readme.md

Known.txt

@@ -1,197 +1 @@
-Ada
-Aeris
-Alina
-Amara
-Anya
-Aria
-Artemis
-Ashe
-Astrid
-Asuka
-Athena
-Azura
-Belladonna
-Bianca
-C.C.
-Calla
-Camilla
-Cassia
-Celeste
-Chika
-Clara
-Delilah
-Dia
-Diana
-Eira
-Elara
-Eli
-Elise
-Elma
-Ember
-Erza
-Esme
-Evelyn
-Evie
-Fiora
-Freya
-Gasai
-Greta
-Hanayo
-Hancock
-Haruhi
-Hatsume
-Hawkeye
-Hinata
-Holo
-Homura
-Ichigo
-Illya
-Inara
-Ino
-Isla
-Isolde
-Ivy
-Jeanne
-Jinx
-Jiro
-Juniper
-Juvia
-Kaelin
-Kagome
-Kagura
-Kaida
-Kairi
-Kali
-Kana
-Kanao
-Kanna
-Kiera
-Kikyo
-Kirari
-Korra
-Kotori
-Kurisu
-Kushina
-Kyoko
-Lan Fan
-Leona
-Levy
-Lilith
-Liora
-Lira
-Lisanna
-Lucia
-Lucoa
-Lucy
-Luna
-Lust
-Lyra
-Madoka
-Maia
-Makima
-Makise
-Makomo
-Mami
-Mari
-Marin
-Mary
-Mavis
-Mayuri
-Medusa
-Mei
-Merlin
-Mikasa
-Milly
-Mina
-Mion
-Mira
-Mirabel
-Misato
-Mitsuri
-Momo
-Morgana
-Nadia
-Nami
-Naomi
-Nelliel
-Nerissa
-Neve
-Nezuko
-Noelle
-Nova
-Nozomi
-Nunnally
-Nyx
-Ochaco
-Odette
-Ophelia
-Orihime
-Orla
-Perona
-Phoebe
-Raven
-Rei
-Reyna
-Rhea
-Rika
-Rin
-Rin Tohsaka
-Rinoa
-Ritsuko
-Riza
-Robin
-Rosalie
-Rowan
-Ruby
-Rukia
-Rumi
-Saber
-Sable
-Sakura
-Sakura Matou
-Sango
-Sansa
-Satoko
-Sayaka
-Scáthach
-Selene
-Seline
-Serena
-Shinobu
-Shion
-Shirley
-Sierra
-Skye
-Sophie
-Soraya
-Sylvia
-Talia
-Tamayo
-Tamsin
-Tashigi
-Tatiana
-Temari
-Thalia
-Tifa
-Toga
-Tohru
-Tsunade
-Umi
-Valeria
-Viola
-Violet
-Vivi
-Wendy
-Winry
-Wynne
-Yara
-Yazawa
-Yoruichi
-Yoshiko
-Yuki Nagato
-Yumeko
-Yuna
-Yuno
-Zara
-Zelda
-Zero Two
+([Yor], Yor Briar, Yor Forger)

