Commit

downloader_utils.py

@@ -31,6 +31,7 @@ from io import BytesIO
 STYLE_POST_TITLE = "post_title"
 STYLE_ORIGINAL_NAME = "original_name"
 STYLE_DATE_BASED = "date_based" # For manga date-based sequential naming
+MANGA_DATE_PREFIX_DEFAULT = "" # Default for the new prefix
 STYLE_POST_TITLE_GLOBAL_NUMBERING = "post_title_global_numbering" # For manga post title + global counter
 
 SKIP_SCOPE_FILES = "files"
@@ -51,6 +52,9 @@ KNOWN_NAMES = [] # This will now store dicts: {'name': str, 'is_group': bool, 'a
 
 MIN_SIZE_FOR_MULTIPART_DOWNLOAD = 10 * 1024 * 1024  # 10 MB - Stays the same
 MAX_PARTS_FOR_MULTIPART_DOWNLOAD = 15 # Max concurrent connections for a single file
+# Max length for a single filename or folder name component to ensure cross-OS compatibility
+# Windows MAX_PATH is 260 for the full path. Individual components are usually shorter.
+MAX_FILENAME_COMPONENT_LENGTH = 150
 
 IMAGE_EXTENSIONS = {
     '.jpg', '.jpeg', '.png', '.gif', '.bmp', '.tiff', '.tif', '.webp',
@@ -63,6 +67,11 @@ VIDEO_EXTENSIONS = {
 ARCHIVE_EXTENSIONS = {
     '.zip', '.rar', '.7z', '.tar', '.gz', '.bz2'
 }
+AUDIO_EXTENSIONS = {
+    '.mp3', '.wav', '.aac', '.flac', '.ogg', '.wma', '.m4a', '.opus',
+    '.aiff', '.ape', '.mid', '.midi'
+}
+
 def parse_cookie_string(cookie_string):
     """Parses a 'name=value; name2=value2' cookie string into a dict."""
     cookies = {}
@@ -131,18 +140,46 @@ def clean_folder_name(name):
 
     if not cleaned: # If empty after initial cleaning
         return "untitled_folder"
+
+    # Truncate if too long
+    if len(cleaned) > MAX_FILENAME_COMPONENT_LENGTH:
+        cleaned = cleaned[:MAX_FILENAME_COMPONENT_LENGTH]
+        # After truncation, it's possible a new trailing space/dot is at the end
+        # or an existing one remains. So, strip them using the loop below.
+
+    # Strip trailing dots/spaces (original logic, now applied to potentially truncated name)
     temp_name = cleaned
     while len(temp_name) > 0 and (temp_name.endswith('.') or temp_name.endswith(' ')):
         temp_name = temp_name[:-1]
+
     return temp_name if temp_name else "untitled_folder"
 
 
 def clean_filename(name):
     if not isinstance(name, str): name = str(name)
     cleaned = re.sub(r'[^\w\s\-\_\.\(\)]', '', name)
-    cleaned = cleaned.strip()
-    cleaned = re.sub(r'\s+', '_', cleaned)
-    return cleaned if cleaned else "untitled_file"
+    cleaned = cleaned.strip() # Remove leading/trailing spaces first
+    cleaned = re.sub(r'\s+', ' ', cleaned) # Replace multiple internal spaces with a single space
+
+    if not cleaned: return "untitled_file"
+
+    base_name, ext = os.path.splitext(cleaned)
+
+    # Calculate max length for base_name, reserving space for the extension
+    max_base_len = MAX_FILENAME_COMPONENT_LENGTH - len(ext)
+
+    if len(base_name) > max_base_len:
+        if max_base_len > 0: # If there's space for at least some of the base name
+            base_name = base_name[:max_base_len]
+        else: # No space for base name (extension is too long or fills the entire allowed space)
+              # In this case, we have to truncate the original 'cleaned' string,
+              # which might cut into the extension, but it's necessary to meet the length.
+            return cleaned[:MAX_FILENAME_COMPONENT_LENGTH] if cleaned else "untitled_file"
+
+    final_name = base_name + ext
+    # Ensure the final reconstructed name isn't empty (e.g. if base_name became empty and ext was also empty)
+    return final_name if final_name else "untitled_file"
+
 
 def strip_html_tags(html_text):
     if not html_text: return ""
@@ -218,6 +255,12 @@ def is_archive(filename):
     _, ext = os.path.splitext(filename)
     return ext.lower() in ARCHIVE_EXTENSIONS
 
