
||||
# This buffer now holds the compressed data
|
||||
data_to_write_io = output_buffer
|
||||
|
||||
# Update the filename to use the .webp extension
|
||||
base, _ = os.path.splitext(filename_to_save_in_main_path)
|
||||
filename_to_save_in_main_path = f"{base}.webp"
|
||||
self.logger(f" ✅ Compression successful. New size: {len(data_to_write_io.getvalue()) / (1024*1024):.2f} MB")
|
||||
|
||||
except Exception as e_compress:
|
||||
self.logger(f" ⚠️ Failed to compress '{api_original_filename}': {e_compress}. Saving original file instead.")
|
||||
data_to_write_io = None # Ensure we fall back to saving the original
|
||||
|
||||
data_to_write_io = None
|
||||
|
||||
effective_save_folder = target_folder_path
|
||||
base_name, extension = os.path.splitext(filename_to_save_in_main_path)
|
||||
counter = 1
|
||||
@@ -637,17 +790,14 @@ class PostProcessorWorker:
|
||||
|
||||
try:
|
||||
if data_to_write_io:
|
||||
# Write the compressed data from the in-memory buffer
|
||||
with open(final_save_path, 'wb') as f_out:
|
||||
f_out.write(data_to_write_io.getvalue())
|
||||
# Clean up the original downloaded part file
|
||||
if downloaded_part_file_path and os.path.exists(downloaded_part_file_path):
|
||||
try:
|
||||
os.remove(downloaded_part_file_path)
|
||||
except OSError as e_rem:
|
||||
self.logger(f" -> Failed to remove .part after compression: {e_rem}")
|
||||
else:
|
||||
# No compression was done, just rename the original file
|
||||
if downloaded_part_file_path and os.path.exists(downloaded_part_file_path):
|
||||
time.sleep(0.1)
|
||||
os.rename(downloaded_part_file_path, final_save_path)
|
||||
@@ -694,10 +844,12 @@ class PostProcessorWorker:
|
||||
self.logger(f" -> Failed to remove partially saved file: {final_save_path}")
|
||||
|
||||
permanent_failure_details = {
|
||||
'file_info': file_info, 'target_folder_path': target_folder_path, 'headers': headers,
|
||||
'file_info': file_info, 'target_folder_path': target_folder_path, 'headers': file_download_headers,
|
||||
'original_post_id_for_log': original_post_id_for_log, 'post_title': post_title,
|
||||
'file_index_in_post': file_index_in_post, 'num_files_in_this_post': num_files_in_this_post,
|
||||
'forced_filename_override': filename_to_save_in_main_path,
|
||||
'service': self.service,
|
||||
'user_id': self.user_id
|
||||
}
|
||||
return 0, 1, final_filename_saved_for_return, was_original_name_kept_flag, FILE_DOWNLOAD_STATUS_FAILED_PERMANENTLY_THIS_SESSION, permanent_failure_details
|
||||
finally:
|
||||
@@ -708,7 +860,7 @@ class PostProcessorWorker:
|
||||
details_for_failure = {
|
||||
'file_info': file_info,
|
||||
'target_folder_path': target_folder_path,
|
||||
'headers': headers,
|
||||
'headers': file_download_headers,
|
||||
'original_post_id_for_log': original_post_id_for_log,
|
||||
'post_title': post_title,
|
||||
'file_index_in_post': file_index_in_post,
|
||||
@@ -722,42 +874,114 @@ class PostProcessorWorker:
|
||||
|
||||
def process(self):
|
||||
|
||||
if self.service == 'discord':
|
||||
post_title = self.post.get('content', '') or f"Message {self.post.get('id', 'N/A')}"
|
||||
post_id = self.post.get('id', 'unknown_id')
|
||||
post_main_file_info = {}
|
||||
post_attachments = self.post.get('attachments', [])
|
||||
post_content_html = self.post.get('content', '')
|
||||
post_data = self.post
|
||||
log_prefix = "Message"
|
||||
else:
|
||||
post_title = self.post.get('title', '') or 'untitled_post'
|
||||
post_id = self.post.get('id', 'unknown_id')
|
||||
post_main_file_info = self.post.get('file')
|
||||
post_attachments = self.post.get('attachments', [])
|
||||
post_content_html = self.post.get('content', '')
|
||||
post_data = self.post
|
||||
log_prefix = "Post"
|
||||
|
||||
content_is_needed = (
|
||||
self.show_external_links or
|
||||
self.extract_links_only or
|
||||
self.scan_content_for_images or
|
||||
(self.filter_mode == 'text_only' and self.text_only_scope == 'content')
|
||||
)
|
||||
|
||||
if content_is_needed and self.post.get('content') is None and self.service != 'discord':
|
||||
|
||||
self.logger(f" Post {post_id} is missing 'content' field, fetching full data...")
|
||||
parsed_url = urlparse(self.api_url_input)
|
||||
api_domain = parsed_url.netloc
|
||||
creator_page_url = f"https://{api_domain}/{self.service}/user/{self.user_id}"
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)',
|
||||
'Referer': creator_page_url,
|
||||
'Accept': 'text/css'
|
||||
|
||||
}
|
||||
|
||||
|
||||
cookies = prepare_cookies_for_request(self.use_cookie, self.cookie_text, self.selected_cookie_file, self.app_base_dir, self.logger, target_domain=api_domain)
|
||||
|
||||
full_post_data = fetch_single_post_data(api_domain, self.service, self.user_id, post_id, headers, self.logger, cookies_dict=cookies)
|
||||
|
||||
if full_post_data:
|
||||
self.logger(" ✅ Full post data fetched successfully.")
|
||||
self.post = full_post_data
|
||||
post_title = self.post.get('title', '') or 'untitled_post'
|
||||
post_main_file_info = self.post.get('file')
|
||||
post_attachments = self.post.get('attachments', [])
|
||||
post_content_html = self.post.get('content', '')
|
||||
post_data = self.post
|
||||
else:
|
||||
self.logger(f" ⚠️ Failed to fetch full content for post {post_id}. Content-dependent features may not work for this post.")
|
||||
|
||||
result_tuple = (0, 0, [], [], [], None, None)
|
||||
total_downloaded_this_post = 0
|
||||
total_skipped_this_post = 0
|
||||
determined_post_save_path_for_history = self.override_output_dir if self.override_output_dir else self.download_root
|
||||
|
||||
try:
|
||||
if self._check_pause(f"Post processing for ID {self.post.get('id', 'N/A')}"):
|
||||
result_tuple = (0, 0, [], [], [], None, None)
|
||||
return result_tuple
|
||||
if self._check_pause(f"{log_prefix} processing for ID {post_id}"):
|
||||
return (0, 0, [], [], [], None, None)
|
||||
if self.check_cancel():
|
||||
result_tuple = (0, 0, [], [], [], None, None)
|
||||
return result_tuple
|
||||
return (0, 0, [], [], [], None, None)
|
||||
|
||||
current_character_filters = self._get_current_character_filters()
|
||||
kept_original_filenames_for_log = []
|
||||
retryable_failures_this_post = []
|
||||
permanent_failures_this_post = []
|
||||
total_downloaded_this_post = 0
|
||||
total_skipped_this_post = 0
|
||||
|
||||
history_data_for_this_post = None
|
||||
|
||||
parsed_api_url = urlparse(self.api_url_input)
|
||||
referer_url = f"https://{parsed_api_url.netloc}/"
|
||||
headers = {'User-Agent': 'Mozilla/5.0', 'Referer': referer_url, 'Accept': '*/*'}
|
||||
link_pattern = re.compile(r"""<a\s+.*?href=["'](https?://[^"']+)["'][^>]*>(.*?)</a>""", re.IGNORECASE | re.DOTALL)
|
||||
post_data = self.post
|
||||
post_title = post_data.get('title', '') or 'untitled_post'
|
||||
post_id = post_data.get('id', 'unknown_id')
|
||||
post_main_file_info = post_data.get('file')
|
||||
post_attachments = post_data.get('attachments', [])
|
||||
|
||||
# CONTEXT-AWARE URL for Referer Header
|
||||
if self.service == 'discord':
|
||||
server_id = self.user_id
|
||||
channel_id = self.post.get('channel', 'unknown_channel')
|
||||
post_page_url = f"https://{parsed_api_url.netloc}/discord/server/{server_id}/{channel_id}"
|
||||
else:
|
||||
post_page_url = f"https://{parsed_api_url.netloc}/{self.service}/user/{self.user_id}/post/{post_id}"
|
||||
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)',
|
||||
'Referer': post_page_url,
|
||||
'Accept': 'text/css'
|
||||
}
|
||||
link_pattern = re.compile(r"""<a\s+.*?href=["'](https?://[^"']+)["'][^>]*>(.*?)</a>""", re.IGNORECASE | re.DOTALL)
|
||||
|
||||
effective_unwanted_keywords_for_folder_naming = self.unwanted_keywords.copy()
|
||||
is_full_creator_download_no_char_filter = not self.target_post_id_from_initial_url and not current_character_filters
|
||||
|
||||
if (self.show_external_links or self.extract_links_only):
|
||||
embed_data = post_data.get('embed')
|
||||
if isinstance(embed_data, dict) and embed_data.get('url'):
|
||||
embed_url = embed_data['url']
|
||||
embed_subject = embed_data.get('subject', embed_url) # Use subject as link text, fallback to URL
|
||||
platform = get_link_platform(embed_url)
|
||||
|
||||
self.logger(f" 🔗 Found embed link: {embed_url}")
|
||||
self._emit_signal('external_link', post_title, embed_subject, embed_url, platform, "")
|
||||
|
||||
if is_full_creator_download_no_char_filter and self.creator_download_folder_ignore_words:
|
||||
self.logger(f" Applying creator download specific folder ignore words ({len(self.creator_download_folder_ignore_words)} words).")
|
||||
effective_unwanted_keywords_for_folder_naming.update(self.creator_download_folder_ignore_words)
|
||||
|
||||
post_content_html = post_data.get('content', '')
|
||||
if not self.extract_links_only:
|
||||
self.logger(f"\n--- Processing Post {post_id} ('{post_title[:50]}...') (Thread: {threading.current_thread().name}) ---")
|
||||
self.logger(f"\n--- Processing {log_prefix} {post_id} ('{post_title[:50]}...') (Thread: {threading.current_thread().name}) ---")
|
||||
|
||||
num_potential_files_in_post = len(post_attachments or []) + (1 if post_main_file_info and post_main_file_info.get('path') else 0)
|
||||
|
||||
post_is_candidate_by_title_char_match = False
|
||||
@@ -789,8 +1013,8 @@ class PostProcessorWorker:
|
||||
|
||||
all_files_from_post_api_for_char_check = []
|
||||
api_file_domain_for_char_check = urlparse(self.api_url_input).netloc
|
||||
if not api_file_domain_for_char_check or not any(d in api_file_domain_for_char_check.lower() for d in ['kemono.su', 'kemono.party', 'coomer.su', 'coomer.party']):
|
||||
api_file_domain_for_char_check = "kemono.su" if "kemono" in self.service.lower() else "coomer.party"
|
||||
if not api_file_domain_for_char_check or not any(d in api_file_domain_for_char_check.lower() for d in ['kemono.su', 'kemono.party', 'kemono.cr', 'coomer.su', 'coomer.party', 'coomer.st']):
|
||||
api_file_domain_for_char_check = "kemono.cr" if "kemono" in self.service.lower() else "coomer.st"
|
||||
if post_main_file_info and isinstance(post_main_file_info, dict) and post_main_file_info.get('path'):
|
||||
original_api_name = post_main_file_info.get('name') or os.path.basename(post_main_file_info['path'].lstrip('/'))
|
||||
if original_api_name:
|
||||
@@ -801,7 +1025,7 @@ class PostProcessorWorker:
|
||||
if original_api_att_name:
|
||||
all_files_from_post_api_for_char_check.append({'_original_name_for_log': original_api_att_name})
|
||||
|
||||
if current_character_filters and self.char_filter_scope == CHAR_SCOPE_COMMENTS:
|
||||
if current_character_filters and self.char_filter_scope == CHAR_SCOPE_COMMENTS and self.service != 'discord':
|
||||
self.logger(f" [Char Scope: Comments] Phase 1: Checking post files for matches before comments for post ID '{post_id}'.")
|
||||
if self._check_pause(f"File check (comments scope) for post {post_id}"):
|
||||
result_tuple = (0, num_potential_files_in_post, [], [], [], None, None)
|
||||
@@ -824,7 +1048,7 @@ class PostProcessorWorker:
|
||||
if post_is_candidate_by_file_char_match_in_comment_scope: break
|
||||
self.logger(f" [Char Scope: Comments] Phase 1 Result: post_is_candidate_by_file_char_match_in_comment_scope = {post_is_candidate_by_file_char_match_in_comment_scope}")
|
||||
|
||||
if current_character_filters and self.char_filter_scope == CHAR_SCOPE_COMMENTS:
|
||||
if current_character_filters and self.char_filter_scope == CHAR_SCOPE_COMMENTS and self.service != 'discord':
|
||||
if not post_is_candidate_by_file_char_match_in_comment_scope:
|
||||
if self._check_pause(f"Comment check for post {post_id}"):
|
||||
result_tuple = (0, num_potential_files_in_post, [], [], [], None, None)
|
||||
@@ -833,9 +1057,9 @@ class PostProcessorWorker:
|
||||
try:
|
||||
parsed_input_url_for_comments = urlparse(self.api_url_input)
|
||||
api_domain_for_comments = parsed_input_url_for_comments.netloc
|
||||
if not any(d in api_domain_for_comments.lower() for d in ['kemono.su', 'kemono.party', 'coomer.su', 'coomer.party']):
|
||||
if not any(d in api_domain_for_comments.lower() for d in ['kemono.su', 'kemono.party', 'kemono.cr', 'coomer.su', 'coomer.party', 'coomer.st']):
|
||||
self.logger(f"⚠️ Unrecognized domain '{api_domain_for_comments}' for comment API. Defaulting based on service.")
|
||||
api_domain_for_comments = "kemono.su" if "kemono" in self.service.lower() else "coomer.party"
|
||||
api_domain_for_comments = "kemono.cr" if "kemono" in self.service.lower() else "coomer.st"
|
||||
comments_data = fetch_post_comments(
|
||||
api_domain_for_comments, self.service, self.user_id, post_id,
|
||||
headers, self.logger, self.cancellation_event, self.pause_event,
|
||||
@@ -888,10 +1112,10 @@ class PostProcessorWorker:
|
||||
return result_tuple
|
||||
|
||||
if not self.extract_links_only and self.manga_mode_active and current_character_filters and (self.char_filter_scope == CHAR_SCOPE_TITLE or self.char_filter_scope == CHAR_SCOPE_BOTH) and not post_is_candidate_by_title_char_match:
|
||||
self.logger(f" -> Skip Post (Manga Mode with Title/Both Scope - No Title Char Match): Title '{post_title[:50]}' doesn't match filters.")
|
||||
self._emit_signal('missed_character_post', post_title, "Manga Mode: No title match for character filter (Title/Both scope)")
|
||||
result_tuple = (0, num_potential_files_in_post, [], [], [], None, None)
|
||||
return result_tuple
|
||||
self.logger(f" -> Skip Post (Manga Mode with Title/Both Scope - No Title Char Match): Title '{post_title[:50]}' doesn't match filters.")
|
||||
self._emit_signal('missed_character_post', post_title, "Manga Mode: No title match for character filter (Title/Both scope)")
|
||||
result_tuple = (0, num_potential_files_in_post, [], [], [], None, None)
|
||||
return result_tuple
|
||||
|
||||
if not isinstance(post_attachments, list):
|
||||
self.logger(f"⚠️ Corrupt attachment data for post {post_id} (expected list, got {type(post_attachments)}). Skipping attachments.")
|
||||
@@ -996,7 +1220,10 @@ class PostProcessorWorker:
|
||||
determined_post_save_path_for_history = os.path.join(determined_post_save_path_for_history, base_folder_names_for_post_content[0])
|
||||
|
||||
if not self.extract_links_only and self.use_post_subfolders:
|
||||
cleaned_post_title_for_sub = clean_folder_name(post_title)
|
||||
cleaned_post_title_for_sub = robust_clean_name(post_title)
|
||||
max_folder_len = 100
|
||||
if len(cleaned_post_title_for_sub) > max_folder_len:
|
||||
cleaned_post_title_for_sub = cleaned_post_title_for_sub[:max_folder_len].strip()
|
||||
post_id_for_fallback = self.post.get('id', 'unknown_id')
|
||||
|
||||
if not cleaned_post_title_for_sub or cleaned_post_title_for_sub == "untitled_folder":
|
||||
@@ -1021,29 +1248,50 @@ class PostProcessorWorker:
|
||||
suffix_counter = 0
|
||||
final_post_subfolder_name = ""
|
||||
|
||||
while True:
|
||||
suffix_counter = 0
|
||||
folder_creation_successful = False
|
||||
final_post_subfolder_name = ""
|
||||
post_id_for_folder = str(self.post.get('id', 'unknown_id'))
|
||||
|
||||
while not folder_creation_successful:
|
||||
if suffix_counter == 0:
|
||||
name_candidate = original_cleaned_post_title_for_sub
|
||||
else:
|
||||
name_candidate = f"{original_cleaned_post_title_for_sub}_{suffix_counter}"
|
||||
|
||||
potential_post_subfolder_path = os.path.join(base_path_for_post_subfolder, name_candidate)
|
||||
try:
|
||||
os.makedirs(potential_post_subfolder_path, exist_ok=False)
|
||||
final_post_subfolder_name = name_candidate
|
||||
if suffix_counter > 0:
|
||||
self.logger(f" Post subfolder name conflict: Using '{final_post_subfolder_name}' instead of '{original_cleaned_post_title_for_sub}' to avoid mixing posts.")
|
||||
break
|
||||
except FileExistsError:
|
||||
suffix_counter += 1
|
||||
if suffix_counter > 100:
|
||||
self.logger(f" ⚠️ Exceeded 100 attempts to find unique subfolder name for '{original_cleaned_post_title_for_sub}'. Using UUID.")
|
||||
final_post_subfolder_name = f"{original_cleaned_post_title_for_sub}_{uuid.uuid4().hex[:8]}"
|
||||
os.makedirs(os.path.join(base_path_for_post_subfolder, final_post_subfolder_name), exist_ok=True)
|
||||
id_file_path = os.path.join(potential_post_subfolder_path, f".postid_{post_id_for_folder}")
|
||||
|
||||
if not os.path.isdir(potential_post_subfolder_path):
|
||||
# Folder does not exist, create it and its ID file
|
||||
try:
|
||||
os.makedirs(potential_post_subfolder_path)
|
||||
with open(id_file_path, 'w') as f:
|
||||
f.write(post_id_for_folder)
|
||||
|
||||
final_post_subfolder_name = name_candidate
|
||||
folder_creation_successful = True
|
||||
if suffix_counter > 0:
|
||||
self.logger(f" Post subfolder name conflict: Using '{final_post_subfolder_name}' to avoid mixing posts.")
|
||||
except OSError as e_mkdir:
|
||||
self.logger(f" ❌ Error creating directory '{potential_post_subfolder_path}': {e_mkdir}.")
|
||||
final_post_subfolder_name = original_cleaned_post_title_for_sub
|
||||
break
|
||||
except OSError as e_mkdir:
|
||||
self.logger(f" ❌ Error creating directory '{potential_post_subfolder_path}': {e_mkdir}. Files for this post might be saved in parent or fail.")
|
||||
final_post_subfolder_name = original_cleaned_post_title_for_sub
|
||||
break
|
||||
else:
|
||||
# Folder exists, check if it's for this post or a different one
|
||||
if os.path.exists(id_file_path):
|
||||
# ID file matches! This is a restore scenario. Reuse the folder.
|
||||
self.logger(f" ℹ️ Re-using existing post subfolder: '{name_candidate}'")
|
||||
final_post_subfolder_name = name_candidate
|
||||
folder_creation_successful = True
|
||||
else:
|
||||
# Folder exists but ID file does not match (or is missing). This is a normal name collision.
|
||||
suffix_counter += 1
|
||||
if suffix_counter > 100: # Safety break
|
||||
self.logger(f" ⚠️ Exceeded 100 attempts to find unique subfolder for '{original_cleaned_post_title_for_sub}'.")
|
||||
final_post_subfolder_name = f"{original_cleaned_post_title_for_sub}_{uuid.uuid4().hex[:8]}"
|
||||
os.makedirs(os.path.join(base_path_for_post_subfolder, final_post_subfolder_name), exist_ok=True)
|
||||
break
|
||||
determined_post_save_path_for_history = os.path.join(base_path_for_post_subfolder, final_post_subfolder_name)
|
||||
|
||||
if self.skip_words_list and (self.skip_words_scope == SKIP_SCOPE_POSTS or self.skip_words_scope == SKIP_SCOPE_BOTH):
|
||||
@@ -1092,7 +1340,6 @@ class PostProcessorWorker:
|
||||
parsed_url = urlparse(self.api_url_input)
|
||||
api_domain = parsed_url.netloc
|
||||
cookies = prepare_cookies_for_request(self.use_cookie, self.cookie_text, self.selected_cookie_file, self.app_base_dir, self.logger, target_domain=api_domain)
|
||||
from .api_client import fetch_single_post_data
|
||||
full_data = fetch_single_post_data(api_domain, self.service, self.user_id, post_id, headers, self.logger, cookies_dict=cookies)
|
||||
if full_data:
|
||||
final_post_data = full_data
|
||||
@@ -1175,11 +1422,18 @@ class PostProcessorWorker:
|
||||
if FPDF:
|
||||
self.logger(f" Creating formatted PDF for {'comments' if self.text_only_scope == 'comments' else 'content'}...")