multipart_downloader.py

@@ -0,0 +1,238 @@
+import os
+import time
+import requests
+import hashlib
+import http.client
+import traceback
+import threading
+from concurrent.futures import ThreadPoolExecutor, as_completed
+
+CHUNK_DOWNLOAD_RETRY_DELAY = 2 # Slightly reduced for faster retries if needed
+MAX_CHUNK_DOWNLOAD_RETRIES = 1 # Further reduced for quicker fallback if a chunk is problematic
+DOWNLOAD_CHUNK_SIZE_ITER = 1024 * 256  # 256KB for iter_content within a chunk download
+
+
+def _download_individual_chunk(chunk_url, 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, # Added cookies_for_chunk
+                               logger_func, emitter=None, api_original_filename=None): # Renamed logger, signals to emitter
+    """Downloads a single chunk of a file and writes it to the temp file."""
+    if cancellation_event and cancellation_event.is_set():
+        logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Download cancelled before start.")
+        return 0, False  # bytes_downloaded, success
+    if skip_event and skip_event.is_set():
+        logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Skip event triggered before start.")
+        return 0, False
+
+    if pause_event and pause_event.is_set():
+        logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Download paused before start...")
+        while pause_event.is_set():
+            if cancellation_event and cancellation_event.is_set():
+                logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Download cancelled while paused.")
+                return 0, False
+            time.sleep(0.2) # Shorter sleep for responsive resume
+        logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Download resumed.")
+
+    chunk_headers = headers.copy()
+    if end_byte != -1 : # For 0-byte files, end_byte might be -1, Range header should not be set or be 0-0
+        chunk_headers['Range'] = f"bytes={start_byte}-{end_byte}"
+    elif start_byte == 0 and end_byte == -1: # Specifically for 0-byte files
+        pass
+
+
+    bytes_this_chunk = 0
+    last_speed_calc_time = time.time()
+    bytes_at_last_speed_calc = 0
+
+    for attempt in range(MAX_CHUNK_DOWNLOAD_RETRIES + 1):
+        if cancellation_event and cancellation_event.is_set():
+            logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Cancelled during retry loop.")
+            return bytes_this_chunk, False
+        if skip_event and skip_event.is_set():
+            logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Skip event during retry loop.")
+            return bytes_this_chunk, False
+        if pause_event and pause_event.is_set():
+            logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Paused during retry loop...")
+            while pause_event.is_set():
+                if cancellation_event and cancellation_event.is_set():
+                    logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Cancelled while paused in retry loop.")
+                    return bytes_this_chunk, False
+                time.sleep(0.2)
+            logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Resumed from retry loop pause.")
+
+        try:
+            if attempt > 0:
+                logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Retrying download (Attempt {attempt}/{MAX_CHUNK_DOWNLOAD_RETRIES})...")
+                time.sleep(CHUNK_DOWNLOAD_RETRY_DELAY * (2 ** (attempt - 1)))
+                last_speed_calc_time = time.time()
+                bytes_at_last_speed_calc = bytes_this_chunk # Current progress of this chunk
+            log_msg = f"   🚀 [Chunk {part_num + 1}/{total_parts}] Starting download: bytes {start_byte}-{end_byte if end_byte != -1 else 'EOF'}"
+            logger_func(log_msg)
+            response = requests.get(chunk_url, headers=chunk_headers, timeout=(10, 120), stream=True, cookies=cookies_for_chunk)
+            response.raise_for_status()
+            if start_byte == 0 and end_byte == -1 and int(response.headers.get('Content-Length', 0)) == 0:
+                logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Confirmed 0-byte file.")
+                with progress_data['lock']:
+                    progress_data['chunks_status'][part_num]['active'] = False
+                    progress_data['chunks_status'][part_num]['speed_bps'] = 0
+                return 0, True
+
+            with open(temp_file_path, 'r+b') as f:  # Open in read-write binary
+                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():
+                        logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Cancelled during data iteration.")
+                        return bytes_this_chunk, False
+                    if skip_event and skip_event.is_set():
+                        logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Skip event during data iteration.")
+                        return bytes_this_chunk, False
+                    if pause_event and pause_event.is_set():
+                        logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Paused during data iteration...")
+                        while pause_event.is_set():
+                            if cancellation_event and cancellation_event.is_set():
+                                logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Cancelled while paused in data iteration.")
+                                return bytes_this_chunk, False
+                            time.sleep(0.2)
+                        logger_func(f"   [Chunk {part_num + 1}/{total_parts}] Resumed from data iteration pause.")
+                    if data_segment:
+                        f.write(data_segment)
+                        bytes_this_chunk += len(data_segment)
+                        
+                        with progress_data['lock']:
+                            progress_data['total_downloaded_so_far'] += len(data_segment)
+                            progress_data['chunks_status'][part_num]['downloaded'] = bytes_this_chunk
+                            progress_data['chunks_status'][part_num]['active'] = True
+
+                            current_time = time.time()
+                            time_delta_speed = current_time - last_speed_calc_time
+                            if time_delta_speed > 0.5: # Calculate speed every 0.5 seconds
+                                bytes_delta = bytes_this_chunk - bytes_at_last_speed_calc
+                                current_speed_bps = (bytes_delta * 8) / time_delta_speed if time_delta_speed > 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                            
+                            if emitter and (current_time - global_emit_time_ref[0] > 0.25): # Max ~4Hz for the whole file
+                                global_emit_time_ref[0] = current_time # Update shared last emit time
+                                status_list_copy = [dict(s) for s in progress_data['chunks_status']] # Make a deep enough copy
+                                if isinstance(emitter, queue.Queue):
+                                    emitter.put({'type': 'file_progress', 'payload': (api_original_filename, status_list_copy)})
+                                elif hasattr(emitter, 'file_progress_signal'): # PostProcessorSignals-like
+                                    emitter.file_progress_signal.emit(api_original_filename, status_list_copy)
+            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}")
+            if attempt == MAX_CHUNK_DOWNLOAD_RETRIES:
+                logger_func(f"   ❌ [Chunk {part_num + 1}/{total_parts}] Failed after {MAX_CHUNK_DOWNLOAD_RETRIES} retries.")
+                return bytes_this_chunk, False
+        except requests.exceptions.RequestException as e: # Includes 4xx/5xx errors after raise_for_status
+            logger_func(f"   ❌ [Chunk {part_num + 1}/{total_parts}] Non-retryable error: {e}")
+            return bytes_this_chunk, False
+        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
+    with progress_data['lock']:
+        progress_data['chunks_status'][part_num]['active'] = False
+        progress_data['chunks_status'][part_num]['speed_bps'] = 0
+    return bytes_this_chunk, False # Should be unreachable
+
+
+def download_file_in_parts(file_url, save_path, total_size, num_parts, headers, api_original_filename,
+                           emitter_for_multipart, cookies_for_chunk_session, # Added cookies_for_chunk_session
+                           cancellation_event, skip_event, logger_func, pause_event):
+    """
+    Downloads a file in multiple parts concurrently.
+    Returns: (download_successful_flag, downloaded_bytes, calculated_file_hash, temp_file_handle_or_None)
+    The temp_file_handle will be an open read-binary file handle to the .part file if successful, otherwise None.
+    It is the responsibility of the caller to close this handle and rename/delete the .part file.
+    """
+    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"
+
+    try:
+        with open(temp_file_path, 'wb') as f_temp:
+            if total_size > 0:
+                f_temp.truncate(total_size) # Pre-allocate space
+    except IOError as e:
+        logger_func(f"   ❌ Error creating/truncating temp file '{temp_file_path}': {e}")
+        return False, 0, None, None
+
+    chunk_size_calc = total_size // num_parts
+    chunks_ranges = []
+    for i in range(num_parts):
+        start = i * chunk_size_calc
+        end = start + chunk_size_calc - 1 if i < num_parts - 1 else total_size - 1
+        if start <= end: # Valid range
+            chunks_ranges.append((start, end))
+        elif total_size == 0 and i == 0: # Special case for 0-byte file
+            chunks_ranges.append((0, -1)) # Indicates 0-byte file, download 0 bytes from offset 0
+
+    chunk_actual_sizes = [] 
+    for start, end in chunks_ranges:
+        if end == -1 and start == 0: # 0-byte file
+            chunk_actual_sizes.append(0)
+        else:
+            chunk_actual_sizes.append(end - start + 1)
+
+    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)
+        return False, 0, None, None
+
+    progress_data = {
+        'total_file_size': total_size, # Overall file size for reference
+        'total_downloaded_so_far': 0,  # New key for overall progress
+        'chunks_status': [ # Status for each chunk
+            {'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)
+        ],
+        'lock': threading.Lock(),
+        'last_global_emit_time': [time.time()] # Shared mutable for global throttling timestamp
+    }
+
+    chunk_futures = []
+    all_chunks_successful = True
+    total_bytes_from_chunks = 0 # Still useful to verify total downloaded against file size
+
+    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,
+                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,
+                api_original_filename=api_original_filename
+            ))
+
+        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:
+                all_chunks_successful = False
+
+    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'): # PostProcessorSignals-like
+                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}")
+        md5_hasher = hashlib.md5()
+        with open(temp_file_path, 'rb') as f_hash:
+            for buf in iter(lambda: f_hash.read(4096*10), b''): # Read in larger buffers for hashing
+                md5_hasher.update(buf)
+        calculated_hash = md5_hasher.hexdigest()
+        return True, total_bytes_from_chunks, calculated_hash, open(temp_file_path, 'rb')
+    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