+def is_audio(filename):
+    if not filename: return False
+    _, ext = os.path.splitext(filename)
+    return ext.lower() in AUDIO_EXTENSIONS
+
+
 
 def is_post_url(url):
     if not isinstance(url, str): return False
@@ -262,19 +305,43 @@ def prepare_cookies_for_request(use_cookie_flag, cookie_text_input, selected_coo
     if not use_cookie_flag:
         return None
 
-    if cookie_text_input:
-        logger_func("   🍪 Using cookies from UI text input.")
-        return parse_cookie_string(cookie_text_input)
-    elif selected_cookie_file_path:
+    # Attempt 1: Selected cookie file
+    if selected_cookie_file_path:
         logger_func(f"   🍪 Attempting to load cookies from selected file: '{os.path.basename(selected_cookie_file_path)}'...")
-        return load_cookies_from_netscape_file(selected_cookie_file_path, logger_func)
-    elif app_base_dir:
-        cookies_filepath = os.path.join(app_base_dir, "cookies.txt")
-        logger_func(f"   🍪 No UI text or specific file selected. Attempting to load default '{os.path.basename(cookies_filepath)}' from app directory...")
-        return load_cookies_from_netscape_file(cookies_filepath, logger_func)
-    else:
-        logger_func("   🍪 Cookie usage enabled, but no text input, specific file, or app base directory provided for cookies.txt.")
-        return None
+        cookies = load_cookies_from_netscape_file(selected_cookie_file_path, logger_func)
+        if cookies:
+            return cookies
+        else:
+            logger_func(f"   ⚠️ Failed to load cookies from selected file: '{os.path.basename(selected_cookie_file_path)}'. Trying other methods.")
+            # Fall through if selected file is invalid or not found
+
+    # Attempt 2: Default cookies.txt in app directory
+    # This is tried if no specific file was selected OR if the selected file was provided but failed to load.
+    if app_base_dir: # Only proceed if app_base_dir is available
+        # Avoid re-logging "not found" or "failed" if a selected_cookie_file_path was already attempted and failed.
+        # Only log the attempt for default if no selected_cookie_file_path was given.
+        default_cookies_path = os.path.join(app_base_dir, "cookies.txt")
+        if os.path.exists(default_cookies_path): # Only attempt if it exists
+            if not selected_cookie_file_path: # Log attempt only if we didn't just try a selected file
+                logger_func(f"   🍪 No specific file selected. Attempting to load default '{os.path.basename(default_cookies_path)}' from app directory...")
+            cookies = load_cookies_from_netscape_file(default_cookies_path, logger_func)
+            if cookies:
+                return cookies
+            elif not selected_cookie_file_path: # Log failure only if we tried default as primary file method
+                 logger_func(f"   ⚠️ Failed to load cookies from default file: '{os.path.basename(default_cookies_path)}'. Trying text input.")
+            # Fall through if default file is invalid or not found
+
+    # Attempt 3: Cookies from UI text input
+    if cookie_text_input:
+        logger_func("   🍪 Using cookies from UI text input (as file methods failed or were not applicable).")
+        cookies = parse_cookie_string(cookie_text_input)
+        if cookies:
+            return cookies
+        else:
+            logger_func("   ⚠️ UI cookie text input was provided but was empty or invalid.")
+
+    logger_func("   🍪 Cookie usage enabled, but no valid cookies found from any source (selected file, default file, or text input).")
+    return None
 