|
||||
pdf = PDF()
|
||||
if getattr(sys, 'frozen', False) and hasattr(sys, '_MEIPASS'):
|
||||
# If the application is run as a bundled exe, _MEIPASS is the temp folder
|
||||
base_path = sys._MEIPASS
|
||||
else:
|
||||
# If running as a normal .py script, use the project_root_dir
|
||||
base_path = self.project_root_dir
|
||||
|
||||
font_path = ""
|
||||
bold_font_path = ""
|
||||
if self.project_root_dir:
|
||||
font_path = os.path.join(self.project_root_dir, 'data', 'dejavu-sans', 'DejaVuSans.ttf')
|
||||
bold_font_path = os.path.join(self.project_root_dir, 'data', 'dejavu-sans', 'DejaVuSans-Bold.ttf')
|
||||
if base_path:
|
||||
font_path = os.path.join(base_path, 'data', 'dejavu-sans', 'DejaVuSans.ttf')
|
||||
bold_font_path = os.path.join(base_path, 'data', 'dejavu-sans', 'DejaVuSans-Bold.ttf')
|
||||
|
||||
try:
|
||||
if not os.path.exists(font_path): raise RuntimeError(f"Font file not found: {font_path}")
|
||||
@@ -1312,9 +1566,8 @@ class PostProcessorWorker:
|
||||
|
||||
all_files_from_post_api = []
|
||||
api_file_domain = urlparse(self.api_url_input).netloc
|
||||
if not api_file_domain or not any(d in api_file_domain.lower() for d in ['kemono.su', 'kemono.party', 'coomer.su', 'coomer.party']):
|
||||
api_file_domain = "kemono.su" if "kemono" in self.service.lower() else "coomer.party"
|
||||
|
||||
if not api_file_domain or not any(d in api_file_domain.lower() for d in ['kemono.su', 'kemono.party', 'kemono.cr', 'coomer.su', 'coomer.party', 'coomer.st']):
|
||||
api_file_domain = "kemono.cr" if "kemono" in self.service.lower() else "coomer.st"
|
||||
if post_main_file_info and isinstance(post_main_file_info, dict) and post_main_file_info.get('path'):
|
||||
file_path = post_main_file_info['path'].lstrip('/')
|
||||
original_api_name = post_main_file_info.get('name') or os.path.basename(file_path)
|
||||
@@ -1572,7 +1825,7 @@ class PostProcessorWorker:
|
||||
self._download_single_file,
|
||||
file_info=file_info_to_dl,
|
||||
target_folder_path=current_path_for_file_instance,
|
||||
headers=headers, original_post_id_for_log=post_id, skip_event=self.skip_current_file_flag,
|
||||
post_page_url=post_page_url, original_post_id_for_log=post_id, skip_event=self.skip_current_file_flag,
|
||||
post_title=post_title, manga_date_file_counter_ref=manga_date_counter_to_pass,
|
||||
manga_global_file_counter_ref=manga_global_counter_to_pass, folder_context_name_for_history=folder_context_for_file,
|
||||
file_index_in_post=file_idx, num_files_in_this_post=len(files_to_download_info_list)
|
||||
@@ -1666,10 +1919,12 @@ class PostProcessorWorker:
|
||||
if not self.extract_links_only and self.use_post_subfolders and total_downloaded_this_post == 0:
|
||||
path_to_check_for_emptiness = determined_post_save_path_for_history
|
||||
try:
|
||||
# Check if the path is a directory and if it's empty
|
||||
if os.path.isdir(path_to_check_for_emptiness) and not os.listdir(path_to_check_for_emptiness):
|
||||
self.logger(f" 🗑️ Removing empty post-specific subfolder: '{path_to_check_for_emptiness}'")
|
||||
os.rmdir(path_to_check_for_emptiness)
|
||||
except OSError as e_rmdir:
|
||||
# Log if removal fails for any reason (e.g., permissions)
|
||||
self.logger(f" ⚠️ Could not remove empty post-specific subfolder '{path_to_check_for_emptiness}': {e_rmdir}")
|
||||
|
||||
result_tuple = (total_downloaded_this_post, total_skipped_this_post,
|
||||
@@ -1677,7 +1932,25 @@ class PostProcessorWorker:
|
||||
permanent_failures_this_post, history_data_for_this_post,
|
||||
None)
|
||||
|
||||
except Exception as main_thread_err:
|
||||
self.logger(f"\n❌ Critical error within Worker process for {log_prefix} {post_id}: {main_thread_err}")
|
||||
self.logger(traceback.format_exc())
|
||||
# Ensure we still return a valid tuple to prevent the app from stalling
|
||||
result_tuple = (0, 1, [], [], [{'error': str(main_thread_err)}], None, None)
|
||||
finally:
|
||||
# This block ALWAYS executes, ensuring that every task signals its completion.
|
||||
# This is critical for the main thread to know when all work is done.
|
||||
if not self.extract_links_only and self.use_post_subfolders and total_downloaded_this_post == 0:
|
||||
path_to_check_for_emptiness = determined_post_save_path_for_history
|
||||
try:
|
||||
# Check if the path is a directory and if it's empty
|
||||
if os.path.isdir(path_to_check_for_emptiness) and not os.listdir(path_to_check_for_emptiness):
|
||||
self.logger(f" 🗑️ Removing empty post-specific subfolder: '{path_to_check_for_emptiness}'")
|
||||
os.rmdir(path_to_check_for_emptiness)
|
||||
except OSError as e_rmdir:
|
||||
# Log if removal fails for any reason (e.g., permissions)
|
||||
self.logger(f" ⚠️ Could not remove potentially empty subfolder '{path_to_check_for_emptiness}': {e_rmdir}")
|
||||
|
||||
self._emit_signal('worker_finished', result_tuple)
|
||||
|
||||
return result_tuple
|
||||
@@ -1718,6 +1991,8 @@ class DownloadThread(QThread):
|
||||
remove_from_filename_words_list=None,
|
||||
manga_date_prefix='',
|
||||
allow_multipart_download=True,
|
||||
multipart_parts_count=4,
|
||||
multipart_min_size_mb=100,
|
||||
selected_cookie_file=None,
|
||||
override_output_dir=None,
|
||||
app_base_dir=None,
|
||||
@@ -1740,7 +2015,10 @@ class DownloadThread(QThread):
|
||||
single_pdf_mode=False,
|
||||
project_root_dir=None,
|
||||
processed_post_ids=None,
|
||||
start_offset=0):
|
||||
start_offset=0,
|
||||
fetch_first=False,
|
||||
skip_file_size_mb=None
|
||||
):
|
||||
super().__init__()
|
||||
self.api_url_input = api_url_input
|
||||
self.output_dir = output_dir
|
||||
@@ -1780,6 +2058,8 @@ class DownloadThread(QThread):
|
||||
self.remove_from_filename_words_list = remove_from_filename_words_list
|
||||
self.manga_date_prefix = manga_date_prefix
|
||||
self.allow_multipart_download = allow_multipart_download
|
||||
self.multipart_parts_count = multipart_parts_count
|
||||
self.multipart_min_size_mb = multipart_min_size_mb
|
||||
self.selected_cookie_file = selected_cookie_file
|
||||
self.app_base_dir = app_base_dir
|
||||
self.cookie_text = cookie_text
|
||||
@@ -1804,6 +2084,8 @@ class DownloadThread(QThread):
|
||||
self.project_root_dir = project_root_dir
|
||||
self.processed_post_ids_set = set(processed_post_ids) if processed_post_ids is not None else set()
|
||||
self.start_offset = start_offset
|
||||
self.fetch_first = fetch_first
|
||||
self.skip_file_size_mb = skip_file_size_mb
|
||||
|
||||
if self.compress_images and Image is None:
|
||||
self.logger("⚠️ Image compression disabled: Pillow library not found (DownloadThread).")
|
||||
@@ -1850,7 +2132,8 @@ class DownloadThread(QThread):
|
||||
selected_cookie_file=self.selected_cookie_file,
|
||||
app_base_dir=self.app_base_dir,
|
||||
manga_filename_style_for_sort_check=self.manga_filename_style if self.manga_mode_active else None,
|
||||
processed_post_ids=self.processed_post_ids_set
|
||||
processed_post_ids=self.processed_post_ids_set,
|
||||
fetch_all_first=self.fetch_first
|
||||
)
|
||||
|
||||
for posts_batch_data in post_generator:
|
||||
@@ -1921,6 +2204,9 @@ class DownloadThread(QThread):
|
||||
'text_only_scope': self.text_only_scope,
|
||||
'text_export_format': self.text_export_format,
|
||||
'single_pdf_mode': self.single_pdf_mode,
|
||||
'multipart_parts_count': self.multipart_parts_count,
|
||||
'multipart_min_size_mb': self.multipart_min_size_mb,
|
||||
'skip_file_size_mb': self.skip_file_size_mb,
|
||||
'project_root_dir': self.project_root_dir,
|
||||
}
|
||||
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -3,15 +3,20 @@ import os
|
||||
import re
|
||||
import traceback
|
||||
import json
|
||||
import base64
|
||||
import time
|
||||
import zipfile
|
||||
from urllib.parse import urlparse, urlunparse, parse_qs, urlencode
|
||||
|
||||
# --- Third-Party Library Imports ---
|
||||
# --- Third-party Library Imports ---
|
||||
import requests
|
||||
import cloudscraper
|
||||
|
||||
try:
|
||||
from mega import Mega
|
||||
MEGA_AVAILABLE = True
|
||||
from Crypto.Cipher import AES
|
||||
PYCRYPTODOME_AVAILABLE = True
|
||||
except ImportError:
|
||||
MEGA_AVAILABLE = False
|
||||
PYCRYPTODOME_AVAILABLE = False
|
||||
|
||||
try:
|
||||
import gdown
|
||||
@@ -19,96 +24,172 @@ try:
|
||||
except ImportError:
|
||||
GDRIVE_AVAILABLE = False
|
||||
|
||||
# --- Helper Functions ---
|
||||
MEGA_API_URL = "https://g.api.mega.co.nz"
|
||||
|
||||
def _get_filename_from_headers(headers):
|
||||
"""
|
||||
Extracts a filename from the Content-Disposition header.
|
||||
|
||||
Args:
|
||||
headers (dict): A dictionary of HTTP response headers.
|
||||
|
||||
Returns:
|
||||
str or None: The extracted filename, or None if not found.
|
||||
"""
|
||||
cd = headers.get('content-disposition')
|
||||
if not cd:
|
||||
return None
|
||||
|
||||
# Handles both filename="file.zip" and filename*=UTF-8''file%20name.zip
|
||||
fname_match = re.findall('filename="?([^"]+)"?', cd)
|
||||
if fname_match:
|
||||
# Sanitize the filename to prevent directory traversal issues
|
||||
# and remove invalid characters for most filesystems.
|
||||
sanitized_name = re.sub(r'[<>:"/\\|?*]', '_', fname_match[0].strip())
|
||||
return sanitized_name
|
||||
|
||||
return None
|
||||
|
||||
# --- Main Service Downloader Functions ---
|
||||
# --- Helper functions for Mega decryption ---
|
||||
|
||||
def download_mega_file(mega_url, download_path, logger_func=print):
|
||||
"""
|
||||
Downloads a file from a Mega.nz URL.
|
||||
Handles both public links and links that include a decryption key.
|
||||
"""
|
||||
if not MEGA_AVAILABLE:
|
||||
logger_func("❌ Mega download failed: 'mega.py' library is not installed.")
|
||||
def urlb64_to_b64(s):
|
||||
s = s.replace('-', '+').replace('_', '/')
|
||||
s += '=' * (-len(s) % 4)
|
||||
return s
|
||||
|
||||
def b64_to_bytes(s):
|
||||
return base64.b64decode(urlb64_to_b64(s))
|
||||
|
||||
def bytes_to_hex(b):
|
||||
return b.hex()
|
||||
|
||||
def hex_to_bytes(h):
|
||||
return bytes.fromhex(h)
|
||||
|
||||
def hrk2hk(hex_raw_key):
|
||||
key_part1 = int(hex_raw_key[0:16], 16)
|
||||
key_part2 = int(hex_raw_key[16:32], 16)
|
||||
key_part3 = int(hex_raw_key[32:48], 16)
|
||||
key_part4 = int(hex_raw_key[48:64], 16)
|
||||
|
||||
final_key_part1 = key_part1 ^ key_part3
|
||||
final_key_part2 = key_part2 ^ key_part4
|
||||
|
||||
return f'{final_key_part1:016x}{final_key_part2:016x}'
|
||||
|
||||
def decrypt_at(at_b64, key_bytes):
|
||||
at_bytes = b64_to_bytes(at_b64)
|
||||
iv = b'\0' * 16
|
||||
cipher = AES.new(key_bytes, AES.MODE_CBC, iv)
|
||||
decrypted_at = cipher.decrypt(at_bytes)
|
||||
return decrypted_at.decode('utf-8').strip('\0').replace('MEGA', '')
|
||||
|
||||
# --- Core Logic for Mega Downloads ---
|
||||
|
||||
def get_mega_file_info(file_id, file_key, session, logger_func):
|
||||
try:
|
||||
hex_raw_key = bytes_to_hex(b64_to_bytes(file_key))
|
||||
hex_key = hrk2hk(hex_raw_key)
|
||||
key_bytes = hex_to_bytes(hex_key)
|
||||
|
||||
payload = [{"a": "g", "p": file_id}]
|
||||
response = session.post(f"{MEGA_API_URL}/cs", json=payload, timeout=20)
|
||||
response.raise_for_status()
|
||||
res_json = response.json()
|
||||
|
||||
if isinstance(res_json, list) and isinstance(res_json[0], int) and res_json[0] < 0:
|
||||
logger_func(f" [Mega] ❌ API Error: {res_json[0]}. The link may be invalid or removed.")
|
||||
return None
|
||||
|
||||
file_size = res_json[0]['s']
|
||||
at_b64 = res_json[0]['at']
|
||||
at_dec_json_str = decrypt_at(at_b64, key_bytes)
|
||||
at_dec_json = json.loads(at_dec_json_str)
|
||||
file_name = at_dec_json['n']
|
||||
|
||||
payload = [{"a": "g", "g": 1, "p": file_id}]
|
||||
response = session.post(f"{MEGA_API_URL}/cs", json=payload, timeout=20)
|
||||
response.raise_for_status()
|
||||
res_json = response.json()
|
||||
dl_temp_url = res_json[0]['g']
|
||||
|
||||
return {
|
||||
'file_name': file_name,
|
||||
'file_size': file_size,
|
||||
'dl_url': dl_temp_url,
|
||||
'hex_raw_key': hex_raw_key
|
||||
}
|
||||
except (requests.RequestException, json.JSONDecodeError, KeyError, ValueError) as e:
|
||||
logger_func(f" [Mega] ❌ Failed to get file info: {e}")
|
||||
return None
|
||||
|
||||
def download_and_decrypt_mega_file(info, download_path, logger_func):
|
||||
file_name = info['file_name']
|
||||
file_size = info['file_size']
|
||||
dl_url = info['dl_url']
|
||||
hex_raw_key = info['hex_raw_key']
|
||||
final_path = os.path.join(download_path, file_name)
|
||||
|
||||
if os.path.exists(final_path) and os.path.getsize(final_path) == file_size:
|
||||
logger_func(f" [Mega] ℹ️ File '{file_name}' already exists with the correct size. Skipping.")
|
||||
return
|
||||
|
||||
logger_func(f" [Mega] Initializing Mega client...")
|
||||
key = hex_to_bytes(hrk2hk(hex_raw_key))
|
||||
iv_hex = hex_raw_key[32:48] + '0000000000000000'
|
||||
iv_bytes = hex_to_bytes(iv_hex)
|
||||
cipher = AES.new(key, AES.MODE_CTR, initial_value=iv_bytes, nonce=b'')
|
||||
|
||||
try:
|
||||
mega = Mega()
|
||||
# Anonymous login is sufficient for public links
|
||||
m = mega.login()
|
||||
|
||||
# --- MODIFIED PART: Added error handling for invalid links ---
|
||||
try:
|
||||
file_details = m.find(mega_url)
|
||||
if file_details is None:
|
||||
logger_func(f" [Mega] ❌ Download failed. The link appears to be invalid or has been taken down: {mega_url}")
|
||||
return
|
||||
except (ValueError, json.JSONDecodeError) as e:
|
||||
# This block catches the "Expecting value" error
|
||||
logger_func(f" [Mega] ❌ Download failed. The link is likely invalid or expired. Error: {e}")
|
||||
return
|
||||
except Exception as e:
|
||||
# Catch other potential errors from the mega.py library
|
||||
logger_func(f" [Mega] ❌ An unexpected error occurred trying to access the link: {e}")
|
||||
return
|
||||
# --- END OF MODIFIED PART ---
|
||||
|
||||
filename = file_details[1]['a']['n']
|
||||
logger_func(f" [Mega] File found: '{filename}'. Starting download...")
|
||||
|
||||
# Sanitize filename before saving
|
||||
safe_filename = "".join([c for c in filename if c.isalpha() or c.isdigit() or c in (' ', '.', '_', '-')]).rstrip()
|
||||
final_path = os.path.join(download_path, safe_filename)
|
||||
|
||||
# Check if file already exists
|
||||
if os.path.exists(final_path):
|
||||
logger_func(f" [Mega] ℹ️ File '{safe_filename}' already exists. Skipping download.")
|
||||
return
|
||||
|
||||
# Start the download
|
||||
m.download_url(mega_url, dest_path=download_path, dest_filename=safe_filename)
|
||||
logger_func(f" [Mega] ✅ Successfully downloaded '{safe_filename}' to '{download_path}'")
|
||||
|
||||
with requests.get(dl_url, stream=True, timeout=(15, 300)) as r:
|
||||
r.raise_for_status()
|
||||
downloaded_bytes = 0
|
||||
last_log_time = time.time()
|
||||
|
||||
with open(final_path, 'wb') as f:
|
||||
for chunk in r.iter_content(chunk_size=8192):
|
||||
if not chunk: continue
|
||||
decrypted_chunk = cipher.decrypt(chunk)
|
||||
f.write(decrypted_chunk)
|
||||
downloaded_bytes += len(chunk)
|
||||
|
||||
current_time = time.time()
|
||||
if current_time - last_log_time > 1:
|
||||
progress_percent = (downloaded_bytes / file_size) * 100 if file_size > 0 else 0
|
||||
logger_func(f" [Mega] Downloading '{file_name}': {downloaded_bytes/1024/1024:.2f}MB / {file_size/1024/1024:.2f}MB ({progress_percent:.1f}%)")
|
||||
last_log_time = current_time
|
||||
|
||||
logger_func(f" [Mega] ✅ Successfully downloaded '{file_name}' to '{download_path}'")
|
||||
except Exception as e:
|
||||
logger_func(f" [Mega] ❌ An unexpected error occurred during the Mega download process: {e}")
|
||||
logger_func(f" [Mega] ❌ An unexpected error occurred during download/decryption: {e}")
|
||||
|
||||
def download_mega_file(mega_url, download_path, logger_func=print):
|
||||
if not PYCRYPTODOME_AVAILABLE:
|
||||
logger_func("❌ Mega download failed: 'pycryptodome' library is not installed. Please run: pip install pycryptodome")
|
||||
return
|
||||
|
||||
logger_func(f" [Mega] Initializing download for: {mega_url}")
|
||||
|
||||
match = re.search(r'mega(?:\.co)?\.nz/(?:file/|#!)?([a-zA-Z0-9]+)(?:#|!)([a-zA-Z0-9_.-]+)', mega_url)
|
||||
if not match:
|
||||
logger_func(f" [Mega] ❌ Error: Invalid Mega URL format.")
|
||||
return
|
||||
|
||||
file_id = match.group(1)
|
||||
file_key = match.group(2)
|
||||
|
||||
session = requests.Session()
|
||||
session.headers.update({'User-Agent': 'Kemono-Downloader-PyQt/1.0'})
|
||||
|
||||
file_info = get_mega_file_info(file_id, file_key, session, logger_func)
|
||||
if not file_info:
|
||||
logger_func(f" [Mega] ❌ Failed to get file info. Aborting.")
|
||||
return
|
||||
|
||||
logger_func(f" [Mega] File found: '{file_info['file_name']}' (Size: {file_info['file_size'] / 1024 / 1024:.2f} MB)")
|
||||
|
||||
download_and_decrypt_mega_file(file_info, download_path, logger_func)
|
||||
|
||||
def download_gdrive_file(url, download_path, logger_func=print):
|
||||
"""Downloads a file from a Google Drive link."""
|
||||
if not GDRIVE_AVAILABLE:
|
||||
logger_func("❌ Google Drive download failed: 'gdown' library is not installed.")
|
||||
return
|
||||
try:
|
||||
logger_func(f" [G-Drive] Starting download for: {url}")
|
||||
# --- MODIFIED PART: Added a message and set quiet=True ---
|
||||
logger_func(" [G-Drive] Download in progress... This may take some time. Please wait.")
|
||||
|
||||
# By setting quiet=True, the progress bar will no longer be printed to the terminal.
|
||||
output_path = gdown.download(url, output=download_path, quiet=True, fuzzy=True)
|
||||
# --- END OF MODIFIED PART ---
|
||||
|
||||
if output_path and os.path.exists(output_path):
|
||||
logger_func(f" [G-Drive] ✅ Successfully downloaded to '{output_path}'")
|
||||
@@ -117,18 +198,15 @@ def download_gdrive_file(url, download_path, logger_func=print):
|
||||
except Exception as e:
|
||||
logger_func(f" [G-Drive] ❌ An unexpected error occurred: {e}")
|
||||
|
||||
# --- MODIFIED DROPBOX DOWNLOADER ---
|
||||
def download_dropbox_file(dropbox_link, download_path=".", logger_func=print):
|
||||
"""
|
||||
Downloads a file from a public Dropbox link by modifying the URL for direct download.