readme.md

@@ -1,105 +1,313 @@
-# Kemono Downloader v3.1.0
+<h1 align="center">Kemono Downloader v4.0.0</h1>
 
-A feature-rich GUI application built with PyQt5 to download content from [Kemono.su](https://kemono.su) or [Coomer.party](https://coomer.party). Offers robust filtering, smart organization, manga-specific handling, and performance tuning. Now with session resuming, better retry logic, and smarter file management.
+<div align="center">
+  <img src="https://github.com/Yuvi9587/Kemono-Downloader/blob/main/Read.png" alt="Kemono Downloader"/>
+</div>
 
 ---
 
-## 🚀 What's New in v3.1.0
-
-* **Session Resuming**  
-  * Automatically saves and resumes incomplete downloads.  
-
-* **Retry on Failure**  
-  * Failed files auto-retry up to 3 times.  
-  * Clear logging for each retry attempt.
-
-* **Batch URL Import**  
-  * Load multiple creator or post URLs from a `.txt` file.  
-
-* **Improved Manga Mode**  
-  * Better post ordering and handling of missing or untitled posts.  
-  * Optional numeric-only sorting for consistent naming.
-
-* **UI Enhancements**  
-  * Settings persist across sessions.  
-  * Improved layout spacing, tooltips, and status indicators.
-
-* **Stability & Speed**  
-  * Faster post fetching with lower memory usage.  
-  * Minor bug fixes (duplicate folders, empty post crashes).
+A powerful, feature-rich GUI application for downloading content from **[Kemono.su](https://kemono.su)** and **[Coomer.party](https://coomer.party)**.  
+Built with **PyQt5**, this tool is ideal for users who want deep filtering, customizable folder structures, efficient downloads, and intelligent automation — all within a modern, user-friendly graphical interface.
 
 ---
 
-## 🧩 Core Features
+##  What's New in v4.0.0?
 
-* **Simple GUI**  
-  Built with PyQt5 for a clean, responsive experience.
+Version 3.5.0 focuses on enhancing access to content and providing even smarter organization:
 
-* **Supports Both Post and Creator URLs**  
-  Download a single post or an entire feed with one click.
+###  Cookie Management
 
-* **Smart Folder System**  
-  Organize files using post titles, known character/show names, or a folder per post.  
-  Detects and auto-names folders based on custom keywords.
-
-* **Known Names Manager**  
-  Add, search, and delete tags for smarter organization.  
-  Saved to `Known.txt` for reuse.
-
-* **Advanced Filters**  
-  * Skip posts or files with specific keywords (e.g. `WIP`, `sketch`).  
-  * Filter by media type: images, videos, or GIFs.  
-  * Skip `.zip` and `.rar` archives.  
-
-* **Manga Mode**  
-  Rename and sort manga posts by title and upload order.  
-  Handles one-image-per-post formats cleanly.
-
-* **Image Compression**  
-  Auto-convert large images (>1.5MB) to WebP (requires Pillow).
-
-* **Multithreaded Downloads**  
-  Adjustable worker count with warnings at unsafe levels.  
-  Full threading for creators, single-thread fallback for post mode.
-
-* **Download Controls**  
-  Cancel, pause, or skip files mid-download.  
-  Visual progress tracking with per-post summaries.
-
-* **Dark Mode**  
-  Clean and modern dark-themed interface.
+- **Access Content:** Seamlessly download from Kemono/Coomer as if you were logged in by using your browser's cookies.
+- **Flexible Input:**
+  - Directly paste your cookie string (e.g., `name1=value1; name2=value2`).
+  - Browse and load cookies from a `cookies.txt` file (Netscape format).
+  - Automatic fallback to a `cookies.txt` file in the application directory if "Use Cookie" is enabled and no other source is specified.
+- **Easy Activation:** A simple "Use Cookie" checkbox in the UI controls this feature.
+- *Important Note: Cookie settings (text, file path, and enabled state) are configured per session and are not saved when the application is closed. You will need to re-apply them on each launch if needed.*
 
 ---
 
-## 🔧 Backend Enhancements
+###  Advanced `Known.txt` and Character Filtering
 
-* **Session File Support**  
-  Downloads can be resumed even after a crash or restart.  
-  Session progress is saved automatically.
+The `Known.txt` system has been revamped for improved performance and stability. The previous method of handling known names could become resource-intensive with large lists, potentially leading to application slowdowns or crashes. This new, streamlined system offers more direct control and robust organization.
+The `Known.txt` file and the "Filter by Character(s)" input field work together to provide powerful and flexible content organization. The `Known.txt` file itself has a straightforward syntax, while the UI input allows for more complex session-specific grouping and alias definitions that can then be added to `Known.txt`.
 