 def fetch_posts_paginated(api_url_base, headers, offset, logger, cancellation_event=None, pause_event=None, cookies_dict=None):    
     if cancellation_event and cancellation_event.is_set(): # type: ignore
@@ -602,12 +669,15 @@ class PostProcessorWorker:
                  allow_multipart_download=True,
                  cookie_text="", # Added missing parameter
                  use_cookie=False, # Added missing parameter
+                 override_output_dir=None, # New parameter
                  selected_cookie_file=None, # Added missing parameter
                  app_base_dir=None, # New parameter for app's base directory
+                 manga_date_prefix=MANGA_DATE_PREFIX_DEFAULT, # New parameter for date-based prefix
                  manga_date_file_counter_ref=None, # New parameter for date-based manga naming
+                 scan_content_for_images=False, # New flag for scanning HTML content
                  manga_global_file_counter_ref=None, # New parameter for global numbering
                  ): # type: ignore
-        self.post = post_data
+        self.post = post_data # type: ignore
         self.download_root = download_root
         self.known_names = known_names
         self.filter_character_list_objects_initial = filter_character_list if filter_character_list else [] # Store initial
@@ -652,10 +722,14 @@ class PostProcessorWorker:
         self.selected_cookie_file = selected_cookie_file # Store selected cookie file path       
         self.app_base_dir = app_base_dir # Store app base dir        
         self.cookie_text = cookie_text # Store cookie text
+        self.manga_date_prefix = manga_date_prefix # Store the prefix
         self.manga_global_file_counter_ref = manga_global_file_counter_ref # Store global counter
         self.use_cookie = use_cookie # Store cookie setting
+        self.override_output_dir = override_output_dir # Store the override directory
+        self.scan_content_for_images = scan_content_for_images # Store new flag
 
         if self.compress_images and Image is None:
+            # type: ignore
             self.logger("⚠️ Image compression disabled: Pillow library not found.")
             self.compress_images = False
 
@@ -676,9 +750,9 @@ class PostProcessorWorker:
         return self.cancellation_event.is_set()
 
     def _check_pause(self, context_message="Operation"):
-        if self.pause_event and self.pause_event.is_set():
+        if self.pause_event and self.pause_event.is_set(): # type: ignore
             self.logger(f"   {context_message} paused...")
-            while self.pause_event.is_set(): # Loop while pause_event is set
+            while self.pause_event.is_set(): # type: ignore # Loop while pause_event is set
                 if self.check_cancel():
                     self.logger(f"   {context_message} cancelled while paused.")
                     return True # Indicates cancellation occurred
@@ -734,6 +808,14 @@ class PostProcessorWorker:
             if self.manga_mode_active: # Note: duplicate_file_mode is overridden to "Delete" in main.py if manga_mode is on
                 if self.manga_filename_style == STYLE_ORIGINAL_NAME:
                     filename_to_save_in_main_path = clean_filename(api_original_filename)
+                    # Apply prefix if provided for Original Name style
+                    if self.manga_date_prefix and self.manga_date_prefix.strip():
+                        cleaned_prefix = clean_filename(self.manga_date_prefix.strip())
+                        if cleaned_prefix:
+                            filename_to_save_in_main_path = f"{cleaned_prefix} {filename_to_save_in_main_path}"
+                        else:
+                            self.logger(f"⚠️ Manga Original Name Mode: Provided prefix '{self.manga_date_prefix}' was empty after cleaning. Using original name only.")
+
                     was_original_name_kept_flag = True
                 elif self.manga_filename_style == STYLE_POST_TITLE:
                     if post_title and post_title.strip():
@@ -742,8 +824,8 @@ class PostProcessorWorker:
                             if file_index_in_post == 0:
                                 filename_to_save_in_main_path = f"{cleaned_post_title_base}{original_ext}"
                             else:
-                                filename_to_save_in_main_path = clean_filename(api_original_filename)
-                                was_original_name_kept_flag = True 
+                                filename_to_save_in_main_path = f"{cleaned_post_title_base}_{file_index_in_post}{original_ext}"
+                                was_original_name_kept_flag = False # Name is derived, not original
                         else:
                             filename_to_save_in_main_path = f"{cleaned_post_title_base}{original_ext}"
                     else:
@@ -759,7 +841,15 @@ class PostProcessorWorker:
                             counter_val_for_filename = manga_date_file_counter_ref[0]
                             manga_date_file_counter_ref[0] += 1
                         