|
||||
|
||||
Args:
|
||||
dropbox_link (str): The public Dropbox link to the file.
|
||||
download_path (str): The directory to save the downloaded file.
|
||||
logger_func (callable): Function to use for logging.
|
||||
Downloads a file or a folder (as a zip) from a public Dropbox link.
|
||||
Uses cloudscraper to handle potential browser checks and auto-extracts zip files.
|
||||
"""
|
||||
logger_func(f" [Dropbox] Attempting to download: {dropbox_link}")
|
||||
|
||||
# Modify the Dropbox URL to force a direct download instead of showing the preview page.
|
||||
# Modify URL to force download (works for both files and folders)
|
||||
parsed_url = urlparse(dropbox_link)
|
||||
query_params = parse_qs(parsed_url.query)
|
||||
query_params['dl'] = ['1']
|
||||
@@ -137,28 +215,60 @@ def download_dropbox_file(dropbox_link, download_path=".", logger_func=print):
|
||||
|
||||
logger_func(f" [Dropbox] Using direct download URL: {direct_download_url}")
|
||||
|
||||
scraper = cloudscraper.create_scraper()
|
||||
|
||||
try:
|
||||
if not os.path.exists(download_path):
|
||||
os.makedirs(download_path, exist_ok=True)
|
||||
logger_func(f" [Dropbox] Created download directory: {download_path}")
|
||||
|
||||
with requests.get(direct_download_url, stream=True, allow_redirects=True, timeout=(10, 300)) as r:
|
||||
with scraper.get(direct_download_url, stream=True, allow_redirects=True, timeout=(20, 600)) as r:
|
||||
r.raise_for_status()
|
||||
|
||||
# Determine filename from headers or URL
|
||||
filename = _get_filename_from_headers(r.headers) or os.path.basename(parsed_url.path) or "dropbox_file"
|
||||
filename = _get_filename_from_headers(r.headers) or os.path.basename(parsed_url.path) or "dropbox_download"
|
||||
# If it's a folder, Dropbox will name it FolderName.zip
|
||||
if not os.path.splitext(filename)[1]:
|
||||
filename += ".zip"
|
||||
|
||||
full_save_path = os.path.join(download_path, filename)
|
||||
|
||||
logger_func(f" [Dropbox] Starting download of '{filename}'...")
|
||||
|
||||
# Write file to disk in chunks
|
||||
total_size = int(r.headers.get('content-length', 0))
|
||||
downloaded_bytes = 0
|
||||
last_log_time = time.time()
|
||||
|
||||
with open(full_save_path, 'wb') as f:
|
||||
for chunk in r.iter_content(chunk_size=8192):
|
||||
f.write(chunk)
|
||||
downloaded_bytes += len(chunk)
|
||||
current_time = time.time()
|
||||
if total_size > 0 and current_time - last_log_time > 1:
|
||||
progress = (downloaded_bytes / total_size) * 100
|
||||
logger_func(f" -> Downloading '{filename}'... {downloaded_bytes/1024/1024:.2f}MB / {total_size/1024/1024:.2f}MB ({progress:.1f}%)")
|
||||
last_log_time = current_time
|
||||
|
||||
logger_func(f" [Dropbox] ✅ Dropbox file downloaded successfully: {full_save_path}")
|
||||
logger_func(f" [Dropbox] ✅ Download complete: {full_save_path}")
|
||||
|
||||
# --- NEW: Auto-extraction logic ---
|
||||
if zipfile.is_zipfile(full_save_path):
|
||||
logger_func(f" [Dropbox] ዚ Detected zip file. Attempting to extract...")
|
||||
extract_folder_name = os.path.splitext(filename)[0]
|
||||
extract_path = os.path.join(download_path, extract_folder_name)
|
||||
os.makedirs(extract_path, exist_ok=True)
|
||||
|
||||
with zipfile.ZipFile(full_save_path, 'r') as zip_ref:
|
||||
zip_ref.extractall(extract_path)
|
||||
|
||||
logger_func(f" [Dropbox] ✅ Successfully extracted to folder: '{extract_path}'")
|
||||
|
||||
# Optional: remove the zip file after extraction
|
||||
try:
|
||||
os.remove(full_save_path)
|
||||
logger_func(f" [Dropbox] 🗑️ Removed original zip file.")
|
||||
except OSError as e:
|
||||
logger_func(f" [Dropbox] ⚠️ Could not remove original zip file: {e}")
|
||||
|
||||
except Exception as e:
|
||||
logger_func(f" [Dropbox] ❌ An error occurred during Dropbox download: {e}")
|
||||
traceback.print_exc(limit=2)
|
||||
raise
|
||||
traceback.print_exc(limit=2)
|
||||
@@ -1,4 +1,5 @@
|
||||
# --- Standard Library Imports ---
|
||||
# --- Standard Library Imports ---
|
||||
import os
|
||||
import time
|
||||
import hashlib
|
||||
@@ -10,28 +11,49 @@ from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||
|
||||
# --- Third-Party Library Imports ---
|
||||
import requests
|
||||
MULTIPART_DOWNLOADER_AVAILABLE = True
|
||||
|
||||
# --- Module Constants ---
|
||||
CHUNK_DOWNLOAD_RETRY_DELAY = 2
|
||||
MAX_CHUNK_DOWNLOAD_RETRIES = 1
|
||||
DOWNLOAD_CHUNK_SIZE_ITER = 1024 * 256 # 256 KB per iteration chunk
|
||||
|
||||
# Flag to indicate if this module and its dependencies are available.
|
||||
# This was missing and caused the ImportError.
|
||||
MULTIPART_DOWNLOADER_AVAILABLE = True
|
||||
|
||||
|
||||
def _download_individual_chunk(
|
||||
chunk_url, temp_file_path, start_byte, end_byte, headers,
|
||||
chunk_url, chunk_temp_file_path, start_byte, end_byte, headers,
|
||||
part_num, total_parts, progress_data, cancellation_event,
|
||||
skip_event, pause_event, global_emit_time_ref, cookies_for_chunk,
|
||||
logger_func, emitter=None, api_original_filename=None
|
||||
):
|
||||
"""
|
||||
Downloads a single segment (chunk) of a larger file. This function is
|
||||
intended to be run in a separate thread by a ThreadPoolExecutor.
|
||||
Downloads a single segment (chunk) of a larger file to its own unique part file.
|
||||
This function is intended to be run in a separate thread by a ThreadPoolExecutor.
|
||||
|
||||
It handles retries, pauses, and cancellations for its specific chunk.
|
||||
It handles retries, pauses, and cancellations for its specific chunk. If a
|
||||
download fails, the partial chunk file is removed, allowing a clean retry later.
|
||||
|
||||
Args:
|
||||
chunk_url (str): The URL to download the file from.
|
||||
chunk_temp_file_path (str): The unique path to save this specific chunk
|
||||
(e.g., 'my_video.mp4.part0').
|
||||
start_byte (int): The starting byte for the Range header.
|
||||
end_byte (int): The ending byte for the Range header.
|
||||
headers (dict): The HTTP headers to use for the request.
|
||||
part_num (int): The index of this chunk (e.g., 0 for the first part).
|
||||
total_parts (int): The total number of chunks for the entire file.
|
||||
progress_data (dict): A thread-safe dictionary for sharing progress.
|
||||
cancellation_event (threading.Event): Event to signal cancellation.
|
||||
skip_event (threading.Event): Event to signal skipping the file.
|
||||
pause_event (threading.Event): Event to signal pausing the download.
|
||||
global_emit_time_ref (list): A mutable list with one element (a timestamp)
|
||||
to rate-limit UI updates.
|
||||
cookies_for_chunk (dict): Cookies to use for the request.
|
||||
logger_func (function): A function to log messages.
|
||||
emitter (queue.Queue or QObject): Emitter for sending progress to the UI.
|
||||
api_original_filename (str): The original filename for UI display.
|
||||
|
||||
Returns:
|
||||
tuple: A tuple containing (bytes_downloaded, success_flag).
|
||||
"""
|
||||
# --- Pre-download checks for control events ---
|
||||
if cancellation_event and cancellation_event.is_set():
|
||||
@@ -49,103 +71,135 @@ def _download_individual_chunk(
|
||||
time.sleep(0.2)
|
||||
logger_func(f" [Chunk {part_num + 1}/{total_parts}] Download resumed.")
|
||||
|
||||
# Prepare headers for the specific byte range of this chunk
|
||||
chunk_headers = headers.copy()
|
||||
if end_byte != -1:
|
||||
chunk_headers['Range'] = f"bytes={start_byte}-{end_byte}"
|
||||
|
||||
bytes_this_chunk = 0
|
||||
last_speed_calc_time = time.time()
|
||||
bytes_at_last_speed_calc = 0
|
||||
# Set this chunk's status to 'active' before starting the download.
|
||||
with progress_data['lock']:
|
||||
progress_data['chunks_status'][part_num]['active'] = True
|
||||
|
||||
# --- Retry Loop ---
|
||||
for attempt in range(MAX_CHUNK_DOWNLOAD_RETRIES + 1):
|
||||
if cancellation_event and cancellation_event.is_set():
|
||||
return bytes_this_chunk, False
|
||||
try:
|
||||
# Prepare headers for the specific byte range of this chunk
|
||||
chunk_headers = headers.copy()
|
||||
if end_byte != -1:
|
||||
chunk_headers['Range'] = f"bytes={start_byte}-{end_byte}"
|
||||
|
||||
try:
|
||||
if attempt > 0:
|
||||
logger_func(f" [Chunk {part_num + 1}/{total_parts}] Retrying (Attempt {attempt + 1}/{MAX_CHUNK_DOWNLOAD_RETRIES + 1})...")
|
||||
time.sleep(CHUNK_DOWNLOAD_RETRY_DELAY * (2 ** (attempt - 1)))
|
||||
last_speed_calc_time = time.time()
|
||||
bytes_at_last_speed_calc = bytes_this_chunk
|
||||
bytes_this_chunk = 0
|
||||
last_speed_calc_time = time.time()
|
||||
bytes_at_last_speed_calc = 0
|
||||
|
||||
logger_func(f" 🚀 [Chunk {part_num + 1}/{total_parts}] Starting download: bytes {start_byte}-{end_byte if end_byte != -1 else 'EOF'}")
|
||||
|
||||
response = requests.get(chunk_url, headers=chunk_headers, timeout=(10, 120), stream=True, cookies=cookies_for_chunk)
|
||||
response.raise_for_status()
|
||||
# --- Retry Loop ---
|
||||
for attempt in range(MAX_CHUNK_DOWNLOAD_RETRIES + 1):
|
||||
if cancellation_event and cancellation_event.is_set():
|
||||
return bytes_this_chunk, False
|
||||
|
||||
# --- Data Writing Loop ---
|
||||
with open(temp_file_path, 'r+b') as f:
|
||||
f.seek(start_byte)
|
||||
for data_segment in response.iter_content(chunk_size=DOWNLOAD_CHUNK_SIZE_ITER):
|
||||
if cancellation_event and cancellation_event.is_set():
|
||||
return bytes_this_chunk, False
|
||||
if pause_event and pause_event.is_set():
|
||||
# Handle pausing during the download stream
|
||||
logger_func(f" [Chunk {part_num + 1}/{total_parts}] Paused...")
|
||||
while pause_event.is_set():
|
||||
if cancellation_event and cancellation_event.is_set(): return bytes_this_chunk, False
|
||||
time.sleep(0.2)
|
||||
logger_func(f" [Chunk {part_num + 1}/{total_parts}] Resumed.")
|
||||
try:
|
||||
if attempt > 0:
|
||||
logger_func(f" [Chunk {part_num + 1}/{total_parts}] Retrying (Attempt {attempt + 1}/{MAX_CHUNK_DOWNLOAD_RETRIES + 1})...")
|
||||
time.sleep(CHUNK_DOWNLOAD_RETRY_DELAY * (2 ** (attempt - 1)))
|
||||
last_speed_calc_time = time.time()
|
||||
bytes_at_last_speed_calc = bytes_this_chunk
|
||||
|
||||
if data_segment:
|
||||
f.write(data_segment)
|
||||
bytes_this_chunk += len(data_segment)
|
||||
|
||||
# Update shared progress data structure
|
||||
with progress_data['lock']:
|
||||
progress_data['total_downloaded_so_far'] += len(data_segment)
|
||||
progress_data['chunks_status'][part_num]['downloaded'] = bytes_this_chunk
|
||||
|
||||
# Calculate and update speed for this chunk
|
||||
current_time = time.time()
|
||||
time_delta = current_time - last_speed_calc_time
|
||||
if time_delta > 0.5:
|
||||
bytes_delta = bytes_this_chunk - bytes_at_last_speed_calc
|
||||
current_speed_bps = (bytes_delta * 8) / time_delta if time_delta > 0 else 0
|
||||
progress_data['chunks_status'][part_num]['speed_bps'] = current_speed_bps
|
||||
last_speed_calc_time = current_time
|
||||
bytes_at_last_speed_calc = bytes_this_chunk
|
||||
|
||||
# Emit progress signal to the UI via the queue
|
||||
if emitter and (current_time - global_emit_time_ref[0] > 0.25):
|
||||
global_emit_time_ref[0] = current_time
|
||||
status_list_copy = [dict(s) for s in progress_data['chunks_status']]
|
||||
if isinstance(emitter, queue.Queue):
|
||||
emitter.put({'type': 'file_progress', 'payload': (api_original_filename, status_list_copy)})
|
||||
elif hasattr(emitter, 'file_progress_signal'):
|
||||
emitter.file_progress_signal.emit(api_original_filename, status_list_copy)
|
||||
|
||||
# If we reach here, the download for this chunk was successful
|
||||
return bytes_this_chunk, True
|
||||
logger_func(f" 🚀 [Chunk {part_num + 1}/{total_parts}] Starting download: bytes {start_byte}-{end_byte if end_byte != -1 else 'EOF'}")
|
||||
|
||||
except (requests.exceptions.ConnectionError, requests.exceptions.Timeout, http.client.IncompleteRead) as e:
|
||||
logger_func(f" ❌ [Chunk {part_num + 1}/{total_parts}] Retryable error: {e}")
|
||||
except requests.exceptions.RequestException as e:
|
||||
logger_func(f" ❌ [Chunk {part_num + 1}/{total_parts}] Non-retryable error: {e}")
|
||||
return bytes_this_chunk, False # Break loop on non-retryable errors
|
||||
except Exception as e:
|
||||
logger_func(f" ❌ [Chunk {part_num + 1}/{total_parts}] Unexpected error: {e}\n{traceback.format_exc(limit=1)}")
|
||||
return bytes_this_chunk, False
|
||||
response = requests.get(chunk_url, headers=chunk_headers, timeout=(10, 120), stream=True, cookies=cookies_for_chunk)
|
||||
response.raise_for_status()
|
||||
|
||||
return bytes_this_chunk, False
|
||||
# --- Data Writing Loop ---
|
||||
# We open the unique chunk file in write-binary ('wb') mode.
|
||||
# No more seeking is required.
|
||||
with open(chunk_temp_file_path, 'wb') as f:
|
||||
for data_segment in response.iter_content(chunk_size=DOWNLOAD_CHUNK_SIZE_ITER):
|
||||
if cancellation_event and cancellation_event.is_set():
|
||||
return bytes_this_chunk, False
|
||||
if pause_event and pause_event.is_set():
|
||||
# Handle pausing during the download stream
|
||||
logger_func(f" [Chunk {part_num + 1}/{total_parts}] Paused...")
|
||||
while pause_event.is_set():
|
||||
if cancellation_event and cancellation_event.is_set(): return bytes_this_chunk, False
|
||||
time.sleep(0.2)
|
||||
logger_func(f" [Chunk {part_num + 1}/{total_parts}] Resumed.")
|
||||
|
||||
if data_segment:
|
||||
f.write(data_segment)
|
||||
bytes_this_chunk += len(data_segment)
|
||||
|
||||
# Update shared progress data structure
|
||||
with progress_data['lock']:
|
||||
progress_data['total_downloaded_so_far'] += len(data_segment)
|
||||
progress_data['chunks_status'][part_num]['downloaded'] = bytes_this_chunk
|
||||
|
||||
# Calculate and update speed for this chunk
|
||||
current_time = time.time()
|
||||
time_delta = current_time - last_speed_calc_time
|
||||
if time_delta > 0.5:
|
||||
bytes_delta = bytes_this_chunk - bytes_at_last_speed_calc
|
||||
current_speed_bps = (bytes_delta * 8) / time_delta if time_delta > 0 else 0
|
||||
progress_data['chunks_status'][part_num]['speed_bps'] = current_speed_bps
|
||||
last_speed_calc_time = current_time
|
||||
bytes_at_last_speed_calc = bytes_this_chunk
|
||||
|
||||
# Emit progress signal to the UI via the queue
|
||||
if emitter and (current_time - global_emit_time_ref[0] > 0.25):
|
||||
global_emit_time_ref[0] = current_time
|
||||
status_list_copy = [dict(s) for s in progress_data['chunks_status']]
|
||||
if isinstance(emitter, queue.Queue):
|
||||
emitter.put({'type': 'file_progress', 'payload': (api_original_filename, status_list_copy)})
|
||||
elif hasattr(emitter, 'file_progress_signal'):
|
||||
emitter.file_progress_signal.emit(api_original_filename, status_list_copy)
|
||||
|
||||
# If we get here, the download for this chunk is successful
|
||||
return bytes_this_chunk, True
|
||||
|
||||
except (requests.exceptions.ConnectionError, requests.exceptions.Timeout, http.client.IncompleteRead) as e:
|
||||
logger_func(f" ❌ [Chunk {part_num + 1}/{total_parts}] Retryable error: {e}")
|
||||
except requests.exceptions.RequestException as e:
|
||||
logger_func(f" ❌ [Chunk {part_num + 1}/{total_parts}] Non-retryable error: {e}")
|
||||
return bytes_this_chunk, False # Break loop on non-retryable errors
|
||||
except Exception as e:
|
||||
logger_func(f" ❌ [Chunk {part_num + 1}/{total_parts}] Unexpected error: {e}\n{traceback.format_exc(limit=1)}")
|
||||
return bytes_this_chunk, False
|
||||
|
||||
# If the retry loop finishes without a successful download
|
||||
return bytes_this_chunk, False
|
||||
finally:
|
||||
# This block runs whether the download succeeded or failed
|
||||
with progress_data['lock']:
|
||||
progress_data['chunks_status'][part_num]['active'] = False
|
||||
progress_data['chunks_status'][part_num]['speed_bps'] = 0.0
|
||||
|
||||
|
||||
def download_file_in_parts(file_url, save_path, total_size, num_parts, headers, api_original_filename,
|
||||
emitter_for_multipart, cookies_for_chunk_session,
|
||||
cancellation_event, skip_event, logger_func, pause_event):
|
||||
logger_func(f"⬇️ Initializing Multi-part Download ({num_parts} parts) for: '{api_original_filename}' (Size: {total_size / (1024*1024):.2f} MB)")
|
||||
temp_file_path = save_path + ".part"
|
||||
"""
|
||||
Manages a resilient, multipart file download by saving each chunk to a separate file.
|
||||
|
||||
try:
|
||||
with open(temp_file_path, 'wb') as f_temp:
|
||||
if total_size > 0:
|
||||
f_temp.truncate(total_size)
|
||||
except IOError as e:
|
||||
logger_func(f" ❌ Error creating/truncating temp file '{temp_file_path}': {e}")
|
||||
return False, 0, None, None
|
||||
This function orchestrates the download process by:
|
||||
1. Checking for already completed chunk files to resume a previous download.
|
||||
2. Submitting only the missing chunks to a thread pool for parallel download.
|
||||
3. Assembling the final file from the individual chunks upon successful completion.
|
||||
4. Cleaning up temporary chunk files after assembly.
|
||||
5. Leaving completed chunks on disk if the download fails, allowing for a future resume.
|
||||
|
||||
Args:
|
||||
file_url (str): The URL of the file to download.
|
||||
save_path (str): The final desired path for the downloaded file (e.g., 'my_video.mp4').
|
||||
total_size (int): The total size of the file in bytes.
|
||||
num_parts (int): The number of parts to split the download into.
|
||||
headers (dict): HTTP headers for the download requests.
|
||||
api_original_filename (str): The original filename for UI progress display.
|
||||
emitter_for_multipart (queue.Queue or QObject): Emitter for UI signals.
|
||||
cookies_for_chunk_session (dict): Cookies for the download requests.
|
||||
cancellation_event (threading.Event): Event to signal cancellation.
|
||||
skip_event (threading.Event): Event to signal skipping the file.
|
||||
logger_func (function): A function for logging messages.
|
||||
pause_event (threading.Event): Event to signal pausing the download.
|
||||
|
||||
Returns:
|
||||
tuple: A tuple containing (success_flag, total_bytes_downloaded, md5_hash, file_handle).
|
||||
The file_handle will be for the final assembled file if successful, otherwise None.
|
||||
"""
|
||||
logger_func(f"⬇️ Initializing Resumable Multi-part Download ({num_parts} parts) for: '{api_original_filename}' (Size: {total_size / (1024*1024):.2f} MB)")
|
||||
|
||||
# Calculate the byte range for each chunk
|
||||
chunk_size_calc = total_size // num_parts
|
||||
chunks_ranges = []
|
||||
for i in range(num_parts):
|
||||
@@ -153,76 +207,119 @@ def download_file_in_parts(file_url, save_path, total_size, num_parts, headers,
|
||||
end = start + chunk_size_calc - 1 if i < num_parts - 1 else total_size - 1
|
||||
if start <= end:
|
||||
chunks_ranges.append((start, end))
|
||||
elif total_size == 0 and i == 0:
|
||||
elif total_size == 0 and i == 0: # Handle zero-byte files
|
||||
chunks_ranges.append((0, -1))
|
||||
|
||||
# Calculate the expected size of each chunk
|
||||
chunk_actual_sizes = []
|
||||
for start, end in chunks_ranges:
|
||||
if end == -1 and start == 0:
|
||||
chunk_actual_sizes.append(0)
|
||||
else:
|
||||
chunk_actual_sizes.append(end - start + 1)
|
||||
chunk_actual_sizes.append(end - start + 1 if end != -1 else 0)
|
||||
|
||||
if not chunks_ranges and total_size > 0:
|
||||
logger_func(f" ⚠️ No valid chunk ranges for multipart download of '{api_original_filename}'. Aborting multipart.")