-* **Retry Logic**  
-  Auto-retries individual failed files before skipping.  
-  Logs all failures with HTTP codes and reasons.
+**1. `Known.txt` File Syntax (Located in App Directory):**
 
-* **Hash-Based Deduplication**  
-  Prevents redownloading of previously saved files.
+`Known.txt` stores your persistent list of characters, series, or keywords for folder organization. Each line is an entry:
 
-* **Smart Naming**  
-  Cleans and standardizes inconsistent post titles.  
-  Adds page indices for manga.
+- **Simple Entries:**
+  - A line like `My Awesome Series` or `Nami`.
+  - **Behavior:** Content matching this term will be saved into a folder named "My Awesome Series" or "Nami" respectively (if "Separate Folders" is enabled).
 
-* **Efficient Logging**  
-  Toggle between basic and advanced views.  
-  Live feedback with color-coded logs.
+**2. "Filter by Character(s)" UI Input Field:**
+
+This field allows for dynamic filtering for the current download session and provides options for how new entries are added to `Known.txt`.
+
+- **Standard Names:**
+  - Input: `Nami, Robin`
+  - Session Behavior: Filters for "Nami" OR "Robin". If "Separate Folders" is on, creates folders "Nami" and "Robin".
+  - `Known.txt` Addition: If "Nami" is new and selected for addition in the confirmation dialog, it's added as `Nami` on a new line in `Known.txt`.
+
+- **Grouped Aliases for a Single Character (using `(...)~` syntax):**
+  - Input: `(Boa, Hancock)~`
+  - Meaning: "Boa" and "Hancock" are different names/aliases for the *same character*. The names are listed within parentheses separated by commas (e.g., `name1, alias1, alias2`), and the entire group is followed by a `~` symbol. This is useful when a creator uses different names for the same character.
+  - Session Behavior: Filters for "Boa" OR "Hancock". If "Separate Folders" is on, creates a single folder named "Boa Hancock".
+  - `Known.txt` Addition: If this group is new and selected for addition, it's added to `Known.txt` as a grouped alias entry, typically `(Boa Hancock)`. The first name in the `Known.txt` entry (e.g., "Boa Hancock") becomes the primary folder name.
+
+- **Combined Folder for Distinct Characters (using `(...)` syntax):**
+  - Input: `(Vivi, Uta)`
+  - Meaning: "Vivi" and "Uta" are *distinct characters*, but for this download session, their content should be grouped into a single folder. The names are listed within parentheses separated by commas. This is useful for grouping art of less frequent characters without creating many small individual folders.
+  - Session Behavior: Filters for "Vivi" OR "Uta". If "Separate Folders" is on, creates a single folder named "Vivi Uta".
+  - `Known.txt` Addition: If this "combined group" is new and selected for addition, "Vivi" and "Uta" are added to `Known.txt` as *separate, individual simple entries* on new lines:
+    ```
+    Vivi
+    Uta
+    ```
+    The combined folder "Vivi Uta" is a session-only convenience; `Known.txt` stores them as distinct entities for future individual use.
+
+**3. Interaction with `Known.txt`:**
+
+- **Adding New Names from Filters:** When you use the "Filter by Character(s)" input, if any names or groups are new (not already in `Known.txt`), a dialog will appear after you start the download. This dialog allows you to select which of these new names/groups should be added to `Known.txt`, formatted according to the rules described above.
+- **Intelligent Fallback:** If "Separate Folders by Name/Title" is active, and content doesn't match the "Filter by Character(s)" UI input, the downloader consults your `Known.txt` file for folder naming.
+- **Direct Management:** You can add simple entries directly to `Known.txt` using the list and "Add" button in the UI's `Known.txt` management section. For creating or modifying complex grouped alias entries directly in the file, or for bulk edits, click the "Open Known.txt" button. The application reloads `Known.txt` on startup or before a download process begins.
+
+---
+##  What's in v3.5.0? (Previous Update)
+This version brings significant enhancements to manga/comic downloading, filtering capabilities, and user experience:
+
+###  Enhanced Manga/Comic Mode
+
+- **New "Date Based" Filename Style:**
+
+  - Perfect for truly sequential content! Files are named numerically (e.g., `001.jpg`, `002.jpg`, `003.ext`...) across an *entire creator's feed*, strictly following post publication order.
+
+  - **Smart Numbering:** Automatically resumes from the highest existing number found in the series folder (and subfolders, if "Subfolder per Post" is enabled).
+
+  - **Guaranteed Order:** Disables multi-threading for post processing to ensure sequential accuracy.
+
+  - Works alongside the existing "Post Title" and "Original File Name" styles.
 