-                        filename_to_save_in_main_path = f"{counter_val_for_filename:03d}{original_ext}"
+                        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())
+                            if cleaned_prefix: # Ensure prefix is not empty after cleaning
+                                filename_to_save_in_main_path = f"{cleaned_prefix} {base_numbered_name}{original_ext}"
+                            else: # Prefix became empty after cleaning
+                                filename_to_save_in_main_path = f"{base_numbered_name}{original_ext}"; self.logger(f"⚠️ Manga Date Mode: Provided prefix '{self.manga_date_prefix}' was empty after cleaning. Using number only.")
+                        else: # No prefix provided
+                            filename_to_save_in_main_path = f"{base_numbered_name}{original_ext}"
                     else:
                         self.logger(f"⚠️ Manga Date Mode: Counter ref not provided or malformed for '{api_original_filename}'. Using original. Ref: {manga_date_file_counter_ref}")
                         filename_to_save_in_main_path = clean_filename(api_original_filename)
@@ -796,8 +886,10 @@ class PostProcessorWorker:
                     if not word_to_remove: continue
                     pattern = re.compile(re.escape(word_to_remove), re.IGNORECASE)
                     modified_base_name = pattern.sub("", modified_base_name)
-                modified_base_name = re.sub(r'[_.\s-]+', '_', modified_base_name) 
-                modified_base_name = modified_base_name.strip('_') 
+                # After removals, normalize all seps (underscore, dot, multiple spaces, hyphen) to a single space, then strip.
+                modified_base_name = re.sub(r'[_.\s-]+', ' ', modified_base_name) # Convert all separators to spaces
+                modified_base_name = re.sub(r'\s+', ' ', modified_base_name)     # Condense multiple spaces to one
+                modified_base_name = modified_base_name.strip()                  # Remove leading/trailing spaces
                 if modified_base_name and modified_base_name != ext_for_removal.lstrip('.'):
                     filename_to_save_in_main_path = modified_base_name + ext_for_removal
                 else: 
@@ -807,6 +899,7 @@ class PostProcessorWorker:
             is_img_type = is_image(api_original_filename)
             is_vid_type = is_video(api_original_filename)
             is_archive_type = is_archive(api_original_filename)
+            is_audio_type = is_audio(api_original_filename)
 
             if self.filter_mode == 'archive':
                 if not is_archive_type:
@@ -820,6 +913,10 @@ class PostProcessorWorker:
                 if not is_vid_type:
                     self.logger(f"   -> Filter Skip: '{api_original_filename}' (Not Video).")
                     return 0, 1, api_original_filename, False, FILE_DOWNLOAD_STATUS_SKIPPED, None
+            elif self.filter_mode == 'audio': # New audio filter mode
+                if not is_audio_type:
+                    self.logger(f"   -> Filter Skip: '{api_original_filename}' (Not Audio).")
+                    return 0, 1, api_original_filename, False, FILE_DOWNLOAD_STATUS_SKIPPED, None
 
             if self.skip_zip and is_zip(api_original_filename):
                 self.logger(f"   -> Pref Skip: '{api_original_filename}' (ZIP).")
@@ -1271,7 +1368,7 @@ class PostProcessorWorker:
                     self.logger(f"   -> Skip Post (Folder Keyword): Potential folder '{folder_name_to_check}' contains '{matched_skip}'.")
                     return 0, num_potential_files_in_post, [], []
 
-        if (self.show_external_links or self.extract_links_only) and post_content_html:
+        if (self.show_external_links or self.extract_links_only) and post_content_html: # type: ignore
             if self._check_pause(f"External link extraction for post {post_id}"): return 0, num_potential_files_in_post, [], []
             try:
                 unique_links_data = {} 
@@ -1318,14 +1415,14 @@ class PostProcessorWorker:
             if original_api_name:
                 all_files_from_post_api.append({
                     'url': f"https://{api_file_domain}{file_path}" if file_path.startswith('/') else f"https://{api_file_domain}/data/{file_path}",
-                    'name': original_api_name,
+                    'name': original_api_name, # This is the cleaned/API provided name
                     '_original_name_for_log': original_api_name,
-                    '_is_thumbnail': self.download_thumbnails and is_image(original_api_name)
+                    '_is_thumbnail': is_image(original_api_name) # Mark if it's an image from API
                 })
             else: self.logger(f"   ⚠️ Skipping main file for post {post_id}: Missing name (Path: {file_path})")
 