|
||||
if os.path.exists(temp_file_path): os.remove(temp_file_path)
|
||||
logger_func(f" ⚠️ No valid chunk ranges for multipart download of '{api_original_filename}'. Aborting.")
|
||||
return False, 0, None, None
|
||||
|
||||
# --- Resumption Logic: Check for existing complete chunks ---
|
||||
chunks_to_download = []
|
||||
total_bytes_resumed = 0
|
||||
for i, (start, end) in enumerate(chunks_ranges):
|
||||
chunk_part_path = f"{save_path}.part{i}"
|
||||
expected_chunk_size = chunk_actual_sizes[i]
|
||||
|
||||
if os.path.exists(chunk_part_path) and os.path.getsize(chunk_part_path) == expected_chunk_size:
|
||||
logger_func(f" [Chunk {i + 1}/{num_parts}] Resuming with existing complete chunk file.")
|
||||
total_bytes_resumed += expected_chunk_size
|
||||
else:
|
||||
chunks_to_download.append({'index': i, 'start': start, 'end': end})
|
||||
|
||||
# Setup the shared progress data structure
|
||||
progress_data = {
|
||||
'total_file_size': total_size,
|
||||
'total_downloaded_so_far': 0,
|
||||
'chunks_status': [
|
||||
{'id': i, 'downloaded': 0, 'total': chunk_actual_sizes[i] if i < len(chunk_actual_sizes) else 0, 'active': False, 'speed_bps': 0.0}
|
||||
for i in range(num_parts)
|
||||
],
|
||||
'total_downloaded_so_far': total_bytes_resumed,
|
||||
'chunks_status': [],
|
||||
'lock': threading.Lock(),
|
||||
'last_global_emit_time': [time.time()]
|
||||
}
|
||||
for i in range(num_parts):
|
||||
is_resumed = not any(c['index'] == i for c in chunks_to_download)
|
||||
progress_data['chunks_status'].append({
|
||||
'id': i,
|
||||
'downloaded': chunk_actual_sizes[i] if is_resumed else 0,
|
||||
'total': chunk_actual_sizes[i],
|
||||
'active': False,
|
||||
'speed_bps': 0.0
|
||||
})
|
||||
|
||||
# --- Download Phase ---
|
||||
chunk_futures = []
|
||||
all_chunks_successful = True
|
||||
total_bytes_from_chunks = 0
|
||||
total_bytes_from_threads = 0
|
||||
|
||||
with ThreadPoolExecutor(max_workers=num_parts, thread_name_prefix=f"MPChunk_{api_original_filename[:10]}_") as chunk_pool:
|
||||
for i, (start, end) in enumerate(chunks_ranges):
|
||||
if cancellation_event and cancellation_event.is_set(): all_chunks_successful = False; break
|
||||
chunk_futures.append(chunk_pool.submit(
|
||||
_download_individual_chunk, chunk_url=file_url, temp_file_path=temp_file_path,
|
||||
for chunk_info in chunks_to_download:
|
||||
if cancellation_event and cancellation_event.is_set():
|
||||
all_chunks_successful = False
|
||||
break
|
||||
|
||||
i, start, end = chunk_info['index'], chunk_info['start'], chunk_info['end']
|
||||
chunk_part_path = f"{save_path}.part{i}"
|
||||
|
||||
future = chunk_pool.submit(
|
||||
_download_individual_chunk,
|
||||
chunk_url=file_url,
|
||||
chunk_temp_file_path=chunk_part_path,
|
||||
start_byte=start, end_byte=end, headers=headers, part_num=i, total_parts=num_parts,
|
||||
progress_data=progress_data, cancellation_event=cancellation_event, skip_event=skip_event, global_emit_time_ref=progress_data['last_global_emit_time'],
|
||||
pause_event=pause_event, cookies_for_chunk=cookies_for_chunk_session, logger_func=logger_func, emitter=emitter_for_multipart,
|
||||
progress_data=progress_data, cancellation_event=cancellation_event,
|
||||
skip_event=skip_event, global_emit_time_ref=progress_data['last_global_emit_time'],
|
||||
pause_event=pause_event, cookies_for_chunk=cookies_for_chunk_session,
|
||||
logger_func=logger_func, emitter=emitter_for_multipart,
|
||||
api_original_filename=api_original_filename
|
||||
))
|
||||
)
|
||||
chunk_futures.append(future)
|
||||
|
||||
for future in as_completed(chunk_futures):
|
||||
if cancellation_event and cancellation_event.is_set(): all_chunks_successful = False; break
|
||||
bytes_downloaded_this_chunk, success_this_chunk = future.result()
|
||||
total_bytes_from_chunks += bytes_downloaded_this_chunk
|
||||
if not success_this_chunk:
|
||||
if cancellation_event and cancellation_event.is_set():
|
||||
all_chunks_successful = False
|
||||
bytes_downloaded, success = future.result()
|
||||
total_bytes_from_threads += bytes_downloaded
|
||||
if not success:
|
||||
all_chunks_successful = False
|
||||
|
||||
total_bytes_final = total_bytes_resumed + total_bytes_from_threads
|
||||
|
||||
if cancellation_event and cancellation_event.is_set():
|
||||
logger_func(f" Multi-part download for '{api_original_filename}' cancelled by main event.")
|
||||
all_chunks_successful = False
|
||||
if emitter_for_multipart:
|
||||
with progress_data['lock']:
|
||||
status_list_copy = [dict(s) for s in progress_data['chunks_status']]
|
||||
if isinstance(emitter_for_multipart, queue.Queue):
|
||||
emitter_for_multipart.put({'type': 'file_progress', 'payload': (api_original_filename, status_list_copy)})
|
||||
elif hasattr(emitter_for_multipart, 'file_progress_signal'):
|
||||
emitter_for_multipart.file_progress_signal.emit(api_original_filename, status_list_copy)
|
||||
|
||||
if all_chunks_successful and (total_bytes_from_chunks == total_size or total_size == 0):
|
||||
logger_func(f" ✅ Multi-part download successful for '{api_original_filename}'. Total bytes: {total_bytes_from_chunks}")
|
||||
# --- Assembly and Cleanup Phase ---
|
||||
if all_chunks_successful and (total_bytes_final == total_size or total_size == 0):
|
||||
logger_func(f" ✅ All {num_parts} chunks complete. Assembling final file...")
|
||||
md5_hasher = hashlib.md5()
|
||||
with open(temp_file_path, 'rb') as f_hash:
|
||||
for buf in iter(lambda: f_hash.read(4096*10), b''):
|
||||
md5_hasher.update(buf)
|
||||
calculated_hash = md5_hasher.hexdigest()
|
||||
return True, total_bytes_from_chunks, calculated_hash, open(temp_file_path, 'rb')
|
||||
try:
|
||||
with open(save_path, 'wb') as final_file:
|
||||
for i in range(num_parts):
|
||||
chunk_part_path = f"{save_path}.part{i}"
|
||||
with open(chunk_part_path, 'rb') as chunk_file:
|
||||
content = chunk_file.read()
|
||||
final_file.write(content)
|
||||
md5_hasher.update(content)
|
||||
|
||||
calculated_hash = md5_hasher.hexdigest()
|
||||
logger_func(f" ✅ Assembly successful for '{api_original_filename}'. Total bytes: {total_bytes_final}")
|
||||
return True, total_bytes_final, calculated_hash, open(save_path, 'rb')
|
||||
except Exception as e:
|
||||
logger_func(f" ❌ Critical error during file assembly: {e}. Cleaning up.")
|
||||
return False, total_bytes_final, None, None
|
||||
finally:
|
||||
# Cleanup all individual chunk files after successful assembly
|
||||
for i in range(num_parts):
|
||||
chunk_part_path = f"{save_path}.part{i}"
|
||||
if os.path.exists(chunk_part_path):
|
||||
try:
|
||||
os.remove(chunk_part_path)
|
||||
except OSError as e:
|
||||
logger_func(f" ⚠️ Failed to remove temp part file '{chunk_part_path}': {e}")
|
||||
else:
|
||||
logger_func(f" ❌ Multi-part download failed for '{api_original_filename}'. Success: {all_chunks_successful}, Bytes: {total_bytes_from_chunks}/{total_size}. Cleaning up.")
|
||||
if os.path.exists(temp_file_path):
|
||||
try: os.remove(temp_file_path)
|
||||
except OSError as e: logger_func(f" Failed to remove temp part file '{temp_file_path}': {e}")
|
||||
return False, total_bytes_from_chunks, None, None
|
||||
# If download failed, we do NOT clean up, allowing for resumption later
|
||||
logger_func(f" ❌ Multi-part download failed for '{api_original_filename}'. Success: {all_chunks_successful}, Bytes: {total_bytes_final}/{total_size}. Partial chunks saved for future resumption.")
|
||||
return False, total_bytes_final, None, None
|
||||
|
||||
125
src/services/updater.py
Normal file
125
src/services/updater.py
Normal file
@@ -0,0 +1,125 @@
|
||||
import sys
|
||||
import os
|
||||
import requests
|
||||
import subprocess # Keep this for now, though it's not used in the final command
|
||||
from packaging.version import parse as parse_version
|
||||
from PyQt5.QtCore import QThread, pyqtSignal
|
||||
|
||||
# Constants for the updater
|
||||
GITHUB_REPO_URL = "https://api.github.com/repos/Yuvi9587/Kemono-Downloader/releases/latest"
|
||||
EXE_NAME = "Kemono.Downloader.exe"
|
||||
|
||||
class UpdateChecker(QThread):
|
||||
"""Checks for a new version on GitHub in a background thread."""
|
||||
update_available = pyqtSignal(str, str) # new_version, download_url
|
||||
up_to_date = pyqtSignal(str)
|
||||
update_error = pyqtSignal(str)
|
||||
|
||||
def __init__(self, current_version):
|
||||
super().__init__()
|
||||
self.current_version_str = current_version.lstrip('v')
|
||||
|
||||
def run(self):
|
||||
try:
|
||||
response = requests.get(GITHUB_REPO_URL, timeout=15)
|
||||
response.raise_for_status()
|
||||
data = response.json()
|
||||
|
||||
latest_version_str = data['tag_name'].lstrip('v')
|
||||
current_version = parse_version(self.current_version_str)
|
||||
latest_version = parse_version(latest_version_str)
|
||||
|
||||
if latest_version > current_version:
|
||||
for asset in data.get('assets', []):
|
||||
if asset['name'] == EXE_NAME:
|
||||
self.update_available.emit(latest_version_str, asset['browser_download_url'])
|
||||
return
|
||||
self.update_error.emit(f"Update found, but '{EXE_NAME}' is missing from the release assets.")
|
||||
else:
|
||||
self.up_to_date.emit("You are on the latest version.")
|
||||
|
||||
except requests.exceptions.RequestException as e:
|
||||
self.update_error.emit(f"Network error: {e}")
|
||||
except Exception as e:
|
||||
self.update_error.emit(f"An error occurred: {e}")
|
||||
|
||||
|
||||
class UpdateDownloader(QThread):
|
||||
"""
|
||||
Downloads the new executable and runs an updater script that kills the old process,
|
||||
replaces the file, and displays a message in the terminal.
|
||||
"""
|
||||
download_finished = pyqtSignal()
|
||||
download_error = pyqtSignal(str)
|
||||
|
||||
def __init__(self, download_url, parent_app):
|
||||
super().__init__()
|
||||
self.download_url = download_url
|
||||
self.parent_app = parent_app
|
||||
|
||||
def run(self):
|
||||
try:
|
||||
app_path = sys.executable
|
||||
app_dir = os.path.dirname(app_path)
|
||||
temp_path = os.path.join(app_dir, f"{EXE_NAME}.tmp")
|
||||
old_path = os.path.join(app_dir, f"{EXE_NAME}.old")
|
||||
updater_script_path = os.path.join(app_dir, "updater.bat")
|
||||
|
||||
# --- NEW: Path for the PID file ---
|
||||
pid_file_path = os.path.join(app_dir, "updater.pid")
|
||||
|
||||
# Download the new executable
|
||||
with requests.get(self.download_url, stream=True, timeout=300) as r:
|
||||
r.raise_for_status()
|
||||
with open(temp_path, 'wb') as f:
|
||||
for chunk in r.iter_content(chunk_size=8192):
|
||||
f.write(chunk)
|
||||
|
||||
# --- NEW: Write the current Process ID to the pid file ---
|
||||
with open(pid_file_path, "w") as f:
|
||||
f.write(str(os.getpid()))
|
||||
|
||||
# --- NEW BATCH SCRIPT ---
|
||||
# This script now reads the PID from the "updater.pid" file.
|
||||
script_content = f"""
|
||||
@echo off
|
||||
SETLOCAL
|
||||
|
||||
echo.
|
||||
echo Reading process information...
|
||||
set /p PID=<{pid_file_path}
|
||||
|
||||
echo Closing the old application (PID: %PID%)...
|
||||
taskkill /F /PID %PID%
|
||||
|
||||
echo Waiting for files to unlock...
|
||||
timeout /t 2 /nobreak > nul
|
||||
|
||||
echo Replacing application files...
|
||||
if exist "{old_path}" del /F /Q "{old_path}"
|
||||
rename "{app_path}" "{os.path.basename(old_path)}"
|
||||
rename "{temp_path}" "{EXE_NAME}"
|
||||
|
||||
echo.
|
||||
echo ============================================================
|
||||
echo Update Complete!
|
||||
echo You can now close this window and run {EXE_NAME}.
|
||||
echo ============================================================
|
||||
echo.
|
||||
pause
|
||||
|
||||
echo Cleaning up helper files...
|
||||
del "{pid_file_path}"
|
||||
del "%~f0"
|
||||
ENDLOCAL
|
||||
"""
|
||||
with open(updater_script_path, "w") as f:
|
||||
f.write(script_content)
|
||||
|
||||
# --- Go back to the os.startfile command that we know works ---
|
||||
os.startfile(updater_script_path)
|
||||
|
||||
self.download_finished.emit()
|
||||
|
||||
except Exception as e:
|
||||
self.download_error.emit(f"Failed to download or run updater: {e}")
|
||||
@@ -960,15 +960,16 @@ class EmptyPopupDialog (QDialog ):
|
||||
|
||||
self .parent_app .log_signal .emit (f"ℹ️ Added {num_just_added_posts } selected posts to the download queue. Total in queue: {total_in_queue }.")
|
||||
|
||||
# --- START: MODIFIED LOGIC ---
|
||||
# Removed the blockSignals(True/False) calls to allow the main window's UI to update correctly.
|
||||
if self .parent_app .link_input :
|
||||
self .parent_app .link_input .blockSignals (True )
|
||||
self .parent_app .link_input .setText (
|
||||
self .parent_app ._tr ("popup_posts_selected_text","Posts - {count} selected").format (count =num_just_added_posts )
|
||||
)
|
||||
self .parent_app .link_input .blockSignals (False )
|
||||
self .parent_app .link_input .setPlaceholderText (
|
||||
self .parent_app ._tr ("items_in_queue_placeholder","{count} items in queue from popup.").format (count =total_in_queue )
|
||||
)
|
||||
# --- END: MODIFIED LOGIC ---
|
||||
|
||||
self.selected_creators_for_queue.clear()
|
||||
|
||||
@@ -989,9 +990,6 @@ class EmptyPopupDialog (QDialog ):
|
||||
self .add_selected_button .setEnabled (True )
|
||||
self .setWindowTitle (self ._tr ("creator_popup_title","Creator Selection"))
|
||||
|
||||
|
||||
|
||||
|
||||
def _get_domain_for_service (self ,service_name ):
|
||||
"""Determines the base domain for a given service."""
|
||||
service_lower =service_name .lower ()
|
||||
|
||||
@@ -42,17 +42,12 @@ class ErrorFilesDialog(QDialog):
|
||||
if app_icon and not app_icon.isNull():
|
||||
self.setWindowIcon(app_icon)
|
||||
|
||||
# --- START OF FIX ---
|
||||
# Get the user-defined scale factor from the parent application.
|
||||
scale_factor = getattr(self.parent_app, 'scale_factor', 1.0)
|
||||
|
||||
# Define base dimensions and apply the correct scale factor.
|
||||
base_width, base_height = 550, 400
|
||||
self.setMinimumSize(int(base_width * scale_factor), int(base_height * scale_factor))
|
||||
self.resize(int(base_width * scale_factor * 1.1), int(base_height * scale_factor * 1.1))
|
||||
# --- END OF FIX ---
|
||||
|
||||
# --- Initialize UI and Apply Theming ---
|
||||
self._init_ui()
|
||||
self._retranslate_ui()
|
||||
self._apply_theme()
|
||||
@@ -106,7 +101,17 @@ class ErrorFilesDialog(QDialog):
|
||||
post_title = error_info.get('post_title', 'Unknown Post')
|
||||
post_id = error_info.get('original_post_id_for_log', 'N/A')
|
||||
|
||||
item_text = f"File: {filename}\nFrom Post: '{post_title}' (ID: {post_id})"
|
||||
creator_name = "Unknown Creator"
|
||||
service = error_info.get('service')
|
||||
user_id = error_info.get('user_id')
|
||||
|
||||
# Check if we have the necessary info and access to the cache
|
||||
if service and user_id and hasattr(self.parent_app, 'creator_name_cache'):
|
||||
creator_key = (service.lower(), str(user_id))
|
||||
# Look up the name, fall back to the user_id if not found
|
||||
creator_name = self.parent_app.creator_name_cache.get(creator_key, user_id)
|
||||
|
||||
item_text = f"File: {filename}\nCreator: {creator_name} - Post: '{post_title}' (ID: {post_id})"
|
||||
list_item = QListWidgetItem(item_text)
|
||||
list_item.setData(Qt.UserRole, error_info)
|
||||
list_item.setFlags(list_item.flags() | Qt.ItemIsUserCheckable)
|
||||
|
||||
@@ -3,7 +3,7 @@ import html
|
||||
import re
|
||||
|
||||
# --- Third-Party Library Imports ---
|
||||
import requests
|
||||
import cloudscraper # MODIFIED: Import cloudscraper
|
||||
from PyQt5.QtCore import QCoreApplication, Qt
|
||||
from PyQt5.QtWidgets import (
|
||||
QApplication, QDialog, QHBoxLayout, QLabel, QLineEdit, QListWidget,
|
||||
@@ -12,7 +12,6 @@ from PyQt5.QtWidgets import (
|
||||
|
||||
# --- Local Application Imports ---
|
||||
from ...i18n.translator import get_translation
|
||||
# Corrected Import: Get the icon from the new assets utility module
|
||||
from ..assets import get_app_icon_object
|
||||
from ...utils.network_utils import prepare_cookies_for_request
|
||||
from .CookieHelpDialog import CookieHelpDialog
|
||||
@@ -37,13 +36,13 @@ class FavoriteArtistsDialog (QDialog ):
|
||||
self ._init_ui ()
|
||||
self ._fetch_favorite_artists ()
|
||||
|
||||
def _get_domain_for_service (self ,service_name ):
|
||||
service_lower =service_name .lower ()
|
||||
coomer_primary_services ={'onlyfans','fansly','manyvids','candfans'}
|
||||
if service_lower in coomer_primary_services :
|
||||
return "coomer.su"
|
||||
else :
|
||||
return "kemono.su"
|
||||
def _get_domain_for_service(self, service_name):
|
||||
service_lower = service_name.lower()
|
||||
coomer_primary_services = {'onlyfans', 'fansly', 'manyvids', 'candfans'}
|
||||
if service_lower in coomer_primary_services:
|
||||
return "coomer.st"
|
||||
else:
|
||||
return "kemono.cr"
|
||||
|
||||
def _tr (self ,key ,default_text =""):
|
||||
"""Helper to get translation based on current app language."""
|
||||
@@ -126,32 +125,49 @@ class FavoriteArtistsDialog (QDialog ):
|
||||
self .artist_list_widget .setVisible (show )
|
||||
|
||||
def _fetch_favorite_artists (self ):
|
||||
# --- FIX: Use cloudscraper and add proper headers ---
|
||||
scraper = cloudscraper.create_scraper()
|
||||
# --- END FIX ---
|
||||
|
||||
if self.cookies_config['use_cookie']:
|
||||
# Check if we can load cookies for at least one of the services.
|
||||
kemono_cookies = prepare_cookies_for_request(True, self.cookies_config['cookie_text'], self.cookies_config['selected_cookie_file'], self.cookies_config['app_base_dir'], self._logger, target_domain="kemono.su")
|
||||
coomer_cookies = prepare_cookies_for_request(True, self.cookies_config['cookie_text'], self.cookies_config['selected_cookie_file'], self.cookies_config['app_base_dir'], self._logger, target_domain="coomer.su")
|
||||
kemono_cookies = prepare_cookies_for_request(
|
||||
True, self.cookies_config['cookie_text'], self.cookies_config['selected_cookie_file'],
|
||||
self.cookies_config['app_base_dir'], self._logger, target_domain="kemono.cr"
|
||||
)
|
||||
if not kemono_cookies:
|
||||
self._logger("No cookies for kemono.cr, trying fallback kemono.su...")