 ---
 
-## 📦 Installation
+###  "Remove Words from Filename" Feature
+
+- Specify comma-separated words or phrases (case-insensitive) that will be automatically removed from filenames.
+
+- Example: `patreon, [HD], _final` transforms `AwesomeArt_patreon` `Hinata_Hd` into `AwesomeArt.jpg` `Hinata.jpg`.
+
+---
+
+###  New "Only Archives" File Filter Mode
+
+- Exclusively downloads `.zip` and `.rar` files.
+
+- Automatically disables conflicting options like "Skip .zip/.rar" and external link logging.
+
+---
+
+###  Improved Character Filter Scope - "Comments (Beta)"
+
+- **File-First Check:** Prioritizes matching filenames before checking post comments for character names.
+
+- **Comment Fallback:** Only checks comments if no filename match is found, reducing unnecessary API calls.
+
+---
+
+###  Refined "Missed Character Log"
+
+- Displays a capitalized, alphabetized list of key terms from skipped post titles.
+
+- Makes it easier to spot patterns or characters that might be unintentionally excluded.
+
+---
+
+###  Enhanced Multi-part Download Progress
+
+- Granular visibility into active chunk downloads and combined speed for large files.
+
+---
+
+###  Updated Onboarding Tour
+
+- Improved guide for new users, covering v4.0.0 features and existing core functions.
+
+---
+
+###  Robust Configuration Path
+
+- Settings and `Known.txt` are now stored in the same folder as app.
+
+---
+
+##  Core Features
+
+---
+
+### User Interface & Workflow
+
+- **Clean PyQt5 GUI** — Simple, modern, and dark-themed.
+
+- **Persistent Settings** — Saves preferences between sessions.
+
+- **Download Modes:**
+  - Single Post URL
+  - Entire Creator Feed
+
+- **Flexible Options:**
+  - Specify Page Range (disabled in Manga Mode)
+  - Custom Folder Name for single posts
+
+---
+
+###  Smart Filtering
+
+- **Character Name Filtering:**
+  - Use `Tifa, Aerith` or group `(Boa, Hancock)` → folder `Boa Hancock`
+  - Flexible input for current session and for adding to `Known.txt`.
+  - Examples:
+    - `Nami` (simple character)
+    - `(Boa Hancock)~` (aliases for one character, session folder "Boa Hancock", adds `(Boa Hancock)` to `Known.txt`)
+    - `(Vivi, Uta)` (distinct characters, session folder "Vivi Uta", adds `Vivi` and `Uta` separately to `Known.txt`)
+  - See "Advanced `Known.txt` and Character Filtering" for full details.
+  - **Filter Scopes:**
+    - `Files`
+    - `Title`
+    - `Both (Title then Files)`
+    - `Comments (Beta - Files first)`
+
+- **Skip with Words:**
+  - Exclude with `WIP, sketch, preview`
+
+  - **Skip Scopes:**
+    - `Files`
+    - `Posts`
+    - `Both (Posts then Files)`
+
+- **File Type Filters:**
+  - `All`, `Images/GIFs`, `Videos`, `📦 Only Archives`, `🔗 Only Links`
+
+- **Filename Cleanup:**
+  - Remove illegal and unwanted characters or phrases
+
+---
+
+### Manga/Comic Mode (Creator Feeds Only)
+
+- **Chronological Processing** — Oldest posts first
+
+- **Filename Style Options:**
+  - `Name: Post Title (Default)`
+  - `Name: Original File`
+  - `Name: Date Based (New)`
+
+- **Best With:** Character filters set to manga/series title
+
+---
+
+### Folder Structure & Naming
+
+- **Subfolders:**
+  - Auto-created based on character name, post title, or `Known.txt`
+
+  - "Subfolder per Post" option for further nesting
+
+- **Smart Naming:** Cleans invalid characters and structures logically
+
+---
+
+### Thumbnail & Compression Tools
+
+- **Download Thumbnails Only**
+
+- **Compress to WebP** (via Pillow)
+  - Converts large images to smaller WebP versions
+
+---
+
+###  Performance Features
+
+- **Multithreading:**
+  - For both post processing and file downloading
+
+- **Multi-part Downloads:**
+  - Toggleable in GUI
+  - Splits large files into chunks
+  - Granular chunk-level progress display
+
+---
+
+### Logging & Progress
+
+- **Real-time Logs:** Activity, errors, skipped posts
+
+- **Missed Character Log:** Shows skipped keywords in easy-to-read list
+
+- **External Links Log:** Shows links (unless disabled in some modes)
+
+- **Export Links:** Save `.txt` of links (Only Links mode)
+
+---
+
+###  Config System
+
+- **`Known.txt` for Smart Folder Naming (Located in App Directory):**
+  - A user-editable file that stores a list of preferred names, series titles, or keywords.
+  - It's primarily used as an intelligent fallback for folder creation when "Separate Folders by Name/Title" is enabled.
+  - **Syntax:**
+    - Simple entries: `My Favorite Series` (creates folder "My Favorite Series", matches "My Favorite Series").
+    - Grouped entries: `(Desired Folder Name, alias1, alias2)` (creates folder "Desired Folder Name"; matches "Desired Folder Name", "alias1", or "alias2").
+
+- **Settings Stored in App Directory**
+
+- **Editable Within GUI**
+
+---
+
+## Installation
+
+---
 