         for idx, att_info in enumerate(post_attachments):
-            if isinstance(att_info, dict) and att_info.get('path'):
+            if isinstance(att_info, dict) and att_info.get('path'): # Ensure att_info is a dict
                 att_path = att_info['path'].lstrip('/')
                 original_api_att_name = att_info.get('name') or os.path.basename(att_path)
                 if original_api_att_name:
@@ -1333,16 +1430,99 @@ class PostProcessorWorker:
                         'url': f"https://{api_file_domain}{att_path}" if att_path.startswith('/') else f"https://{api_file_domain}/data/{att_path}",
                         'name': original_api_att_name,
                         '_original_name_for_log': original_api_att_name,
-                        '_is_thumbnail': self.download_thumbnails and is_image(original_api_att_name)
+                        '_is_thumbnail': is_image(original_api_att_name) # Mark if it's an image from API
                     })
                 else: self.logger(f"   ⚠️ Skipping attachment {idx+1} for post {post_id}: Missing name (Path: {att_path})")
             else: self.logger(f"   ⚠️ Skipping invalid attachment {idx+1} for post {post_id}: {str(att_info)[:100]}")
 
+        # --- New: Scan post content for additional image URLs if enabled ---
+        if self.scan_content_for_images and post_content_html and not self.extract_links_only: # This block was duplicated, ensure only one exists
+            self.logger(f"   Scanning post content for additional image URLs (Post ID: {post_id})...")
+            
+            parsed_input_url = urlparse(self.api_url_input)
+            base_url_for_relative_paths = f"{parsed_input_url.scheme}://{parsed_input_url.netloc}"
+            img_ext_pattern = "|".join(ext.lstrip('.') for ext in IMAGE_EXTENSIONS)
+            
+            # 1. Regex for direct absolute image URLs in text
+            direct_url_pattern_str = r"""(?i)\b(https?://[^\s"'<>\[\]\{\}\|\^\\^~\[\]`]+\.(?:""" + img_ext_pattern + r"""))\b"""
+            # 2. Regex for <img> tags (captures src content)
+            img_tag_src_pattern_str = r"""<img\s+[^>]*?src\s*=\s*["']([^"']+)["']"""
+
+            found_image_sources = set()
+
+            for direct_url_match in re.finditer(direct_url_pattern_str, post_content_html):
+                found_image_sources.add(direct_url_match.group(1))
+
+            for img_tag_match in re.finditer(img_tag_src_pattern_str, post_content_html, re.IGNORECASE):
+                src_attr = img_tag_match.group(1).strip()
+                src_attr = html.unescape(src_attr)
+                if not src_attr: continue
+
+                resolved_src_url = ""
+                if src_attr.startswith(('http://', 'https://')):
+                    resolved_src_url = src_attr
+                elif src_attr.startswith('//'):
+                    resolved_src_url = f"{parsed_input_url.scheme}:{src_attr}"
+                elif src_attr.startswith('/'):
+                    resolved_src_url = f"{base_url_for_relative_paths}{src_attr}"
+                
+                if resolved_src_url:
+                    parsed_resolved_url = urlparse(resolved_src_url)
+                    if any(parsed_resolved_url.path.lower().endswith(ext) for ext in IMAGE_EXTENSIONS):
+                        found_image_sources.add(resolved_src_url)
+
+            if found_image_sources:
+                self.logger(f"      Found {len(found_image_sources)} potential image URLs/sources in content.")
+                existing_urls_in_api_list = {f_info['url'] for f_info in all_files_from_post_api}
+
+                for found_url in found_image_sources: # Iterate over the unique, resolved URLs
+                    if self.check_cancel(): break
+                    if found_url in existing_urls_in_api_list:
+                        self.logger(f"         Skipping URL from content (already in API list or previously added from content): {found_url[:70]}...")
+                        continue