|
||||
kemono_cookies = prepare_cookies_for_request(
|
||||
True, self.cookies_config['cookie_text'], self.cookies_config['selected_cookie_file'],
|
||||
self.cookies_config['app_base_dir'], self._logger, target_domain="kemono.su"
|
||||
)
|
||||
|
||||
coomer_cookies = prepare_cookies_for_request(
|
||||
True, self.cookies_config['cookie_text'], self.cookies_config['selected_cookie_file'],
|
||||
self.cookies_config['app_base_dir'], self._logger, target_domain="coomer.st"
|
||||
)
|
||||
if not coomer_cookies:
|
||||
self._logger("No cookies for coomer.st, trying fallback coomer.su...")
|
||||
coomer_cookies = prepare_cookies_for_request(
|
||||
True, self.cookies_config['cookie_text'], self.cookies_config['selected_cookie_file'],
|
||||
self.cookies_config['app_base_dir'], self._logger, target_domain="coomer.su"
|
||||
)
|
||||
|
||||
if not kemono_cookies and not coomer_cookies:
|
||||
# If cookies are enabled but none could be loaded, show help and stop.
|
||||
self.status_label.setText(self._tr("fav_artists_cookies_required_status", "Error: Cookies enabled but could not be loaded for any source."))
|
||||
self._logger("Error: Cookies enabled but no valid cookies were loaded. Showing help dialog.")
|
||||
cookie_help_dialog = CookieHelpDialog(self.parent_app, self)
|
||||
cookie_help_dialog.exec_()
|
||||
self.download_button.setEnabled(False)
|
||||
return # Stop further execution
|
||||
|
||||
kemono_fav_url ="https://kemono.su/api/v1/account/favorites?type=artist"
|
||||
coomer_fav_url ="https://coomer.su/api/v1/account/favorites?type=artist"
|
||||
return
|
||||
|
||||
self .all_fetched_artists =[]
|
||||
fetched_any_successfully =False
|
||||
errors_occurred =[]
|
||||
any_cookies_loaded_successfully_for_any_source =False
|
||||
|
||||
api_sources =[
|
||||
{"name":"Kemono.su","url":kemono_fav_url ,"domain":"kemono.su"},
|
||||
{"name":"Coomer.su","url":coomer_fav_url ,"domain":"coomer.su"}
|
||||
api_sources = [
|
||||
{"name": "Kemono.cr", "url": "https://kemono.cr/api/v1/account/favorites?type=artist", "domain": "kemono.cr"},
|
||||
{"name": "Coomer.st", "url": "https://coomer.st/api/v1/account/favorites?type=artist", "domain": "coomer.st"}
|
||||
]
|
||||
|
||||
for source in api_sources :
|
||||
@@ -159,23 +175,39 @@ class FavoriteArtistsDialog (QDialog ):
|
||||
self .status_label .setText (self ._tr ("fav_artists_loading_from_source_status","⏳ Loading favorites from {source_name}...").format (source_name =source ['name']))
|
||||
QCoreApplication .processEvents ()
|
||||
|
||||
cookies_dict_for_source =None
|
||||
if self .cookies_config ['use_cookie']:
|
||||
cookies_dict_for_source =prepare_cookies_for_request (
|
||||
True ,
|
||||
self .cookies_config ['cookie_text'],
|
||||
self .cookies_config ['selected_cookie_file'],
|
||||
self .cookies_config ['app_base_dir'],
|
||||
self ._logger ,
|
||||
target_domain =source ['domain']
|
||||
cookies_dict_for_source = None
|
||||
if self.cookies_config['use_cookie']:
|
||||
primary_domain = source['domain']
|
||||
fallback_domain = "kemono.su" if "kemono" in primary_domain else "coomer.su"
|
||||
|
||||
cookies_dict_for_source = prepare_cookies_for_request(
|
||||
True, self.cookies_config['cookie_text'], self.cookies_config['selected_cookie_file'],
|
||||
self.cookies_config['app_base_dir'], self._logger, target_domain=primary_domain
|
||||
)
|
||||
if cookies_dict_for_source :
|
||||
any_cookies_loaded_successfully_for_any_source =True
|
||||
else :
|
||||
self ._logger (f"Warning ({source ['name']}): Cookies enabled but could not be loaded for this domain. Fetch might fail if cookies are required.")
|
||||
if not cookies_dict_for_source:
|
||||
self._logger(f"Warning ({source['name']}): No cookies for '{primary_domain}'. Trying fallback '{fallback_domain}'...")
|
||||
cookies_dict_for_source = prepare_cookies_for_request(
|
||||
True, self.cookies_config['cookie_text'], self.cookies_config['selected_cookie_file'],
|
||||
self.cookies_config['app_base_dir'], self._logger, target_domain=fallback_domain
|
||||
)
|
||||
|
||||
if cookies_dict_for_source:
|
||||
any_cookies_loaded_successfully_for_any_source = True
|
||||
else:
|
||||
self._logger(f"Warning ({source['name']}): Cookies enabled but not loaded for this source. Fetch may fail.")
|
||||
try :
|
||||
headers ={'User-Agent':'Mozilla/5.0'}
|
||||
response =requests .get (source ['url'],headers =headers ,cookies =cookies_dict_for_source ,timeout =20 )
|
||||
# --- FIX: Add Referer and Accept headers ---
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
|
||||
'Referer': f"https://{source['domain']}/favorites",
|
||||
'Accept': 'text/css'
|
||||
}
|
||||
# --- END FIX ---
|
||||
|
||||
# --- FIX: Use scraper instead of requests ---
|
||||
response = scraper.get(source['url'], headers=headers, cookies=cookies_dict_for_source, timeout=20)
|
||||
# --- END FIX ---
|
||||
|
||||
response .raise_for_status ()
|
||||
artists_data_from_api =response .json ()
|
||||
|
||||
@@ -210,20 +242,15 @@ class FavoriteArtistsDialog (QDialog ):
|
||||
fetched_any_successfully =True
|
||||
self ._logger (f"Fetched {processed_artists_from_source } artists from {source ['name']}.")
|
||||
|
||||
except requests .exceptions .RequestException as e :
|
||||
except Exception as e :
|
||||
error_msg =f"Error fetching favorites from {source ['name']}: {e }"
|
||||
self ._logger (error_msg )
|
||||
errors_occurred .append (error_msg )
|
||||
except Exception as e :
|
||||
error_msg =f"An unexpected error occurred with {source ['name']}: {e }"
|
||||
self ._logger (error_msg )
|
||||
errors_occurred .append (error_msg )
|
||||
|
||||
|
||||
if self .cookies_config ['use_cookie']and not any_cookies_loaded_successfully_for_any_source :
|
||||
self .status_label .setText (self ._tr ("fav_artists_cookies_required_status","Error: Cookies enabled but could not be loaded for any source."))
|
||||
self ._logger ("Error: Cookies enabled but no cookies loaded for any source. Showing help dialog.")
|
||||
cookie_help_dialog =CookieHelpDialog (self )
|
||||
cookie_help_dialog = CookieHelpDialog(self.parent_app, self)
|
||||
cookie_help_dialog .exec_ ()
|
||||
self .download_button .setEnabled (False )
|
||||
if not fetched_any_successfully :
|
||||
@@ -244,7 +271,7 @@ class FavoriteArtistsDialog (QDialog ):
|
||||
self ._show_content_elements (True )
|
||||
self .download_button .setEnabled (True )
|
||||
elif not fetched_any_successfully and not errors_occurred :
|
||||
self .status_label .setText (self ._tr ("fav_artists_none_found_status","No favorite artists found on Kemono.su or Coomer.su."))
|
||||
self .status_label .setText (self ._tr ("fav_artists_none_found_status","No favorite artists found on Kemono or Coomer."))
|
||||
self ._show_content_elements (False )
|
||||
self .download_button .setEnabled (False )
|
||||
else :
|
||||
@@ -300,4 +327,4 @@ class FavoriteArtistsDialog (QDialog ):
|
||||
self .accept ()
|
||||
|
||||
def get_selected_artists (self ):
|
||||
return self .selected_artists_data
|
||||
return self .selected_artists_data
|
||||
|
||||
@@ -7,7 +7,7 @@ import traceback
|
||||
import json
|
||||
import re
|
||||
from collections import defaultdict
|
||||
import requests
|
||||
import cloudscraper # MODIFIED: Import cloudscraper
|
||||
from PyQt5.QtCore import QCoreApplication, Qt, pyqtSignal, QThread
|
||||
from PyQt5.QtWidgets import (
|
||||
QApplication, QDialog, QHBoxLayout, QLabel, QLineEdit, QListWidget,
|
||||
@@ -34,28 +34,29 @@ class FavoritePostsFetcherThread (QThread ):
|
||||
self .target_domain_preference =target_domain_preference
|
||||
self .cancellation_event =threading .Event ()
|
||||
self .error_key_map ={
|
||||
"Kemono.su":"kemono_su",
|
||||
"Coomer.su":"coomer_su"
|
||||
"kemono.cr":"kemono_su",
|
||||
"coomer.st":"coomer_su"
|
||||
}
|
||||
|
||||
def _logger (self ,message ):
|
||||
self .parent_logger_func (f"[FavPostsFetcherThread] {message }")
|
||||
|
||||
def run (self ):
|
||||
kemono_fav_posts_url ="https://kemono.su/api/v1/account/favorites?type=post"
|
||||
coomer_fav_posts_url ="https://coomer.su/api/v1/account/favorites?type=post"
|
||||
def run(self):
|
||||
# --- FIX: Use cloudscraper and add proper headers ---
|
||||
scraper = cloudscraper.create_scraper()
|
||||
# --- END FIX ---
|
||||
|
||||
all_fetched_posts_temp =[]
|
||||
error_messages_for_summary =[]
|
||||
fetched_any_successfully =False
|
||||
any_cookies_loaded_successfully_for_any_source =False
|
||||
all_fetched_posts_temp = []
|
||||
error_messages_for_summary = []
|
||||
fetched_any_successfully = False
|
||||
any_cookies_loaded_successfully_for_any_source = False
|
||||
|
||||
self .status_update .emit ("key_fetching_fav_post_list_init")
|
||||
self .progress_bar_update .emit (0 ,0 )
|
||||
self.status_update.emit("key_fetching_fav_post_list_init")
|
||||
self.progress_bar_update.emit(0, 0)
|
||||
|
||||
api_sources =[
|
||||
{"name":"Kemono.su","url":kemono_fav_posts_url ,"domain":"kemono.su"},
|
||||
{"name":"Coomer.su","url":coomer_fav_posts_url ,"domain":"coomer.su"}
|
||||
api_sources = [
|
||||
{"name": "Kemono.cr", "url": "https://kemono.cr/api/v1/account/favorites?type=post", "domain": "kemono.cr"},
|
||||
{"name": "Coomer.st", "url": "https://coomer.st/api/v1/account/favorites?type=post", "domain": "coomer.st"}
|
||||
]
|
||||
|
||||
api_sources_to_try =[]
|
||||
@@ -76,20 +77,27 @@ class FavoritePostsFetcherThread (QThread ):
|
||||
if self .cancellation_event .is_set ():
|
||||
self .finished .emit ([],"KEY_FETCH_CANCELLED_DURING")
|
||||
return
|
||||
cookies_dict_for_source =None
|
||||
if self .cookies_config ['use_cookie']:
|
||||
cookies_dict_for_source =prepare_cookies_for_request (
|
||||
True ,
|
||||
self .cookies_config ['cookie_text'],
|
||||
self .cookies_config ['selected_cookie_file'],
|
||||
self .cookies_config ['app_base_dir'],
|
||||
self ._logger ,
|
||||
target_domain =source ['domain']
|
||||
cookies_dict_for_source = None
|
||||
if self.cookies_config['use_cookie']:
|
||||
primary_domain = source['domain']
|
||||
fallback_domain = "kemono.su" if "kemono" in primary_domain else "coomer.su"
|
||||
|
||||
cookies_dict_for_source = prepare_cookies_for_request(
|
||||
True, self.cookies_config['cookie_text'], self.cookies_config['selected_cookie_file'],
|
||||
self.cookies_config['app_base_dir'], self._logger, target_domain=primary_domain
|
||||
)
|
||||
if cookies_dict_for_source :
|
||||
any_cookies_loaded_successfully_for_any_source =True
|
||||
else :
|
||||
self ._logger (f"Warning ({source ['name']}): Cookies enabled but could not be loaded for this domain. Fetch might fail if cookies are required.")
|
||||
|
||||
if not cookies_dict_for_source and fallback_domain:
|
||||
self._logger(f"Warning ({source['name']}): No cookies for '{primary_domain}'. Trying fallback '{fallback_domain}'...")
|
||||
cookies_dict_for_source = prepare_cookies_for_request(
|
||||
True, self.cookies_config['cookie_text'], self.cookies_config['selected_cookie_file'],
|
||||
self.cookies_config['app_base_dir'], self._logger, target_domain=fallback_domain
|
||||
)
|
||||
|
||||
if cookies_dict_for_source:
|
||||
any_cookies_loaded_successfully_for_any_source = True
|
||||
else:
|
||||
self._logger(f"Warning ({source['name']}): Cookies enabled but could not be loaded for this domain. Fetch might fail if cookies are required.")
|
||||
|
||||
self ._logger (f"Attempting to fetch favorite posts from: {source ['name']} ({source ['url']})")
|
||||
source_key_part =self .error_key_map .get (source ['name'],source ['name'].lower ().replace ('.','_'))
|
||||
@@ -97,8 +105,18 @@ class FavoritePostsFetcherThread (QThread ):
|
||||
QCoreApplication .processEvents ()
|
||||
|
||||
try :
|
||||
headers ={'User-Agent':'Mozilla/5.0'}
|
||||
response =requests .get (source ['url'],headers =headers ,cookies =cookies_dict_for_source ,timeout =20 )
|
||||
# --- FIX: Add Referer and Accept headers ---
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36',
|
||||
'Referer': f"https://{source['domain']}/favorites",
|
||||
'Accept': 'text/css'
|
||||
}
|
||||
# --- END FIX ---
|
||||
|
||||
# --- FIX: Use scraper instead of requests ---
|
||||
response = scraper.get(source['url'], headers=headers, cookies=cookies_dict_for_source, timeout=20)
|
||||
# --- END FIX ---
|
||||
|
||||
response .raise_for_status ()
|
||||
posts_data_from_api =response .json ()
|
||||
|
||||
@@ -130,33 +148,24 @@ class FavoritePostsFetcherThread (QThread ):
|
||||
fetched_any_successfully =True
|
||||
self ._logger (f"Fetched {processed_posts_from_source } posts from {source ['name']}.")
|
||||
|
||||
except requests .exceptions .RequestException as e :
|
||||
except Exception as e :
|
||||
err_detail =f"Error fetching favorite posts from {source ['name']}: {e }"
|
||||
self ._logger (err_detail )
|
||||
error_messages_for_summary .append (err_detail )
|
||||
if e .response is not None and e .response .status_code ==401 :
|
||||
if hasattr(e, 'response') and e.response is not None and e.response.status_code == 401:
|
||||
self .finished .emit ([],"KEY_AUTH_FAILED")
|
||||
self ._logger (f"Authorization failed for {source ['name']}, emitting KEY_AUTH_FAILED.")
|
||||
return
|
||||
except Exception as e :
|
||||
err_detail =f"An unexpected error occurred with {source ['name']}: {e }"
|
||||
self ._logger (err_detail )
|
||||
error_messages_for_summary .append (err_detail )
|
||||
|
||||
if self .cancellation_event .is_set ():
|
||||
self .finished .emit ([],"KEY_FETCH_CANCELLED_AFTER")
|
||||
return
|
||||
|
||||
|
||||
if self .cookies_config ['use_cookie']and not any_cookies_loaded_successfully_for_any_source :
|
||||
|
||||
if self .target_domain_preference and not any_cookies_loaded_successfully_for_any_source :
|
||||
|
||||
domain_key_part =self .error_key_map .get (self .target_domain_preference ,self .target_domain_preference .lower ().replace ('.','_'))
|
||||
self .finished .emit ([],f"KEY_COOKIES_REQUIRED_BUT_NOT_FOUND_FOR_DOMAIN_{domain_key_part }")
|
||||
return
|
||||
|
||||
|
||||
self .finished .emit ([],"KEY_COOKIES_REQUIRED_BUT_NOT_FOUND_GENERIC")
|
||||
return
|
||||
|
||||
@@ -409,14 +418,14 @@ class FavoritePostsDialog (QDialog ):
|
||||
if status_key .startswith ("KEY_COOKIES_REQUIRED_BUT_NOT_FOUND_FOR_DOMAIN_")or status_key =="KEY_COOKIES_REQUIRED_BUT_NOT_FOUND_GENERIC":
|
||||
status_label_text_key ="fav_posts_cookies_required_error"
|
||||
self ._logger (f"Cookie error: {status_key }. Showing help dialog.")
|
||||
cookie_help_dialog =CookieHelpDialog (self )
|
||||
cookie_help_dialog = CookieHelpDialog(self.parent_app, self)
|
||||
cookie_help_dialog .exec_ ()
|
||||
elif status_key =="KEY_AUTH_FAILED":
|
||||
status_label_text_key ="fav_posts_auth_failed_title"
|
||||
self ._logger (f"Auth error: {status_key }. Showing help dialog.")
|
||||
QMessageBox .warning (self ,self ._tr ("fav_posts_auth_failed_title","Authorization Failed (Posts)"),
|
||||
self ._tr ("fav_posts_auth_failed_message_generic","...").format (domain_specific_part =specific_domain_msg_part ))
|
||||
cookie_help_dialog =CookieHelpDialog (self )
|
||||
cookie_help_dialog = CookieHelpDialog(self.parent_app, self)
|
||||
cookie_help_dialog .exec_ ()
|
||||
elif status_key =="KEY_NO_FAVORITES_FOUND_ALL_PLATFORMS":
|
||||
status_label_text_key ="fav_posts_no_posts_found_status"
|
||||
@@ -620,4 +629,4 @@ class FavoritePostsDialog (QDialog ):
|
||||
self .accept ()
|
||||
|
||||
def get_selected_posts (self ):
|
||||
return self .selected_posts_data
|
||||
return self .selected_posts_data
|
||||
@@ -1,23 +1,111 @@
|
||||
# --- Standard Library Imports ---
|
||||
import os
|
||||
import json
|
||||
import sys
|
||||
|
||||
# --- PyQt5 Imports ---
|
||||
from PyQt5.QtCore import Qt, QStandardPaths
|
||||
from PyQt5.QtCore import Qt, QStandardPaths, QTimer
|
||||
from PyQt5.QtWidgets import (
|
||||
QApplication, QDialog, QHBoxLayout, QLabel, QPushButton, QVBoxLayout,
|
||||
QGroupBox, QComboBox, QMessageBox, QGridLayout, QCheckBox
|
||||
)
|
||||
|
||||
# --- Local Application Imports ---
|
||||
from ...i18n.translator import get_translation
|
||||
from ...utils.resolution import get_dark_theme
|
||||
from ..assets import get_app_icon_object
|
||||
|
||||
from ..main_window import get_app_icon_object
|
||||
from ...config.constants import (
|
||||
THEME_KEY, LANGUAGE_KEY, DOWNLOAD_LOCATION_KEY,
|
||||
RESOLUTION_KEY, UI_SCALE_KEY, SAVE_CREATOR_JSON_KEY
|
||||
RESOLUTION_KEY, UI_SCALE_KEY, SAVE_CREATOR_JSON_KEY,
|
||||
COOKIE_TEXT_KEY, USE_COOKIE_KEY,
|
||||
FETCH_FIRST_KEY, DISCORD_TOKEN_KEY, POST_DOWNLOAD_ACTION_KEY
|
||||
)
|
||||
from ...services.updater import UpdateChecker, UpdateDownloader
|
||||
|
||||
class CountdownMessageBox(QDialog):
|
||||
"""
|
||||
A custom message box that includes a countdown timer for the 'Yes' button,
|
||||
which automatically accepts the dialog when the timer reaches zero.
|
||||
"""
|
||||
def __init__(self, title, text, countdown_seconds=10, parent_app=None, parent=None):
|
||||
super().__init__(parent)
|
||||
self.parent_app = parent_app
|
||||
self.countdown = countdown_seconds
|
||||
|
||||
# --- Basic Window Setup ---
|
||||
self.setWindowTitle(title)
|
||||
self.setModal(True)
|
||||
app_icon = get_app_icon_object()
|
||||
if app_icon and not app_icon.isNull():
|
||||
self.setWindowIcon(app_icon)
|
||||
|
||||
self._init_ui(text)
|
||||
self._apply_theme()
|
||||
|
||||
# --- Timer Setup ---
|
||||
self.timer = QTimer(self)
|
||||
self.timer.setInterval(1000) # Tick every second
|
||||
self.timer.timeout.connect(self._update_countdown)
|
||||
self.timer.start()
|
||||
|
||||
def _init_ui(self, text):
|
||||
"""Initializes the UI components of the dialog."""
|
||||
main_layout = QVBoxLayout(self)
|
||||
|
||||
self.message_label = QLabel(text)
|
||||
self.message_label.setWordWrap(True)
|
||||
self.message_label.setAlignment(Qt.AlignCenter)
|
||||
main_layout.addWidget(self.message_label)
|
||||
|
||||
buttons_layout = QHBoxLayout()
|
||||
buttons_layout.addStretch(1)
|
||||
|
||||
self.yes_button = QPushButton()
|
||||
self.yes_button.clicked.connect(self.accept)
|
||||
self.yes_button.setDefault(True)
|
||||
|
||||
self.no_button = QPushButton()
|
||||
self.no_button.clicked.connect(self.reject)
|
||||
|
||||
buttons_layout.addWidget(self.yes_button)
|
||||
buttons_layout.addWidget(self.no_button)
|
||||
buttons_layout.addStretch(1)
|
||||
|
||||
main_layout.addLayout(buttons_layout)
|
||||
|
||||
self._retranslate_ui()
|
||||
self._update_countdown() # Initial text setup
|
||||
|
||||
def _tr(self, key, default_text=""):
|
||||
"""Helper for translations."""