 ### Requirements
 
-* Python 3.6+
-* Pip packages:
+- Python 3.6 or higher  
+- pip
+
+---
+
+### Install Dependencies
 
 ```bash
 pip install PyQt5 requests Pillow
+
+```
+
+***
+
+## ** Build a Standalone Executable (Optional)**
+
+1. Install PyInstaller:
+```bash
+pip install pyinstaller
+```
+
+2. Run:
+```bash
+pyinstaller --name "Kemono Downloader" --onefile --windowed --icon="Kemono.ico" main.py
+```
+
+3. Output will be in the `dist/` folder.
+
+***
+
+## ** Config Files**
+- `settings.json` — Stores your UI preferences and settings.
+- `Known.txt` — Stores character names, series titles, or keywords for organizing downloaded content into specific folders.
+  - Supports simple entries (e.g., `My Series`) and grouped entries for aliases (e.g., `(Folder Name, alias1, alias2)` where "Folder Name" is the name of the created folder, and all terms are used for matching).
+
+***
+
+## ** Feedback & Support**
+
+Issues? Suggestions?  
+Open an issue on the [GitHub repository](https://github.com/Yuvi9587/kemono-downloader) or join our community.

tour.py

@@ -1,325 +0,0 @@
-import sys
-import traceback # Added for enhanced error reporting
-from PyQt5.QtWidgets import (
-    QApplication, QDialog, QWidget, QLabel, QPushButton, QVBoxLayout, QHBoxLayout,
-    QStackedWidget, QSpacerItem, QSizePolicy, QCheckBox, QDesktopWidget
-)
-from PyQt5.QtCore import Qt, QSettings, pyqtSignal
-
-class TourStepWidget(QWidget):
-    """A single step/page in the tour."""
-    def __init__(self, title_text, content_text, parent=None):
-        super().__init__(parent)
-        layout = QVBoxLayout(self)
-        layout.setContentsMargins(20, 20, 20, 20)
-        layout.setSpacing(10) # Adjusted spacing between title and content for bullet points
-
-        title_label = QLabel(title_text)
-        title_label.setAlignment(Qt.AlignCenter)
-        # Increased padding-bottom for more space below title
-        title_label.setStyleSheet("font-size: 18px; font-weight: bold; color: #E0E0E0; padding-bottom: 15px;")
-
-        content_label = QLabel(content_text)
-        content_label.setWordWrap(True)
-        content_label.setAlignment(Qt.AlignLeft)
-        content_label.setTextFormat(Qt.RichText)
-        # Adjusted line-height for bullet point readability
-        content_label.setStyleSheet("font-size: 11pt; color: #C8C8C8; line-height: 1.8;")
-
-        layout.addWidget(title_label)
-        layout.addWidget(content_label)
-        layout.addStretch(1)
-
-class TourDialog(QDialog):
-    """
-    A dialog that shows a multi-page tour to the user.
-    Includes a "Never show again" checkbox.
-    Uses QSettings to remember this preference.
-    """
-    tour_finished_normally = pyqtSignal()
-    tour_skipped = pyqtSignal()
-
-    CONFIG_ORGANIZATION_NAME = "KemonoDownloader"
-    CONFIG_APP_NAME_TOUR = "ApplicationTour"
-    TOUR_SHOWN_KEY = "neverShowTourAgainV3" # Updated key for new tour content
-
-    def __init__(self, parent=None):
-        super().__init__(parent)
-        self.settings = QSettings(self.CONFIG_ORGANIZATION_NAME, self.CONFIG_APP_NAME_TOUR)
-        self.current_step = 0
-
-        self.setWindowTitle("Welcome to Kemono Downloader!")
-        self.setModal(True)
-        # Set fixed square size, smaller than main window
-        self.setFixedSize(600, 620) # Slightly adjusted for potentially more text
-        self.setStyleSheet("""
-            QDialog {
-                background-color: #2E2E2E;
-                border: 1px solid #5A5A5A;
-            }
-            QLabel {
-                color: #E0E0E0;
-            }
-            QCheckBox {
-                color: #C0C0C0;
-                font-size: 10pt;
-                spacing: 5px;
-            }
-            QCheckBox::indicator {
-                width: 13px;
-                height: 13px;
-            }
-            QPushButton {
-                background-color: #555;
-                color: #F0F0F0;
-                border: 1px solid #6A6A6A;
-                padding: 8px 15px;
-                border-radius: 4px;
-                min-height: 25px;
-                font-size: 11pt;
-            }
-            QPushButton:hover {
-                background-color: #656565;
-            }
-            QPushButton:pressed {
-                background-color: #4A4A4A;
-            }
-        """)
-        self._init_ui()
-        self._center_on_screen()
-
-    def _center_on_screen(self):
-        """Centers the dialog on the screen."""
-        try:
-            screen_geometry = QDesktopWidget().screenGeometry()
-            dialog_geometry = self.frameGeometry()
-            center_point = screen_geometry.center()
-            dialog_geometry.moveCenter(center_point)
-            self.move(dialog_geometry.topLeft())
-        except Exception as e:
-            print(f"[Tour] Error centering dialog: {e}")
-
-
-    def _init_ui(self):
-        main_layout = QVBoxLayout(self)
-        main_layout.setContentsMargins(0, 0, 0, 0)
-        main_layout.setSpacing(0)
-
-        self.stacked_widget = QStackedWidget()
-        main_layout.addWidget(self.stacked_widget, 1)
-
-        # --- Define Tour Steps with Updated Content ---
-        step1_content = (
-            "Hello! This quick tour will walk you through the main features of the Kemono Downloader."
-            "<ul>"
-            "<li>Our goal is to help you easily download content from Kemono and Coomer.</li>"
-            "<li>Use the <b>Next</b> and <b>Back</b> buttons to navigate.</li>"
-            "<li>Click <b>Skip Tour</b> to close this guide at any time.</li>"
-            "<li>Check <b>'Never show this tour again'</b> if you don't want to see this on future startups.</li>"
-            "</ul>"
-        )
-        self.step1 = TourStepWidget("👋 Welcome!", step1_content)
-
-        step2_content = (
-            "Let's start with the basics for downloading:"
-            "<ul>"
-            "<li><b>🔗 Kemono Creator/Post URL:</b><br>"