+                    try:
+                        parsed_found_url = urlparse(found_url)
+                        url_filename = os.path.basename(parsed_found_url.path)
+                        if not url_filename or not is_image(url_filename):
+                            self.logger(f"         Skipping URL from content (no filename part or not an image extension): {found_url[:70]}...")
+                            continue
+
+                        self.logger(f"      Adding image from content: {url_filename} (URL: {found_url[:70]}...)")
+                        all_files_from_post_api.append({
+                            'url': found_url,
+                            'name': url_filename,
+                            '_original_name_for_log': url_filename,
+                            '_is_thumbnail': False, # Images from content are not API thumbnails
+                            '_from_content_scan': True 
+                        })
+                        existing_urls_in_api_list.add(found_url) 
+                    except Exception as e_url_parse:
+                        self.logger(f"         Error processing URL from content '{found_url[:70]}...': {e_url_parse}")
+            else:
+                self.logger(f"      No additional image URLs found in post content scan for post {post_id}.")
+        # --- End of new content scanning logic ---
+
+        # --- Final filtering based on download_thumbnails and scan_content_for_images flags ---
         if self.download_thumbnails:
-            all_files_from_post_api = [finfo for finfo in all_files_from_post_api if finfo['_is_thumbnail']]
-            if not all_files_from_post_api:
-                 self.logger(f"   -> No image thumbnails found for post {post_id} in thumbnail-only mode.")
-                 return 0, 0, [], []
+            if self.scan_content_for_images:
+                # Both "Download Thumbnails Only" AND "Scan Content for Images" are checked.
+                # Prioritize images from content scan.
+                self.logger(f"   Mode: 'Download Thumbnails Only' + 'Scan Content for Images' active. Prioritizing images from content scan for post {post_id}.")
+                all_files_from_post_api = [finfo for finfo in all_files_from_post_api if finfo.get('_from_content_scan')]
+                if not all_files_from_post_api:
+                    self.logger(f"   -> No images found via content scan for post {post_id} in this combined mode.")
+                    return 0, 0, [], [] # No files to download for this post
+            else:
+                # Only "Download Thumbnails Only" is checked. Filter for API thumbnails.
+                self.logger(f"   Mode: 'Download Thumbnails Only' active. Filtering for API thumbnails for post {post_id}.")
+                all_files_from_post_api = [finfo for finfo in all_files_from_post_api if finfo.get('_is_thumbnail')]
+                if not all_files_from_post_api:
+                    self.logger(f"   -> No API image thumbnails found for post {post_id} in thumbnail-only mode.")
+                    return 0, 0, [], [] # No files to download for this post
+        # If self.download_thumbnails is False, all_files_from_post_api remains as is.
+        # It will contain all API files (images marked with _is_thumbnail: True, others False)
+        # and potentially content-scanned images (marked with _from_content_scan: True).
+
         if self.manga_mode_active and self.manga_filename_style == STYLE_DATE_BASED:
             def natural_sort_key_for_files(file_api_info):
                 name = file_api_info.get('_original_name_for_log', '').lower()
@@ -1444,7 +1624,7 @@ class PostProcessorWorker:
                     total_skipped_this_post += 1
                     continue
 
-                current_path_for_file = self.download_root
+                current_path_for_file = self.override_output_dir if self.override_output_dir else self.download_root # Use override if provided
 