|
||||
if self.parent_app and hasattr(self.parent_app, 'current_selected_language'):
|
||||
return get_translation(self.parent_app.current_selected_language, key, default_text)
|
||||
return default_text
|
||||
|
||||
def _retranslate_ui(self):
|
||||
"""Sets translated text for UI elements."""
|
||||
self.no_button.setText(self._tr("no_button_text", "No"))
|
||||
# The 'yes' button text is handled by the countdown
|
||||
|
||||
def _update_countdown(self):
|
||||
"""Updates the countdown and button text each second."""
|
||||
if self.countdown <= 0:
|
||||
self.timer.stop()
|
||||
self.accept() # Automatically accept when countdown finishes
|
||||
return
|
||||
|
||||
yes_text = self._tr("yes_button_text", "Yes")
|
||||
self.yes_button.setText(f"{yes_text} ({self.countdown})")
|
||||
self.countdown -= 1
|
||||
|
||||
def _apply_theme(self):
|
||||
"""Applies the current theme from the parent application."""
|
||||
if self.parent_app and hasattr(self.parent_app, 'current_theme') and self.parent_app.current_theme == "dark":
|
||||
scale = getattr(self.parent_app, 'scale_factor', 1)
|
||||
self.setStyleSheet(get_dark_theme(scale))
|
||||
else:
|
||||
self.setStyleSheet("")
|
||||
|
||||
class FutureSettingsDialog(QDialog):
|
||||
"""
|
||||
@@ -28,6 +116,7 @@ class FutureSettingsDialog(QDialog):
|
||||
super().__init__(parent)
|
||||
self.parent_app = parent_app_ref
|
||||
self.setModal(True)
|
||||
self.update_downloader_thread = None # To keep a reference
|
||||
|
||||
app_icon = get_app_icon_object()
|
||||
if app_icon and not app_icon.isNull():
|
||||
@@ -35,7 +124,7 @@ class FutureSettingsDialog(QDialog):
|
||||
|
||||
screen_height = QApplication.primaryScreen().availableGeometry().height() if QApplication.primaryScreen() else 800
|
||||
scale_factor = screen_height / 800.0
|
||||
base_min_w, base_min_h = 420, 360 # Adjusted height for new layout
|
||||
base_min_w, base_min_h = 420, 520 # Increased height for new options
|
||||
scaled_min_w = int(base_min_w * scale_factor)
|
||||
scaled_min_h = int(base_min_h * scale_factor)
|
||||
self.setMinimumSize(scaled_min_w, scaled_min_h)
|
||||
@@ -48,25 +137,21 @@ class FutureSettingsDialog(QDialog):
|
||||
"""Initializes all UI components and layouts for the dialog."""
|
||||
main_layout = QVBoxLayout(self)
|
||||
|
||||
# --- Group 1: Interface Settings ---
|
||||
self.interface_group_box = QGroupBox()
|
||||
interface_layout = QGridLayout(self.interface_group_box)
|
||||
|
||||
# Theme
|
||||
self.theme_label = QLabel()
|
||||
self.theme_toggle_button = QPushButton()
|
||||
self.theme_toggle_button.clicked.connect(self._toggle_theme)
|
||||
interface_layout.addWidget(self.theme_label, 0, 0)
|
||||
interface_layout.addWidget(self.theme_toggle_button, 0, 1)
|
||||
|
||||
# UI Scale
|
||||
self.ui_scale_label = QLabel()
|
||||
self.ui_scale_combo_box = QComboBox()
|
||||
self.ui_scale_combo_box.currentIndexChanged.connect(self._display_setting_changed)
|
||||
interface_layout.addWidget(self.ui_scale_label, 1, 0)
|
||||
interface_layout.addWidget(self.ui_scale_combo_box, 1, 1)
|
||||
|
||||
# Language
|
||||
|
||||
self.language_label = QLabel()
|
||||
self.language_combo_box = QComboBox()
|
||||
self.language_combo_box.currentIndexChanged.connect(self._language_selection_changed)
|
||||
@@ -75,85 +160,148 @@ class FutureSettingsDialog(QDialog):
|
||||
|
||||
main_layout.addWidget(self.interface_group_box)
|
||||
|
||||
# --- Group 2: Download & Window Settings ---
|
||||
self.download_window_group_box = QGroupBox()
|
||||
download_window_layout = QGridLayout(self.download_window_group_box)
|
||||
|
||||
# Window Size (Resolution)
|
||||
|
||||
self.window_size_label = QLabel()
|
||||
self.resolution_combo_box = QComboBox()
|
||||
self.resolution_combo_box.currentIndexChanged.connect(self._display_setting_changed)
|
||||
download_window_layout.addWidget(self.window_size_label, 0, 0)
|
||||
download_window_layout.addWidget(self.resolution_combo_box, 0, 1)
|
||||
|
||||
# Default Path
|
||||
self.default_path_label = QLabel()
|
||||
self.save_path_button = QPushButton()
|
||||
self.save_path_button.clicked.connect(self._save_download_path)
|
||||
self.save_path_button.clicked.connect(self._save_settings)
|
||||
download_window_layout.addWidget(self.default_path_label, 1, 0)
|
||||
download_window_layout.addWidget(self.save_path_button, 1, 1)
|
||||
|
||||
# Save Creator.json Checkbox
|
||||
self.post_download_action_label = QLabel()
|
||||
self.post_download_action_combo = QComboBox()
|
||||
self.post_download_action_combo.currentIndexChanged.connect(self._post_download_action_changed)
|
||||
download_window_layout.addWidget(self.post_download_action_label, 2, 0)
|
||||
download_window_layout.addWidget(self.post_download_action_combo, 2, 1)
|
||||
|
||||
self.save_creator_json_checkbox = QCheckBox()
|
||||
self.save_creator_json_checkbox.stateChanged.connect(self._creator_json_setting_changed)
|
||||
download_window_layout.addWidget(self.save_creator_json_checkbox, 2, 0, 1, 2)
|
||||
self.save_creator_json_checkbox.stateChanged.connect(self._creator_json_setting_changed)
|
||||
download_window_layout.addWidget(self.save_creator_json_checkbox, 3, 0, 1, 2)
|
||||
|
||||
self.fetch_first_checkbox = QCheckBox()
|
||||
self.fetch_first_checkbox.stateChanged.connect(self._fetch_first_setting_changed)
|
||||
download_window_layout.addWidget(self.fetch_first_checkbox, 4, 0, 1, 2)
|
||||
|
||||
main_layout.addWidget(self.download_window_group_box)
|
||||
|
||||
self.update_group_box = QGroupBox()
|
||||
update_layout = QGridLayout(self.update_group_box)
|
||||
self.version_label = QLabel()
|
||||
self.update_status_label = QLabel()
|
||||
self.check_update_button = QPushButton()
|
||||
self.check_update_button.clicked.connect(self._check_for_updates)
|
||||
update_layout.addWidget(self.version_label, 0, 0)
|
||||
update_layout.addWidget(self.update_status_label, 0, 1)
|
||||
update_layout.addWidget(self.check_update_button, 1, 0, 1, 2)
|
||||
main_layout.addWidget(self.update_group_box)
|
||||
|
||||
main_layout.addStretch(1)
|
||||
|
||||
# --- OK Button ---
|
||||
self.ok_button = QPushButton()
|
||||
self.ok_button.clicked.connect(self.accept)
|
||||
main_layout.addWidget(self.ok_button, 0, Qt.AlignRight | Qt.AlignBottom)
|
||||
|
||||
def _retranslate_ui(self):
|
||||
self.setWindowTitle(self._tr("settings_dialog_title", "Settings"))
|
||||
self.interface_group_box.setTitle(self._tr("interface_group_title", "Interface Settings"))
|
||||
self.download_window_group_box.setTitle(self._tr("download_window_group_title", "Download & Window Settings"))
|
||||
self.theme_label.setText(self._tr("theme_label", "Theme:"))
|
||||
self.ui_scale_label.setText(self._tr("ui_scale_label", "UI Scale:"))
|
||||
self.language_label.setText(self._tr("language_label", "Language:"))
|
||||
self.window_size_label.setText(self._tr("window_size_label", "Window Size:"))
|
||||
self.default_path_label.setText(self._tr("default_path_label", "Default Path:"))
|
||||
self.post_download_action_label.setText(self._tr("post_download_action_label", "Action After Download:"))
|
||||
self.save_creator_json_checkbox.setText(self._tr("save_creator_json_label", "Save Creator.json file"))
|
||||
self.fetch_first_checkbox.setText(self._tr("fetch_first_label", "Fetch First (Download after all pages are found)"))
|
||||
self.fetch_first_checkbox.setToolTip(self._tr("fetch_first_tooltip", "If checked, the downloader will find all posts from a creator first before starting any downloads.\nThis can be slower to start but provides a more accurate progress bar."))
|
||||
self._update_theme_toggle_button_text()
|
||||
self.save_path_button.setText(self._tr("settings_save_all_button", "Save Path + Cookie + Token"))
|
||||
self.save_path_button.setToolTip(self._tr("settings_save_all_tooltip", "Save the current 'Download Location', Cookie, and Discord Token settings for future sessions."))
|
||||
self.ok_button.setText(self._tr("ok_button", "OK"))
|
||||
|
||||
self.update_group_box.setTitle(self._tr("update_group_title", "Application Updates"))
|
||||
current_version = self.parent_app.windowTitle().split(' v')[-1]
|
||||
self.version_label.setText(self._tr("current_version_label", f"Current Version: v{current_version}"))
|
||||
self.update_status_label.setText(self._tr("update_status_ready", "Ready to check."))
|
||||
self.check_update_button.setText(self._tr("check_for_updates_button", "Check for Updates"))
|
||||
|
||||
self._populate_display_combo_boxes()
|
||||
self._populate_language_combo_box()
|
||||
self._populate_post_download_action_combo()
|
||||
self._load_checkbox_states()
|
||||
|
||||
def _check_for_updates(self):
|
||||
self.check_update_button.setEnabled(False)
|
||||
self.update_status_label.setText(self._tr("update_status_checking", "Checking..."))
|
||||
current_version = self.parent_app.windowTitle().split(' v')[-1]
|
||||
|
||||
self.update_checker_thread = UpdateChecker(current_version)
|
||||
self.update_checker_thread.update_available.connect(self._on_update_available)
|
||||
self.update_checker_thread.up_to_date.connect(self._on_up_to_date)
|
||||
self.update_checker_thread.update_error.connect(self._on_update_error)
|
||||
self.update_checker_thread.start()
|
||||
|
||||
def _on_update_available(self, new_version, download_url):
|
||||
self.update_status_label.setText(self._tr("update_status_found", f"Update found: v{new_version}"))
|
||||
self.check_update_button.setEnabled(True)
|
||||
|
||||
reply = QMessageBox.question(self, self._tr("update_available_title", "Update Available"),
|
||||
self._tr("update_available_message", f"A new version (v{new_version}) is available.\nWould you like to download and install it now?"),
|
||||
QMessageBox.Yes | QMessageBox.No, QMessageBox.Yes)
|
||||
if reply == QMessageBox.Yes:
|
||||
self.ok_button.setEnabled(False)
|
||||
self.check_update_button.setEnabled(False)
|
||||
self.update_status_label.setText(self._tr("update_status_downloading", "Downloading update..."))
|
||||
self.update_downloader_thread = UpdateDownloader(download_url, self.parent_app)
|
||||
self.update_downloader_thread.download_finished.connect(self._on_download_finished)
|
||||
self.update_downloader_thread.download_error.connect(self._on_update_error)
|
||||
self.update_downloader_thread.start()
|
||||
|
||||
def _on_download_finished(self):
|
||||
QApplication.instance().quit()
|
||||
|
||||
def _on_up_to_date(self, message):
|
||||
self.update_status_label.setText(self._tr("update_status_latest", message))
|
||||
self.check_update_button.setEnabled(True)
|
||||
|
||||
def _on_update_error(self, message):
|
||||
self.update_status_label.setText(self._tr("update_status_error", f"Error: {message}"))
|
||||
self.check_update_button.setEnabled(True)
|
||||
self.ok_button.setEnabled(True)
|
||||
|
||||
def _load_checkbox_states(self):
|
||||
"""Loads the initial state for all checkboxes from settings."""
|
||||
self.save_creator_json_checkbox.blockSignals(True)
|
||||
# Default to True so the feature is on by default for users
|
||||
should_save = self.parent_app.settings.value(SAVE_CREATOR_JSON_KEY, True, type=bool)
|
||||
self.save_creator_json_checkbox.setChecked(should_save)
|
||||
self.save_creator_json_checkbox.blockSignals(False)
|
||||
|
||||
self.fetch_first_checkbox.blockSignals(True)
|
||||
should_fetch_first = self.parent_app.settings.value(FETCH_FIRST_KEY, False, type=bool)
|
||||
self.fetch_first_checkbox.setChecked(should_fetch_first)
|
||||
self.fetch_first_checkbox.blockSignals(False)
|
||||
|
||||
def _creator_json_setting_changed(self, state):
|
||||
"""Saves the state of the 'Save Creator.json' checkbox."""
|
||||
is_checked = state == Qt.Checked
|
||||
self.parent_app.settings.setValue(SAVE_CREATOR_JSON_KEY, is_checked)
|
||||
self.parent_app.settings.sync()
|
||||
|
||||
def _fetch_first_setting_changed(self, state):
|
||||
is_checked = state == Qt.Checked
|
||||
self.parent_app.settings.setValue(FETCH_FIRST_KEY, is_checked)
|
||||
self.parent_app.settings.sync()
|
||||
|
||||
def _tr(self, key, default_text=""):
|
||||
if callable(get_translation) and self.parent_app:
|
||||
return get_translation(self.parent_app.current_selected_language, key, default_text)
|
||||
return default_text
|
||||
|
||||
def _retranslate_ui(self):
|
||||
self.setWindowTitle(self._tr("settings_dialog_title", "Settings"))
|
||||
|
||||
# Group Box Titles
|
||||
self.interface_group_box.setTitle(self._tr("interface_group_title", "Interface Settings"))
|
||||
self.download_window_group_box.setTitle(self._tr("download_window_group_title", "Download & Window Settings"))
|
||||
|
||||
# Interface Group Labels
|
||||
self.theme_label.setText(self._tr("theme_label", "Theme:"))
|
||||
self.ui_scale_label.setText(self._tr("ui_scale_label", "UI Scale:"))
|
||||
self.language_label.setText(self._tr("language_label", "Language:"))
|
||||
|
||||
# Download & Window Group Labels
|
||||
self.window_size_label.setText(self._tr("window_size_label", "Window Size:"))
|
||||
self.default_path_label.setText(self._tr("default_path_label", "Default Path:"))
|
||||
self.save_creator_json_checkbox.setText(self._tr("save_creator_json_label", "Save Creator.json file"))
|
||||
|
||||
# Buttons and Controls
|
||||
self._update_theme_toggle_button_text()
|
||||
self.save_path_button.setText(self._tr("settings_save_path_button", "Save Current Download Path"))
|
||||
self.save_path_button.setToolTip(self._tr("settings_save_path_tooltip", "Save the current 'Download Location' for future sessions."))
|
||||
self.ok_button.setText(self._tr("ok_button", "OK"))
|
||||
|
||||
# Populate dropdowns
|
||||
self._populate_display_combo_boxes()
|
||||
self._populate_language_combo_box()
|
||||
self._load_checkbox_states()
|
||||
|
||||
def _apply_theme(self):
|
||||
if self.parent_app and self.parent_app.current_theme == "dark":
|
||||
scale = getattr(self.parent_app, 'scale_factor', 1)
|
||||
@@ -179,14 +327,7 @@ class FutureSettingsDialog(QDialog):
|
||||
def _populate_display_combo_boxes(self):
|
||||
self.resolution_combo_box.blockSignals(True)
|
||||
self.resolution_combo_box.clear()
|
||||
resolutions = [
|
||||
("Auto", self._tr("auto_resolution", "Auto (System Default)")),
|
||||
("1280x720", "1280 x 720"),
|
||||
("1600x900", "1600 x 900"),
|
||||
("1920x1080", "1920 x 1080 (Full HD)"),
|
||||
("2560x1440", "2560 x 1440 (2K)"),
|
||||
("3840x2160", "3840 x 2160 (4K)")
|
||||
]
|
||||
resolutions = [("Auto", "Auto"), ("1280x720", "1280x720"), ("1600x900", "1600x900"), ("1920x1080", "1920x1080")]
|
||||
current_res = self.parent_app.settings.value(RESOLUTION_KEY, "Auto")
|
||||
for res_key, res_name in resolutions:
|
||||
self.resolution_combo_box.addItem(res_name, res_key)
|
||||
@@ -197,43 +338,24 @@ class FutureSettingsDialog(QDialog):
|
||||
self.ui_scale_combo_box.blockSignals(True)
|
||||
self.ui_scale_combo_box.clear()
|
||||
scales = [
|
||||
(0.5, "50%"),
|
||||
(0.7, "70%"),
|
||||
(0.9, "90%"),
|
||||
(1.0, "100% (Default)"),
|
||||
(1.25, "125%"),
|
||||
(1.50, "150%"),
|
||||
(1.75, "175%"),
|
||||
(2.0, "200%")
|
||||
(0.5, "50%"), (0.7, "70%"), (0.9, "90%"), (1.0, "100% (Default)"),
|
||||
(1.25, "125%"), (1.50, "150%"), (1.75, "175%"), (2.0, "200%")
|
||||
]
|
||||
|
||||
current_scale = float(self.parent_app.settings.value(UI_SCALE_KEY, 1.0))
|
||||
current_scale = self.parent_app.settings.value(UI_SCALE_KEY, 1.0)
|
||||
for scale_val, scale_name in scales:
|
||||
self.ui_scale_combo_box.addItem(scale_name, scale_val)
|
||||
if abs(current_scale - scale_val) < 0.01:
|
||||
if abs(float(current_scale) - scale_val) < 0.01:
|
||||
self.ui_scale_combo_box.setCurrentIndex(self.ui_scale_combo_box.count() - 1)
|
||||
self.ui_scale_combo_box.blockSignals(False)
|
||||
|
||||
def _display_setting_changed(self):
|
||||
selected_res = self.resolution_combo_box.currentData()
|
||||
selected_scale = self.ui_scale_combo_box.currentData()
|
||||
|
||||
self.parent_app.settings.setValue(RESOLUTION_KEY, selected_res)
|
||||
self.parent_app.settings.setValue(UI_SCALE_KEY, selected_scale)
|
||||
self.parent_app.settings.sync()
|
||||
|
||||
msg_box = QMessageBox(self)
|
||||
msg_box.setIcon(QMessageBox.Information)
|
||||
msg_box.setWindowTitle(self._tr("display_change_title", "Display Settings Changed"))
|
||||
msg_box.setText(self._tr("language_change_message", "A restart is required for these changes to take effect."))
|
||||
msg_box.setInformativeText(self._tr("language_change_informative", "Would you like to restart now?"))
|
||||
restart_button = msg_box.addButton(self._tr("restart_now_button", "Restart Now"), QMessageBox.ApplyRole)
|
||||
ok_button = msg_box.addButton(self._tr("ok_button", "OK"), QMessageBox.AcceptRole)
|
||||
msg_box.setDefaultButton(ok_button)
|
||||
msg_box.exec_()
|
||||
|
||||
if msg_box.clickedButton() == restart_button:
|
||||
self.parent_app._request_restart_application()
|
||||
QMessageBox.information(self, self._tr("display_change_title", "Display Settings Changed"),
|
||||
self._tr("language_change_message", "A restart is required..."))
|
||||
|
||||
def _populate_language_combo_box(self):
|
||||
self.language_combo_box.blockSignals(True)
|
||||
@@ -257,40 +379,74 @@ class FutureSettingsDialog(QDialog):
|
||||
self.parent_app.settings.setValue(LANGUAGE_KEY, selected_lang_code)
|
||||
self.parent_app.settings.sync()
|
||||
self.parent_app.current_selected_language = selected_lang_code
|
||||
|
||||
self._retranslate_ui()
|
||||
if hasattr(self.parent_app, '_retranslate_main_ui'):
|
||||
self.parent_app._retranslate_main_ui()
|
||||
|
||||
msg_box = QMessageBox(self)
|
||||
msg_box.setIcon(QMessageBox.Information)
|
||||
msg_box.setWindowTitle(self._tr("language_change_title", "Language Changed"))
|
||||
msg_box.setText(self._tr("language_change_message", "A restart is required..."))
|
||||
msg_box.setInformativeText(self._tr("language_change_informative", "Would you like to restart now?"))
|
||||
restart_button = msg_box.addButton(self._tr("restart_now_button", "Restart Now"), QMessageBox.ApplyRole)
|
||||
ok_button = msg_box.addButton(self._tr("ok_button", "OK"), QMessageBox.AcceptRole)
|
||||
msg_box.setDefaultButton(ok_button)
|
||||
msg_box.exec_()
|
||||
self.parent_app._retranslate_main_ui()
|
||||
QMessageBox.information(self, self._tr("language_change_title", "Language Changed"),
|
||||
self._tr("language_change_message", "A restart is required..."))
|
||||
|
||||
if msg_box.clickedButton() == restart_button:
|
||||
self.parent_app._request_restart_application()
|
||||
def _populate_post_download_action_combo(self):
|
||||
"""Populates the action dropdown and sets the current selection from settings."""