-            "   Paste the full web address (URL) of a creator's page (e.g., <i>https://kemono.su/patreon/user/12345</i>) "
-            "or a specific post (e.g., <i>.../post/98765</i>).</li><br>"
-            "<li><b>📁 Download Location:</b><br>"
-            "   Click 'Browse...' to choose a folder on your computer where all downloaded files will be saved. "
-            "This is required unless you are using 'Only Links' mode.</li><br>"
-            "<li><b>📄 Page Range (Creator URLs only):</b><br>"
-            "   If downloading from a creator's page, you can specify a range of pages (e.g., pages 2 to 5). "
-            "Leave blank for all pages. This is disabled for single post URLs or when <b>Manga/Comic Mode</b> is active.</li>"
-            "</ul>"
-        )
-        self.step2 = TourStepWidget("① Getting Started", step2_content)
-
-        step3_content = (
-            "Refine what you download with these filters:"
-            "<ul>"
-            "<li><b>🎯 Filter by Character(s):</b><br>"
-            "   Enter character names, comma-separated (e.g., <i>Tifa, Aerith</i>). "
-            "   <ul><li>In <b>Normal Mode</b>, this filters individual files by matching their filenames.</li>"
-            "       <li>In <b>Manga/Comic Mode</b>, this filters entire posts by matching the post title. Useful for targeting specific series.</li>"
-            "       <li>Also helps in folder naming if 'Separate Folders' is enabled.</li></ul></li><br>"
-            "<li><b>🚫 Skip with Words:</b><br>"
-            "   Enter words, comma-separated (e.g., <i>WIP, sketch, preview</i>). "
-            "   The <b>Scope</b> button (next to this input) cycles how this filter applies:"
-            "   <ul><li><i>Scope: Files:</i> Skips files if their names contain any of these words.</li>"
-            "       <li><i>Scope: Posts:</i> Skips entire posts if their titles contain any of these words.</li>"
-            "       <li><i>Scope: Both:</i> Applies both file and post title skipping.</li></ul></li><br>"
-            "<li><b>Filter Files (Radio Buttons):</b> Choose what to download:"
-            "   <ul>"
-            "   <li><i>All:</i> Downloads all file types found.</li>"
-            "   <li><i>Images/GIFs:</i> Only common image formats and GIFs.</li>"
-            "   <li><i>Videos:</i> Only common video formats.</li>"
-            "   <li><b><i>📦 Only Archives:</i></b> Exclusively downloads <b>.zip</b> and <b>.rar</b> files. When selected, 'Skip .zip' and 'Skip .rar' checkboxes are automatically disabled and unchecked.</li>"
-            "   <li><i>🔗 Only Links:</i> Extracts and displays external links from post descriptions instead of downloading files.</li>"
-            "   </ul></li>"
-            "</ul>"
-        )
-        self.step3 = TourStepWidget("② Filtering Downloads", step3_content)
-
-        step4_content = (
-            "More options to customize your downloads:"
-            "<ul>"
-            "<li><b>Skip .zip / Skip .rar:</b> Check these to avoid downloading these archive file types. "
-            "   <i>(Note: These are disabled and ignored if '📦 Only Archives' mode is selected).</i></li><br>"
-            "<li><b>Download Thumbnails Only:</b> Downloads small preview images instead of full-sized files (if available).</li><br>"
-            "<li><b>Compress Large Images:</b> If the 'Pillow' library is installed, images larger than 1.5MB will be converted to WebP format if the WebP version is significantly smaller.</li><br>"
-            "<li><b>🗄️ Custom Folder Name (Single Post Only):</b><br>"
-            "   If you are downloading a single specific post URL AND 'Separate Folders by Name/Title' is enabled, "
-            "you can enter a custom name here for that post's download folder.</li>"
-            "</ul>"
-        )
-        self.step4 = TourStepWidget("③ Fine-Tuning Downloads", step4_content)
-
-        step5_content = (
-            "Organize your downloads and manage performance:"
-            "<ul>"
-            "<li><b>⚙️ Separate Folders by Name/Title:</b> Creates subfolders based on the 'Filter by Character(s)' input or post titles (can use the 'Known Shows/Characters' list as a fallback for folder names).</li><br>"
-            "<li><b>Subfolder per Post:</b> If 'Separate Folders' is on, this creates an additional subfolder for <i>each individual post</i> inside the main character/title folder.</li><br>"
-            "<li><b>🚀 Use Multithreading (Threads):</b> Enables faster downloads for creator pages by processing multiple posts or files concurrently. The number of threads can be adjusted. Single post URLs are processed using a single thread for post data but can use multiple threads for file downloads within that post.</li><br>"
-            "<li><b>📖 Manga/Comic Mode (Creator URLs only):</b> Tailored for sequential content."
-            "   <ul>"
-            "   <li>Downloads posts from <b>oldest to newest</b>.</li>"
-            "   <li>The 'Page Range' input is disabled as all posts are fetched.</li>"
-            "   <li>A <b>filename style toggle button</b> (e.g., 'Name: Post Title' or 'Name: Original File') appears in the top-right of the log area when this mode is active for a creator feed. Click it to change naming:"
-            "       <ul>"
-            "       <li><b><i>Name: Post Title (Default):</i></b> The first file in a post is named after the post's title (e.g., <i>MyMangaChapter1.jpg</i>). Subsequent files in the <i>same post</i> (if any) will retain their original filenames.</li>"
-            "       <li><b><i>Name: Original File:</i></b> All files will attempt to keep their original filenames as provided by the site (e.g., <i>001.jpg, page_02.png</i>). You'll see a recommendation to use 'Post Title' style if you choose this.</li>"
-            "       </ul>"
-            "   </li>"
-            "   <li>For best results with 'Name: Post Title' style, use the 'Filter by Character(s)' field with the manga/series title.</li>"