|
||||
self.post_download_action_combo.blockSignals(True)
|
||||
self.post_download_action_combo.clear()
|
||||
|
||||
actions = [
|
||||
(self._tr("action_off", "Off"), "off"),
|
||||
(self._tr("action_notify", "Notify with Sound"), "notify"),
|
||||
(self._tr("action_sleep", "Sleep"), "sleep"),
|
||||
(self._tr("action_shutdown", "Shutdown"), "shutdown")
|
||||
]
|
||||
|
||||
current_action = self.parent_app.settings.value(POST_DOWNLOAD_ACTION_KEY, "off")
|
||||
|
||||
for text, key in actions:
|
||||
self.post_download_action_combo.addItem(text, key)
|
||||
if current_action == key:
|
||||
self.post_download_action_combo.setCurrentIndex(self.post_download_action_combo.count() - 1)
|
||||
|
||||
self.post_download_action_combo.blockSignals(False)
|
||||
|
||||
def _post_download_action_changed(self):
|
||||
"""Saves the selected post-download action to settings."""
|
||||
selected_action = self.post_download_action_combo.currentData()
|
||||
self.parent_app.settings.setValue(POST_DOWNLOAD_ACTION_KEY, selected_action)
|
||||
self.parent_app.settings.sync()
|
||||
|
||||
def _save_settings(self):
|
||||
path_saved = False
|
||||
cookie_saved = False
|
||||
token_saved = False
|
||||
|
||||
def _save_download_path(self):
|
||||
if hasattr(self.parent_app, 'dir_input') and self.parent_app.dir_input:
|
||||
current_path = self.parent_app.dir_input.text().strip()
|
||||
if current_path and os.path.isdir(current_path):
|
||||
self.parent_app.settings.setValue(DOWNLOAD_LOCATION_KEY, current_path)
|
||||
self.parent_app.settings.sync()
|
||||
QMessageBox.information(self,
|
||||
self._tr("settings_save_path_success_title", "Path Saved"),
|
||||
self._tr("settings_save_path_success_message", "Download location '{path}' saved.").format(path=current_path))
|
||||
elif not current_path:
|
||||
QMessageBox.warning(self,
|
||||
self._tr("settings_save_path_empty_title", "Empty Path"),
|
||||
self._tr("settings_save_path_empty_message", "Download location cannot be empty."))
|
||||
path_saved = True
|
||||
|
||||
if hasattr(self.parent_app, 'use_cookie_checkbox'):
|
||||
use_cookie = self.parent_app.use_cookie_checkbox.isChecked()
|
||||
cookie_content = self.parent_app.cookie_text_input.text().strip()
|
||||
if use_cookie and cookie_content:
|
||||
self.parent_app.settings.setValue(USE_COOKIE_KEY, True)
|
||||
self.parent_app.settings.setValue(COOKIE_TEXT_KEY, cookie_content)
|
||||
cookie_saved = True
|
||||
else:
|
||||
QMessageBox.warning(self,
|
||||
self._tr("settings_save_path_invalid_title", "Invalid Path"),
|
||||
self._tr("settings_save_path_invalid_message", "The path '{path}' is not a valid directory.").format(path=current_path))
|
||||
self.parent_app.settings.setValue(USE_COOKIE_KEY, False)
|
||||
self.parent_app.settings.setValue(COOKIE_TEXT_KEY, "")
|
||||
|
||||
if (hasattr(self.parent_app, 'remove_from_filename_input') and
|
||||
hasattr(self.parent_app, 'remove_from_filename_label_widget')):
|
||||
|
||||
label_text = self.parent_app.remove_from_filename_label_widget.text()
|
||||
if "Token" in label_text:
|
||||
discord_token = self.parent_app.remove_from_filename_input.text().strip()
|
||||
if discord_token:
|
||||
self.parent_app.settings.setValue(DISCORD_TOKEN_KEY, discord_token)
|
||||
token_saved = True
|
||||
|
||||
self.parent_app.settings.sync()
|
||||
|
||||
if path_saved or cookie_saved or token_saved:
|
||||
QMessageBox.information(self, "Settings Saved", "Settings have been saved successfully.")
|
||||
else:
|
||||
QMessageBox.critical(self, "Error", "Could not access download path input from main application.")
|
||||
QMessageBox.warning(self, "Nothing to Save", "No valid settings were found to save.")
|
||||
|
||||
@@ -4,7 +4,7 @@ from PyQt5.QtCore import QUrl, QSize, Qt
|
||||
from PyQt5.QtGui import QIcon, QDesktopServices
|
||||
from PyQt5.QtWidgets import (
|
||||
QApplication, QDialog, QHBoxLayout, QLabel, QPushButton, QVBoxLayout,
|
||||
QStackedWidget, QScrollArea, QFrame, QWidget
|
||||
QStackedWidget, QListWidget, QFrame, QWidget, QScrollArea
|
||||
)
|
||||
from ...i18n.translator import get_translation
|
||||
from ..main_window import get_app_icon_object
|
||||
@@ -46,13 +46,12 @@ class TourStepWidget(QWidget):
|
||||
layout.addWidget(scroll_area, 1)
|
||||
|
||||
|
||||
class HelpGuideDialog (QDialog ):
|
||||
"""A multi-page dialog for displaying the feature guide."""
|
||||
def __init__ (self ,steps_data ,parent_app ,parent =None ):
|
||||
super ().__init__ (parent )
|
||||
self .current_step =0
|
||||
self .steps_data =steps_data
|
||||
self .parent_app =parent_app
|
||||
class HelpGuideDialog(QDialog):
|
||||
"""A multi-page dialog for displaying the feature guide with a navigation list."""
|
||||
def __init__(self, steps_data, parent_app, parent=None):
|
||||
super().__init__(parent)
|
||||
self.steps_data = steps_data
|
||||
self.parent_app = parent_app
|
||||
|
||||
scale = self.parent_app.scale_factor if hasattr(self.parent_app, 'scale_factor') else 1.0
|
||||
|
||||
@@ -61,7 +60,7 @@ class HelpGuideDialog (QDialog ):
|
||||
self.setWindowIcon(app_icon)
|
||||
|
||||
self.setModal(True)
|
||||
self.resize(int(650 * scale), int(600 * scale))
|
||||
self.resize(int(800 * scale), int(650 * scale))
|
||||
|
||||
dialog_font_size = int(11 * scale)
|
||||
|
||||
@@ -69,6 +68,7 @@ class HelpGuideDialog (QDialog ):
|
||||
if hasattr(self.parent_app, 'current_theme') and self.parent_app.current_theme == "dark":
|
||||
current_theme_style = get_dark_theme(scale)
|
||||
else:
|
||||
# Basic light theme fallback
|
||||
current_theme_style = f"""
|
||||
QDialog {{ background-color: #F0F0F0; border: 1px solid #B0B0B0; }}
|
||||
QLabel {{ color: #1E1E1E; }}
|
||||
@@ -86,118 +86,107 @@ class HelpGuideDialog (QDialog ):
|
||||
"""
|
||||
|
||||
self.setStyleSheet(current_theme_style)
|
||||
self ._init_ui ()
|
||||
if self .parent_app :
|
||||
self .move (self .parent_app .geometry ().center ()-self .rect ().center ())
|
||||
self._init_ui()
|
||||
if self.parent_app:
|
||||
self.move(self.parent_app.geometry().center() - self.rect().center())
|
||||
|
||||
def _tr (self ,key ,default_text =""):
|
||||
def _tr(self, key, default_text=""):
|
||||
"""Helper to get translation based on current app language."""
|
||||
if callable (get_translation )and self .parent_app :
|
||||
return get_translation (self .parent_app .current_selected_language ,key ,default_text )
|
||||
return default_text
|
||||
if callable(get_translation) and self.parent_app:
|
||||
return get_translation(self.parent_app.current_selected_language, key, default_text)
|
||||
return default_text
|
||||
|
||||
def _init_ui(self):
|
||||
main_layout = QVBoxLayout(self)
|
||||
main_layout.setContentsMargins(15, 15, 15, 15)
|
||||
main_layout.setSpacing(10)
|
||||
|
||||
def _init_ui (self ):
|
||||
main_layout =QVBoxLayout (self )
|
||||
main_layout .setContentsMargins (0 ,0 ,0 ,0 )
|
||||
main_layout .setSpacing (0 )
|
||||
# Title
|
||||
title_label = QLabel(self._tr("help_guide_dialog_title", "Kemono Downloader - Feature Guide"))
|
||||
scale = getattr(self.parent_app, 'scale_factor', 1.0)
|
||||
title_font_size = int(16 * scale)
|
||||
title_label.setStyleSheet(f"font-size: {title_font_size}pt; font-weight: bold; color: #E0E0E0;")
|
||||
title_label.setAlignment(Qt.AlignCenter)
|
||||
main_layout.addWidget(title_label)
|
||||
|
||||
self .stacked_widget =QStackedWidget ()
|
||||
main_layout .addWidget (self .stacked_widget ,1 )
|
||||
# Content Layout (Navigation + Stacked Pages)
|
||||
content_layout = QHBoxLayout()
|
||||
main_layout.addLayout(content_layout, 1)
|
||||
|
||||
self .tour_steps_widgets =[]
|
||||
scale = self.parent_app.scale_factor if hasattr(self.parent_app, 'scale_factor') else 1.0
|
||||
for title, content in self.steps_data:
|
||||
step_widget = TourStepWidget(title, content, scale=scale)
|
||||
self.tour_steps_widgets.append(step_widget)
|
||||
self.nav_list = QListWidget()
|
||||
self.nav_list.setFixedWidth(int(220 * scale))
|
||||
self.nav_list.setStyleSheet(f"""
|
||||
QListWidget {{
|
||||
background-color: #2E2E2E;
|
||||
border: 1px solid #4A4A4A;
|
||||
border-radius: 4px;
|
||||
font-size: {int(11 * scale)}pt;
|
||||
}}
|
||||
QListWidget::item {{
|
||||
padding: 10px;
|
||||
border-bottom: 1px solid #4A4A4A;
|
||||
}}
|
||||
QListWidget::item:selected {{
|
||||
background-color: #87CEEB;
|
||||
color: #2E2E2E;
|
||||
font-weight: bold;
|
||||
}}
|
||||
""")
|
||||
content_layout.addWidget(self.nav_list)
|
||||
|
||||
self.stacked_widget = QStackedWidget()
|
||||
content_layout.addWidget(self.stacked_widget)
|
||||
|
||||
for title_key, content_key in self.steps_data:
|
||||
title = self._tr(title_key, title_key)
|
||||
content = self._tr(content_key, f"Content for {content_key} not found.")
|
||||
|
||||
self.nav_list.addItem(title)
|
||||
|
||||
step_widget = TourStepWidget(title, content, scale=scale)
|
||||
self.stacked_widget.addWidget(step_widget)
|
||||
|
||||
self .setWindowTitle (self ._tr ("help_guide_dialog_title","Kemono Downloader - Feature Guide"))
|
||||
self.nav_list.currentRowChanged.connect(self.stacked_widget.setCurrentIndex)
|
||||
if self.nav_list.count() > 0:
|
||||
self.nav_list.setCurrentRow(0)
|
||||
|
||||
buttons_layout =QHBoxLayout ()
|
||||
buttons_layout .setContentsMargins (15 ,10 ,15 ,15 )
|
||||
buttons_layout .setSpacing (10 )
|
||||
# Footer Layout (Social links and Close button)
|
||||
footer_layout = QHBoxLayout()
|
||||
footer_layout.setContentsMargins(0, 10, 0, 0)
|
||||
|
||||
# Social Media Icons
|
||||
if getattr(sys, 'frozen', False) and hasattr(sys, '_MEIPASS'):
|
||||
assets_base_dir = sys._MEIPASS
|
||||
else:
|
||||
assets_base_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', '..', '..'))
|
||||
|
||||
self .back_button =QPushButton (self ._tr ("tour_dialog_back_button","Back"))
|
||||
self .back_button .clicked .connect (self ._previous_step )
|
||||
self .back_button .setEnabled (False )
|
||||
github_icon_path = os.path.join(assets_base_dir, "assets", "github.png")
|
||||
instagram_icon_path = os.path.join(assets_base_dir, "assets", "instagram.png")
|
||||
discord_icon_path = os.path.join(assets_base_dir, "assets", "discord.png")
|
||||
|
||||
if getattr (sys ,'frozen',False )and hasattr (sys ,'_MEIPASS'):
|
||||
assets_base_dir =sys ._MEIPASS
|
||||
else :
|
||||
assets_base_dir =os.path.abspath(os.path.join(os.path.dirname(__file__), '..', '..', '..'))
|
||||
self.github_button = QPushButton(QIcon(github_icon_path), "")
|
||||
self.instagram_button = QPushButton(QIcon(instagram_icon_path), "")
|
||||
self.discord_button = QPushButton(QIcon(discord_icon_path), "")
|
||||
|
||||
github_icon_path =os .path .join (assets_base_dir ,"assets","github.png")
|
||||
instagram_icon_path =os .path .join (assets_base_dir ,"assets","instagram.png")
|
||||
discord_icon_path =os .path .join (assets_base_dir ,"assets","discord.png")
|
||||
|
||||
self .github_button =QPushButton (QIcon (github_icon_path ),"")
|
||||
self .instagram_button =QPushButton (QIcon (instagram_icon_path ),"")
|
||||
self .Discord_button =QPushButton (QIcon (discord_icon_path ),"")
|
||||
|
||||
scale = self.parent_app.scale_factor if hasattr(self.parent_app, 'scale_factor') else 1.0
|
||||
icon_dim = int(24 * scale)
|
||||
icon_size = QSize(icon_dim, icon_dim)
|
||||
self .github_button .setIconSize (icon_size )
|
||||
self .instagram_button .setIconSize (icon_size )
|
||||
self .Discord_button .setIconSize (icon_size )
|
||||
|
||||
for button, tooltip_key, url in [
|
||||
(self.github_button, "help_guide_github_tooltip", "https://github.com/Yuvi9587"),
|
||||
(self.instagram_button, "help_guide_instagram_tooltip", "https://www.instagram.com/uvi.arts/"),
|
||||
(self.discord_button, "help_guide_discord_tooltip", "https://discord.gg/BqP64XTdJN")
|
||||
]:
|
||||
button.setIconSize(icon_size)
|
||||
button.setToolTip(self._tr(tooltip_key))
|
||||
button.setFixedSize(icon_size.width() + 8, icon_size.height() + 8)
|
||||
button.setStyleSheet("background-color: transparent; border: none;")
|
||||
button.clicked.connect(lambda _, u=url: QDesktopServices.openUrl(QUrl(u)))
|
||||
footer_layout.addWidget(button)
|
||||
|
||||
self .next_button =QPushButton (self ._tr ("tour_dialog_next_button","Next"))
|
||||
self .next_button .clicked .connect (self ._next_step_action )
|
||||
self .next_button .setDefault (True )
|
||||
self .github_button .clicked .connect (self ._open_github_link )
|
||||
self .instagram_button .clicked .connect (self ._open_instagram_link )
|
||||
self .Discord_button .clicked .connect (self ._open_Discord_link )
|
||||
self .github_button .setToolTip (self ._tr ("help_guide_github_tooltip","Visit project's GitHub page (Opens in browser)"))
|
||||
self .instagram_button .setToolTip (self ._tr ("help_guide_instagram_tooltip","Visit our Instagram page (Opens in browser)"))
|
||||
self .Discord_button .setToolTip (self ._tr ("help_guide_discord_tooltip","Visit our Discord community (Opens in browser)"))
|
||||
footer_layout.addStretch(1)
|
||||
|
||||
self.finish_button = QPushButton(self._tr("tour_dialog_finish_button", "Finish"))
|
||||
self.finish_button.clicked.connect(self.accept)
|
||||
footer_layout.addWidget(self.finish_button)
|
||||
|
||||
social_layout =QHBoxLayout ()
|
||||
social_layout .setSpacing (10 )
|
||||
social_layout .addWidget (self .github_button )
|
||||
social_layout .addWidget (self .instagram_button )
|
||||
social_layout .addWidget (self .Discord_button )
|
||||
|
||||
while buttons_layout .count ():
|
||||
item =buttons_layout .takeAt (0 )
|
||||
if item .widget ():
|
||||
item .widget ().setParent (None )
|
||||
elif item .layout ():
|
||||
pass
|
||||
buttons_layout .addLayout (social_layout )
|
||||
buttons_layout .addStretch (1 )
|
||||
buttons_layout .addWidget (self .back_button )
|
||||
buttons_layout .addWidget (self .next_button )
|
||||
main_layout .addLayout (buttons_layout )
|
||||
self ._update_button_states ()
|
||||
|
||||
def _next_step_action (self ):
|
||||
if self .current_step <len (self .tour_steps_widgets )-1 :
|
||||
self .current_step +=1
|
||||
self .stacked_widget .setCurrentIndex (self .current_step )
|
||||
else :
|
||||
self .accept ()
|
||||
self ._update_button_states ()
|
||||
|
||||
def _previous_step (self ):
|
||||
if self .current_step >0 :
|
||||
self .current_step -=1
|
||||
self .stacked_widget .setCurrentIndex (self .current_step )
|
||||
self ._update_button_states ()
|
||||
|
||||
def _update_button_states (self ):
|
||||
if self .current_step ==len (self .tour_steps_widgets )-1 :
|
||||
self .next_button .setText (self ._tr ("tour_dialog_finish_button","Finish"))
|
||||
else :
|
||||
self .next_button .setText (self ._tr ("tour_dialog_next_button","Next"))
|
||||
self .back_button .setEnabled (self .current_step >0 )
|
||||
|
||||
def _open_github_link (self ):
|
||||
QDesktopServices .openUrl (QUrl ("https://github.com/Yuvi9587"))
|
||||
|
||||
def _open_instagram_link (self ):
|
||||
QDesktopServices .openUrl (QUrl ("https://www.instagram.com/uvi.arts/"))
|
||||
|
||||
def _open_Discord_link (self ):
|
||||
QDesktopServices .openUrl (QUrl ("https://discord.gg/BqP64XTdJN"))
|
||||
main_layout.addLayout(footer_layout)
|
||||
@@ -24,7 +24,7 @@ class MoreOptionsDialog(QDialog):
|
||||
layout.addWidget(self.description_label)
|
||||
self.radio_button_group = QButtonGroup(self)
|
||||
self.radio_content = QRadioButton("Description/Content")
|
||||
self.radio_comments = QRadioButton("Comments (Not Working)")
|
||||
self.radio_comments = QRadioButton("Comments")
|
||||
self.radio_button_group.addButton(self.radio_content)
|
||||
self.radio_button_group.addButton(self.radio_comments)
|
||||
layout.addWidget(self.radio_content)
|
||||
|
||||
118
src/ui/dialogs/MultipartScopeDialog.py
Normal file
118
src/ui/dialogs/MultipartScopeDialog.py
Normal file
@@ -0,0 +1,118 @@
|
||||
# multipart_scope_dialog.py
|
||||
from PyQt5.QtWidgets import (
|
||||
QDialog, QVBoxLayout, QGroupBox, QRadioButton, QDialogButtonBox, QButtonGroup,
|
||||
QLabel, QLineEdit, QHBoxLayout, QFrame
|
||||
)
|
||||
from PyQt5.QtGui import QIntValidator
|
||||
from PyQt5.QtCore import Qt
|
||||
|
||||
# It's good practice to get this constant from the source
|
||||
# but for this example, we will define it here.
|
||||
MAX_PARTS = 16
|
||||
|
||||
class MultipartScopeDialog(QDialog):
|
||||
"""
|
||||
A dialog to let the user select the scope, number of parts, and minimum size for multipart downloads.
|
||||
"""
|
||||
SCOPE_VIDEOS = 'videos'
|
||||
SCOPE_ARCHIVES = 'archives'
|
||||
SCOPE_BOTH = 'both'
|
||||
|
||||
def __init__(self, current_scope='both', current_parts=4, current_min_size_mb=100, parent=None):
|
||||
super().__init__(parent)
|
||||
self.setWindowTitle("Multipart Download Options")
|
||||
self.setWindowFlags(self.windowFlags() & ~Qt.WindowContextHelpButtonHint)
|
||||
self.setMinimumWidth(350)
|
||||
|
||||
# Main Layout
|
||||
layout = QVBoxLayout(self)
|
||||
|
||||
# --- Options Group for Scope ---
|
||||
self.options_group_box = QGroupBox("Apply multipart downloads to:")
|
||||
options_layout = QVBoxLayout()
|
||||
# ... (Radio buttons and button group code remains unchanged) ...
|
||||
self.radio_videos = QRadioButton("Videos Only")
|
||||
self.radio_archives = QRadioButton("Archives Only (.zip, .rar, etc.)")
|
||||
self.radio_both = QRadioButton("Both Videos and Archives")
|
||||
|
||||
if current_scope == self.SCOPE_VIDEOS:
|
||||
self.radio_videos.setChecked(True)
|
||||
elif current_scope == self.SCOPE_ARCHIVES:
|
||||
self.radio_archives.setChecked(True)
|
||||
else:
|
||||
self.radio_both.setChecked(True)
|
||||
|
||||
self.button_group = QButtonGroup(self)
|
||||
self.button_group.addButton(self.radio_videos)
|
||||
self.button_group.addButton(self.radio_archives)
|
||||
self.button_group.addButton(self.radio_both)
|
||||
|
||||
options_layout.addWidget(self.radio_videos)
|
||||
options_layout.addWidget(self.radio_archives)
|
||||
options_layout.addWidget(self.radio_both)
|
||||
self.options_group_box.setLayout(options_layout)
|
||||
layout.addWidget(self.options_group_box)
|
||||
|
||||
# --- START: MODIFIED Download Settings Group ---
|
||||
self.settings_group_box = QGroupBox("Download settings:")
|
||||
settings_layout = QVBoxLayout()
|
||||
|
||||
# Layout for Parts count
|
||||
parts_layout = QHBoxLayout()
|
||||
self.parts_label = QLabel("Number of download parts per file:")
|
||||
self.parts_input = QLineEdit(str(current_parts))
|
||||
self.parts_input.setValidator(QIntValidator(2, MAX_PARTS, self))
|
||||
self.parts_input.setFixedWidth(40)
|
||||
self.parts_input.setToolTip(f"Set the number of concurrent connections per file (2-{MAX_PARTS}).")