-            "   </ul></li><br>"
-            "<li><b>🎭 Known Shows/Characters:</b> Add names here (e.g., <i>Game Title, Series Name, Character Full Name</i>). These are used for automatic folder creation when 'Separate Folders' is on and no specific 'Filter by Character(s)' is provided for a post.</li>"
-            "</ul>"
-        )
-        self.step5 = TourStepWidget("④ Organization & Performance", step5_content)
-
-        step6_content = (
-            "Monitoring and Controls:"
-            "<ul>"
-            "<li><b>📜 Progress Log / Extracted Links Log:</b> Shows detailed download messages. If '🔗 Only Links' mode is active, this area displays the extracted links.</li><br>"
-            "<li><b>Show External Links in Log:</b> If checked, a secondary log panel appears below the main log to display any external links found in post descriptions. <i>(This is disabled if '🔗 Only Links' or '📦 Only Archives' mode is active).</i></li><br>"
-            "<li><b>Log Verbosity (Show Basic/Full Log):</b> Toggles the main log between showing all messages (Full) or only key summaries, errors, and warnings (Basic).</li><br>"
-            "<li><b>🔄 Reset:</b> Clears all input fields, logs, and resets temporary settings to their defaults. Can only be used when no download is active.</li><br>"
-            "<li><b>⬇️ Start Download / ❌ Cancel:</b> These buttons initiate or stop the current download/extraction process.</li>"
-            "</ul>"
-            "<br>You're all set! Click <b>'Finish'</b> to close the tour and start using the downloader."
-        )
-        self.step6 = TourStepWidget("⑤ Logs & Final Controls", step6_content)
-
-
-        self.tour_steps = [self.step1, self.step2, self.step3, self.step4, self.step5, self.step6]
-        for step_widget in self.tour_steps:
-            self.stacked_widget.addWidget(step_widget)
-
-        bottom_controls_layout = QVBoxLayout()
-        bottom_controls_layout.setContentsMargins(15, 10, 15, 15) # Adjusted margins
-        bottom_controls_layout.setSpacing(10)
-
-        self.never_show_again_checkbox = QCheckBox("Never show this tour again")
-        bottom_controls_layout.addWidget(self.never_show_again_checkbox, 0, Qt.AlignLeft)
-
-        buttons_layout = QHBoxLayout()
-        buttons_layout.setSpacing(10)
-
-        self.skip_button = QPushButton("Skip Tour")
-        self.skip_button.clicked.connect(self._skip_tour_action)
-
-        self.back_button = QPushButton("Back")
-        self.back_button.clicked.connect(self._previous_step)
-        self.back_button.setEnabled(False)
-
-        self.next_button = QPushButton("Next")
-        self.next_button.clicked.connect(self._next_step_action)
-        self.next_button.setDefault(True)
-
-        buttons_layout.addWidget(self.skip_button)
-        buttons_layout.addStretch(1)
-        buttons_layout.addWidget(self.back_button)
-        buttons_layout.addWidget(self.next_button)
-
-        bottom_controls_layout.addLayout(buttons_layout)
-        main_layout.addLayout(bottom_controls_layout)
-
-        self._update_button_states()
-
-    def _handle_exit_actions(self):
-        if self.never_show_again_checkbox.isChecked():
-            self.settings.setValue(self.TOUR_SHOWN_KEY, True)
-            self.settings.sync()
-        # else:
-            # print(f"[Tour] '{self.TOUR_SHOWN_KEY}' setting not set to True (checkbox was unchecked on exit).")
-
-
-    def _next_step_action(self):
-        if self.current_step < len(self.tour_steps) - 1:
-            self.current_step += 1
-            self.stacked_widget.setCurrentIndex(self.current_step)
-        else:
-            self._handle_exit_actions()
-            self.tour_finished_normally.emit()
-            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 _skip_tour_action(self):
-        self._handle_exit_actions()
-        self.tour_skipped.emit()
-        self.reject()
-
-    def _update_button_states(self):
-        if self.current_step == len(self.tour_steps) - 1:
-            self.next_button.setText("Finish")
-        else:
-            self.next_button.setText("Next")
-        self.back_button.setEnabled(self.current_step > 0)
-
-    @staticmethod
-    def run_tour_if_needed(parent_app_window):
-        try:
-            settings = QSettings(TourDialog.CONFIG_ORGANIZATION_NAME, TourDialog.CONFIG_APP_NAME_TOUR)
-            never_show_again = settings.value(TourDialog.TOUR_SHOWN_KEY, False, type=bool)
-
-            if never_show_again:
-                return QDialog.Rejected
-
-            tour_dialog = TourDialog(parent_app_window)
-            result = tour_dialog.exec_()
-            return result
-        except Exception as e:
-            print(f"[Tour] CRITICAL ERROR in run_tour_if_needed: {e}")
-            traceback.print_exc()
-            return QDialog.Rejected
-
-if __name__ == '__main__':
-    app = QApplication(sys.argv)
-
-    # --- For testing: force the tour to show by resetting the flag ---
-    # print("[Tour Test] Resetting 'Never show again' flag for testing purposes.")
-    # test_settings = QSettings(TourDialog.CONFIG_ORGANIZATION_NAME, TourDialog.CONFIG_APP_NAME_TOUR)
-    # test_settings.setValue(TourDialog.TOUR_SHOWN_KEY, False) # Set to False to force tour
-    # test_settings.sync()
-    # --- End testing block ---
-
-    print("[Tour Test] Running tour standalone...")
-    result = TourDialog.run_tour_if_needed(None)
-
-    if result == QDialog.Accepted:
-        print("[Tour Test] Tour dialog was accepted (Finished).")
-    elif result == QDialog.Rejected:
-        print("[Tour Test] Tour dialog was rejected (Skipped or previously set to 'Never show again').")
-
-    final_settings = QSettings(TourDialog.CONFIG_ORGANIZATION_NAME, TourDialog.CONFIG_APP_NAME_TOUR)
-    print(f"[Tour Test] Final state of '{TourDialog.TOUR_SHOWN_KEY}' in settings: {final_settings.value(TourDialog.TOUR_SHOWN_KEY, False, type=bool)}")
-
-    sys.exit()