|
||||
parts_layout.addWidget(self.parts_label)
|
||||
parts_layout.addStretch()
|
||||
parts_layout.addWidget(self.parts_input)
|
||||
settings_layout.addLayout(parts_layout)
|
||||
|
||||
# Layout for Minimum Size
|
||||
size_layout = QHBoxLayout()
|
||||
self.size_label = QLabel("Minimum file size for multipart (MB):")
|
||||
self.size_input = QLineEdit(str(current_min_size_mb))
|
||||
self.size_input.setValidator(QIntValidator(10, 10000, self)) # Min 10MB, Max ~10GB
|
||||
self.size_input.setFixedWidth(40)
|
||||
self.size_input.setToolTip("Files smaller than this will use a normal, single-part download.")
|
||||
size_layout.addWidget(self.size_label)
|
||||
size_layout.addStretch()
|
||||
size_layout.addWidget(self.size_input)
|
||||
settings_layout.addLayout(size_layout)
|
||||
|
||||
self.settings_group_box.setLayout(settings_layout)
|
||||
layout.addWidget(self.settings_group_box)
|
||||
# --- END: MODIFIED Download Settings Group ---
|
||||
|
||||
# OK and Cancel Buttons
|
||||
self.button_box = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel)
|
||||
self.button_box.accepted.connect(self.accept)
|
||||
self.button_box.rejected.connect(self.reject)
|
||||
layout.addWidget(self.button_box)
|
||||
|
||||
self.setLayout(layout)
|
||||
|
||||
def get_selected_scope(self):
|
||||
# ... (This method remains unchanged) ...
|
||||
if self.radio_videos.isChecked():
|
||||
return self.SCOPE_VIDEOS
|
||||
if self.radio_archives.isChecked():
|
||||
return self.SCOPE_ARCHIVES
|
||||
return self.SCOPE_BOTH
|
||||
|
||||
def get_selected_parts(self):
|
||||
# ... (This method remains unchanged) ...
|
||||
try:
|
||||
parts = int(self.parts_input.text())
|
||||
return max(2, min(parts, MAX_PARTS))
|
||||
except (ValueError, TypeError):
|
||||
return 4
|
||||
|
||||
def get_selected_min_size(self):
|
||||
"""Returns the selected minimum size in MB as an integer."""
|
||||
try:
|
||||
size = int(self.size_input.text())
|
||||
return max(10, min(size, 10000)) # Enforce valid range
|
||||
except (ValueError, TypeError):
|
||||
return 100 # Return a safe default
|
||||
@@ -3,8 +3,27 @@ import re
|
||||
try:
|
||||
from fpdf import FPDF
|
||||
FPDF_AVAILABLE = True
|
||||
|
||||
# --- FIX: Move the class definition inside the try block ---
|
||||
class PDF(FPDF):
|
||||
"""Custom PDF class to handle headers and footers."""
|
||||
def header(self):
|
||||
pass
|
||||
|
||||
def footer(self):
|
||||
self.set_y(-15)
|
||||
if self.font_family:
|
||||
self.set_font(self.font_family, '', 8)
|
||||
else:
|
||||
self.set_font('Arial', '', 8)
|
||||
self.cell(0, 10, 'Page ' + str(self.page_no()), 0, 0, 'C')
|
||||
|
||||
except ImportError:
|
||||
FPDF_AVAILABLE = False
|
||||
# If the import fails, FPDF and PDF will not be defined,
|
||||
# but the program won't crash here.
|
||||
FPDF = None
|
||||
PDF = None
|
||||
|
||||
def strip_html_tags(text):
|
||||
if not text:
|
||||
@@ -12,19 +31,6 @@ def strip_html_tags(text):
|
||||
clean = re.compile('<.*?>')
|
||||
return re.sub(clean, '', text)
|
||||
|
||||
class PDF(FPDF):
|
||||
"""Custom PDF class to handle headers and footers."""
|
||||
def header(self):
|
||||
pass
|
||||
|
||||
def footer(self):
|
||||
self.set_y(-15)
|
||||
if self.font_family:
|
||||
self.set_font(self.font_family, '', 8)
|
||||
else:
|
||||
self.set_font('Arial', '', 8)
|
||||
self.cell(0, 10, 'Page ' + str(self.page_no()), 0, 0, 'C')
|
||||
|
||||
def create_single_pdf_from_content(posts_data, output_filename, font_path, logger=print):
|
||||
"""
|
||||
Creates a single, continuous PDF, correctly formatting both descriptions and comments.
|
||||
@@ -68,7 +74,7 @@ def create_single_pdf_from_content(posts_data, output_filename, font_path, logge
|
||||
pdf.ln(10)
|
||||
|
||||
pdf.set_font(default_font_family, 'B', 16)
|
||||
pdf.multi_cell(w=0, h=10, text=post.get('title', 'Untitled Post'), align='L')
|
||||
pdf.multi_cell(w=0, h=10, txt=post.get('title', 'Untitled Post'), align='L')
|
||||
pdf.ln(5)
|
||||
|
||||
if 'comments' in post and post['comments']:
|
||||
@@ -89,7 +95,7 @@ def create_single_pdf_from_content(posts_data, output_filename, font_path, logge
|
||||
pdf.ln(10)
|
||||
|
||||
pdf.set_font(default_font_family, '', 11)
|
||||
pdf.multi_cell(0, 7, body)
|
||||
pdf.multi_cell(w=0, h=7, txt=body)
|
||||
|
||||
if comment_index < len(comments_list) - 1:
|
||||
pdf.ln(3)
|
||||
@@ -97,7 +103,7 @@ def create_single_pdf_from_content(posts_data, output_filename, font_path, logge
|
||||
pdf.ln(3)
|
||||
elif 'content' in post:
|
||||
pdf.set_font(default_font_family, '', 12)
|
||||
pdf.multi_cell(w=0, h=7, text=post.get('content', 'No Content'))
|
||||
pdf.multi_cell(w=0, h=7, txt=post.get('content', 'No Content'))
|
||||
|
||||
try:
|
||||
pdf.output(output_filename)
|
||||
@@ -105,4 +111,4 @@ def create_single_pdf_from_content(posts_data, output_filename, font_path, logge
|
||||
return True
|
||||
except Exception as e:
|
||||
logger(f"❌ A critical error occurred while saving the final PDF: {e}")
|
||||
return False
|
||||
return False
|
||||
|
||||
160
src/ui/dialogs/discord_pdf_generator.py
Normal file
160
src/ui/dialogs/discord_pdf_generator.py
Normal file
@@ -0,0 +1,160 @@
|
||||
import os
|
||||
import re
|
||||
import datetime
|
||||
import time
|
||||
try:
|
||||
from fpdf import FPDF
|
||||
FPDF_AVAILABLE = True
|
||||
|
||||
class PDF(FPDF):
|
||||
"""Custom PDF class for Discord chat logs."""
|
||||
def __init__(self, server_name, channel_name, *args, **kwargs):
|
||||
super().__init__(*args, **kwargs)
|
||||
self.server_name = server_name
|
||||
self.channel_name = channel_name
|
||||
self.default_font_family = 'DejaVu' # Can be changed to Arial if font fails
|
||||
|
||||
def header(self):
|
||||
if self.page_no() == 1:
|
||||
return # No header on the title page
|
||||
self.set_font(self.default_font_family, '', 8)
|
||||
self.cell(0, 10, f'{self.server_name} - #{self.channel_name}', 0, 0, 'L')
|
||||
self.cell(0, 10, 'Page ' + str(self.page_no()), 0, 0, 'R')
|
||||
self.ln(10)
|
||||
|
||||
def footer(self):
|
||||
pass # No footer needed, header has page number
|
||||
|
||||
except ImportError:
|
||||
FPDF_AVAILABLE = False
|
||||
FPDF = None
|
||||
PDF = None
|
||||
|
||||
def create_pdf_from_discord_messages(messages_data, server_name, channel_name, output_filename, font_path, logger=print, cancellation_event=None, pause_event=None):
|
||||
"""
|
||||
Creates a single PDF from a list of Discord message objects, formatted as a chat log.
|
||||
UPDATED to include clickable links for attachments and embeds.
|
||||
"""
|
||||
if not FPDF_AVAILABLE:
|
||||
logger("❌ PDF Creation failed: 'fpdf2' library is not installed.")
|
||||
return False
|
||||
|
||||
if not messages_data:
|
||||
logger(" No messages were found or fetched to create a PDF.")
|
||||
return False
|
||||
|
||||
# --- FIX: This helper function now correctly accepts and checks the event objects ---
|
||||
def check_events(c_event, p_event):
|
||||
"""Helper to safely check for pause and cancel events."""
|
||||
if c_event and hasattr(c_event, 'is_cancelled') and c_event.is_cancelled:
|
||||
return True # Stop
|
||||
if p_event and hasattr(p_event, 'is_paused'):
|
||||
while p_event.is_paused:
|
||||
time.sleep(0.5)
|
||||
if c_event and hasattr(c_event, 'is_cancelled') and c_event.is_cancelled:
|
||||
return True
|
||||
return False
|
||||
|
||||
logger(" Sorting messages by date (oldest first)...")
|
||||
messages_data.sort(key=lambda m: m.get('published', m.get('timestamp', '')))
|
||||
|
||||
pdf = PDF(server_name, channel_name)
|
||||
default_font_family = 'DejaVu'
|
||||
|
||||
try:
|
||||
bold_font_path = font_path.replace("DejaVuSans.ttf", "DejaVuSans-Bold.ttf")
|
||||
if not os.path.exists(font_path) or not os.path.exists(bold_font_path):
|
||||
raise RuntimeError("Font files not found")
|
||||
|
||||
pdf.add_font('DejaVu', '', font_path, uni=True)
|
||||
pdf.add_font('DejaVu', 'B', bold_font_path, uni=True)
|
||||
except Exception as font_error:
|
||||
logger(f" ⚠️ Could not load DejaVu font: {font_error}. Falling back to Arial.")
|
||||
default_font_family = 'Arial'
|
||||
pdf.default_font_family = 'Arial'
|
||||
|
||||
# --- Title Page ---
|
||||
pdf.add_page()
|
||||
pdf.set_font(default_font_family, 'B', 24)
|
||||
pdf.cell(w=0, h=20, text="Discord Chat Log", align='C', new_x="LMARGIN", new_y="NEXT")
|
||||
pdf.ln(10)
|
||||
pdf.set_font(default_font_family, '', 16)
|
||||
pdf.cell(w=0, h=10, text=f"Server: {server_name}", align='C', new_x="LMARGIN", new_y="NEXT")
|
||||
pdf.cell(w=0, h=10, text=f"Channel: #{channel_name}", align='C', new_x="LMARGIN", new_y="NEXT")
|
||||
pdf.ln(5)
|
||||
pdf.set_font(default_font_family, '', 10)
|
||||
pdf.cell(w=0, h=10, text=f"Generated on: {datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')}", align='C', new_x="LMARGIN", new_y="NEXT")
|
||||
pdf.cell(w=0, h=10, text=f"Total Messages: {len(messages_data)}", align='C', new_x="LMARGIN", new_y="NEXT")
|
||||
|
||||
pdf.add_page()
|
||||
|
||||
logger(f" Starting PDF creation with {len(messages_data)} messages...")
|
||||
|
||||
for i, message in enumerate(messages_data):
|
||||
# --- FIX: Pass the event objects to the helper function ---
|
||||
if i % 50 == 0:
|
||||
if check_events(cancellation_event, pause_event):
|
||||
logger(" PDF generation cancelled by user.")
|
||||
return False
|
||||
|
||||
author = message.get('author', {}).get('global_name') or message.get('author', {}).get('username', 'Unknown User')
|
||||
timestamp_str = message.get('published', message.get('timestamp', ''))
|
||||
content = message.get('content', '')
|
||||
attachments = message.get('attachments', [])
|
||||
embeds = message.get('embeds', [])
|
||||
|
||||
try:
|
||||
if timestamp_str.endswith('Z'):
|
||||
timestamp_str = timestamp_str[:-1] + '+00:00'
|
||||
dt_obj = datetime.datetime.fromisoformat(timestamp_str)
|
||||
formatted_timestamp = dt_obj.strftime('%Y-%m-%d %H:%M:%S')
|
||||
except (ValueError, TypeError):
|
||||
formatted_timestamp = timestamp_str
|
||||
|
||||
if i > 0:
|
||||
pdf.ln(2)
|
||||
pdf.set_draw_color(200, 200, 200)
|
||||
pdf.cell(0, 0, '', border='T')
|
||||
pdf.ln(2)
|
||||
|
||||
pdf.set_font(default_font_family, 'B', 11)
|
||||
pdf.write(5, f"{author} ")
|
||||
pdf.set_font(default_font_family, '', 9)
|
||||
pdf.set_text_color(128, 128, 128)
|
||||
pdf.write(5, f"({formatted_timestamp})")
|
||||
pdf.set_text_color(0, 0, 0)
|
||||
pdf.ln(6)
|
||||
|
||||
if content:
|
||||
pdf.set_font(default_font_family, '', 10)
|
||||
pdf.multi_cell(w=0, h=5, text=content)
|
||||
|
||||
if attachments or embeds:
|
||||
pdf.ln(1)
|
||||
pdf.set_font(default_font_family, '', 9)
|
||||
pdf.set_text_color(22, 119, 219)
|
||||
|
||||
for att in attachments:
|
||||
file_name = att.get('filename', 'untitled')
|
||||
full_url = att.get('url', '#')
|
||||
pdf.write(5, text=f"[Attachment: {file_name}]", link=full_url)
|
||||
pdf.ln()
|
||||
|
||||
for embed in embeds:
|
||||
embed_url = embed.get('url', 'no url')
|
||||
pdf.write(5, text=f"[Embed: {embed_url}]", link=embed_url)
|
||||
pdf.ln()
|
||||
|
||||
pdf.set_text_color(0, 0, 0)
|
||||
|
||||
if check_events(cancellation_event, pause_event):
|
||||
logger(" PDF generation cancelled by user before final save.")
|
||||
return False
|
||||
|
||||
try:
|
||||
pdf.output(output_filename)
|
||||
logger(f"✅ Successfully created Discord chat log PDF: '{os.path.basename(output_filename)}'")
|
||||
return True
|
||||
except Exception as e:
|
||||
logger(f"❌ A critical error occurred while saving the final PDF: {e}")
|
||||
return False
|
||||
File diff suppressed because it is too large
Load Diff
@@ -141,28 +141,51 @@ def prepare_cookies_for_request(use_cookie_flag, cookie_text_input, selected_coo
|
||||
def extract_post_info(url_string):
|
||||
"""
|
||||
Parses a URL string to extract the service, user ID, and post ID.
|
||||
|
||||
Args:
|
||||
url_string (str): The URL to parse.
|
||||
|
||||
Returns:
|
||||
tuple: A tuple containing (service, user_id, post_id). Any can be None.
|
||||
UPDATED to support Hentai2Read series and chapters.
|
||||
"""
|
||||
if not isinstance(url_string, str) or not url_string.strip():
|
||||
return None, None, None
|
||||
|
||||
stripped_url = url_string.strip()
|
||||
|
||||
# --- Bunkr Check ---
|
||||
bunkr_pattern = re.compile(
|
||||
r"(?:https?://)?(?:[a-zA-Z0-9-]+\.)?bunkr\.(?:si|la|ws|red|black|media|site|is|to|ac|cr|ci|fi|pk|ps|sk|ph|su|ru)|bunkrr\.ru"
|
||||
)
|
||||
if bunkr_pattern.search(stripped_url):
|
||||
return 'bunkr', stripped_url, None
|
||||
|
||||
# --- nhentai Check ---
|
||||
nhentai_match = re.search(r'nhentai\.net/g/(\d+)', stripped_url)
|
||||
if nhentai_match:
|
||||
return 'nhentai', nhentai_match.group(1), None
|
||||
|
||||
# --- Hentai2Read Check (Updated) ---
|
||||
# This regex now captures the manga slug (id1) and optionally the chapter number (id2)
|
||||
hentai2read_match = re.search(r'hentai2read\.com/([^/]+)(?:/(\d+))?/?', stripped_url)
|
||||
if hentai2read_match:
|
||||
manga_slug, chapter_num = hentai2read_match.groups()
|
||||
return 'hentai2read', manga_slug, chapter_num # chapter_num will be None for series URLs
|
||||
|
||||
discord_channel_match = re.search(r'discord\.com/channels/(@me|\d+)/(\d+)', stripped_url)
|
||||
if discord_channel_match:
|
||||
server_id, channel_id = discord_channel_match.groups()
|
||||
return 'discord', server_id, channel_id
|
||||
|
||||
# --- Kemono/Coomer/Discord Parsing ---
|
||||
try:
|
||||
parsed_url = urlparse(url_string.strip())
|
||||
parsed_url = urlparse(stripped_url)
|
||||
path_parts = [part for part in parsed_url.path.strip('/').split('/') if part]
|
||||
|
||||
# Standard format: /<service>/user/<user_id>/post/<post_id>
|
||||
|
||||
if len(path_parts) >= 3 and path_parts[0].lower() == 'discord' and path_parts[1].lower() == 'server':
|
||||
return 'discord', path_parts[2], path_parts[3] if len(path_parts) >= 4 else None
|
||||
|
||||
if len(path_parts) >= 3 and path_parts[1].lower() == 'user':
|
||||
service = path_parts[0]
|
||||
user_id = path_parts[2]
|
||||
post_id = path_parts[4] if len(path_parts) >= 5 and path_parts[3].lower() == 'post' else None
|
||||
return service, user_id, post_id
|
||||
|
||||
# API format: /api/v1/<service>/user/<user_id>...
|
||||
|
||||
if len(path_parts) >= 5 and path_parts[0:2] == ['api', 'v1'] and path_parts[3].lower() == 'user':
|
||||
service = path_parts[2]
|
||||
user_id = path_parts[4]
|
||||
@@ -173,8 +196,7 @@ def extract_post_info(url_string):
|
||||
print(f"Debug: Exception during URL parsing for '{url_string}': {e}")
|
||||
|
||||
return None, None, None
|
||||
|
||||
|
||||
|
||||
def get_link_platform(url):
|
||||
"""
|
||||
Identifies the platform of a given URL based on its domain.
|
||||
@@ -196,10 +218,9 @@ def get_link_platform(url):
|
||||
if 'twitter.com' in domain or 'x.com' in domain: return 'twitter/x'
|
||||
if 'discord.gg' in domain or 'discord.com/invite' in domain: return 'discord invite'
|
||||
if 'pixiv.net' in domain: return 'pixiv'
|
||||
if 'kemono.su' in domain or 'kemono.party' in domain: return 'kemono'
|
||||
if 'coomer.su' in domain or 'coomer.party' in domain: return 'coomer'
|
||||
if 'kemono.su' in domain or 'kemono.party' in domain or 'kemono.cr' in domain: return 'kemono'
|
||||
if 'coomer.su' in domain or 'coomer.party' in domain or 'coomer.st' in domain: return 'coomer'
|
||||
|
||||
# Fallback to a generic name for other domains
|
||||
parts = domain.split('.')
|
||||
if len(parts) >= 2:
|
||||
return parts[-2]
|
||||
|
||||
@@ -284,7 +284,7 @@ def setup_ui(main_app):
|
||||
advanced_row2_layout.addLayout(multithreading_layout)
|
||||
main_app.external_links_checkbox = QCheckBox("Show External Links in Log")
|
||||
advanced_row2_layout.addWidget(main_app.external_links_checkbox)
|
||||
main_app.manga_mode_checkbox = QCheckBox("Manga/Comic Mode")
|
||||
main_app.manga_mode_checkbox = QCheckBox("Renaming Mode")
|
||||
advanced_row2_layout.addWidget(main_app.manga_mode_checkbox)
|
||||
advanced_row2_layout.addStretch(1)
|
||||
checkboxes_group_layout.addLayout(advanced_row2_layout)
|
||||
@@ -391,6 +391,23 @@ def setup_ui(main_app):
|
||||
main_app.link_search_button.setVisible(False)
|
||||
main_app.link_search_button.setFixedWidth(int(30 * scale))
|
||||
log_title_layout.addWidget(main_app.link_search_button)
|
||||
|
||||
discord_controls_layout = QHBoxLayout()
|
||||
|
||||
main_app.discord_scope_toggle_button = QPushButton("Scope: Files")
|
||||
main_app.discord_scope_toggle_button.setVisible(False) # Hidden by default
|
||||
discord_controls_layout.addWidget(main_app.discord_scope_toggle_button)
|
||||
|
||||
main_app.discord_message_limit_input = QLineEdit(main_app)
|
||||
main_app.discord_message_limit_input.setPlaceholderText("Msg Limit")
|
||||
main_app.discord_message_limit_input.setToolTip("Optional: Limit the number of recent messages to process.")
|
||||
main_app.discord_message_limit_input.setValidator(QIntValidator(1, 9999999, main_app))
|
||||
main_app.discord_message_limit_input.setFixedWidth(int(80 * scale))
|
||||
main_app.discord_message_limit_input.setVisible(False) # Hide it by default
|
||||
discord_controls_layout.addWidget(main_app.discord_message_limit_input)
|
||||
|
||||
log_title_layout.addLayout(discord_controls_layout)
|
||||
|
||||
main_app.manga_rename_toggle_button = QPushButton()
|
||||
main_app.manga_rename_toggle_button.setVisible(False)
|
||||
main_app.manga_rename_toggle_button.setFixedWidth(int(140 * scale))
|
||||
|
||||
Reference in New Issue
Block a user