                 if self.use_subfolders:
                     char_title_subfolder_name = None
@@ -1548,18 +1728,21 @@ class DownloadThread(QThread):
                  manga_filename_style=STYLE_POST_TITLE,
                  char_filter_scope=CHAR_SCOPE_FILES, # manga_date_file_counter_ref removed from here
                  remove_from_filename_words_list=None,
+                 manga_date_prefix=MANGA_DATE_PREFIX_DEFAULT, # New parameter
                  allow_multipart_download=True,
                  selected_cookie_file=None, # New parameter for selected cookie file
+                 override_output_dir=None, # New parameter
                  app_base_dir=None, # New parameter
                  manga_date_file_counter_ref=None, # New parameter
                  manga_global_file_counter_ref=None, # New parameter for global numbering
                  use_cookie=False, # Added: Expected by main.py
+                 scan_content_for_images=False, # Added new flag
                  cookie_text="",   # Added: Expected by main.py
                  ):
         super().__init__()
         self.api_url_input = api_url_input
         self.output_dir = output_dir
-        self.known_names = list(known_names_copy)
+        self.known_names = list(known_names_copy) # type: ignore
         self.cancellation_event = cancellation_event
         self.pause_event = pause_event # Store pause_event
         self.skip_current_file_flag = skip_current_file_flag
@@ -1597,12 +1780,15 @@ class DownloadThread(QThread):
         self.manga_filename_style = manga_filename_style
         self.char_filter_scope = char_filter_scope
         self.remove_from_filename_words_list = remove_from_filename_words_list
+        self.manga_date_prefix = manga_date_prefix # Store the prefix
         self.allow_multipart_download = allow_multipart_download
         self.selected_cookie_file = selected_cookie_file # Store selected cookie file
         self.app_base_dir = app_base_dir # Store app base dir
         self.cookie_text = cookie_text # Store cookie text
         self.use_cookie = use_cookie # Store cookie setting
+        self.override_output_dir = override_output_dir # Store override dir
         self.manga_date_file_counter_ref = manga_date_file_counter_ref # Store for passing to worker by DownloadThread
+        self.scan_content_for_images = scan_content_for_images # Store new flag
         self.manga_global_file_counter_ref = manga_global_file_counter_ref # Store for global numbering
         if self.compress_images and Image is None:
             self.logger("⚠️ Image compression disabled: Pillow library not found (DownloadThread).")
@@ -1726,15 +1912,18 @@ class DownloadThread(QThread):
                          skip_current_file_flag=self.skip_current_file_flag,
                          manga_mode_active=self.manga_mode_active,
                          manga_filename_style=self.manga_filename_style,
+                         manga_date_prefix=self.manga_date_prefix, # Pass the prefix
                          char_filter_scope=self.char_filter_scope,
                          remove_from_filename_words_list=self.remove_from_filename_words_list,
                          allow_multipart_download=self.allow_multipart_download,
                          selected_cookie_file=self.selected_cookie_file, # Pass selected cookie file
                          app_base_dir=self.app_base_dir, # Pass app_base_dir
                          cookie_text=self.cookie_text, # Pass cookie text
+                         override_output_dir=self.override_output_dir, # Pass override dir
                          manga_global_file_counter_ref=self.manga_global_file_counter_ref, # Pass the ref
                          use_cookie=self.use_cookie, # Pass cookie setting to worker
                          manga_date_file_counter_ref=current_manga_date_file_counter_ref, # Pass the calculated or passed-in ref
+                         scan_content_for_images=self.scan_content_for_images, # Pass new flag
                          )
                     try:
                         dl_count, skip_count, kept_originals_this_post, retryable_failures = post_processing_worker.process()

multipart_downloader.py

@@ -5,6 +5,7 @@ import hashlib
 import http.client
 import traceback
 import threading
+import queue # Import the missing 'queue' module
 from concurrent.futures import ThreadPoolExecutor, as_completed
 
 CHUNK_DOWNLOAD_RETRY_DELAY = 2 # Slightly reduced for faster retries if needed

readme.md

@@ -1,4 +1,4 @@
-<h1 align="center">Kemono Downloader v4.0.0</h1>
+<h1 align="center">Kemono Downloader v4.1.1</h1>
 
 <div align="center">
   <img src="https://github.com/Yuvi9587/Kemono-Downloader/blob/main/Read.png" alt="Kemono Downloader"/>
@@ -11,9 +11,49 @@ Built with **PyQt5**, this tool is ideal for users who want deep filtering, cust
 
 ---
 
-##  What's New in v4.0.0?
+##  What's New in v4.1.1? - Enhanced Image Discovery & Audio Filtering
 
-Version 3.5.0 focuses on enhancing access to content and providing even smarter organization:
+Version 4.1.1 brings significant enhancements, including smarter image capture from post content and a dedicated filter mode for audio files.
+
+###  "Scan Content for Images" Feature
+
+- **Enhanced Image Discovery:** A new checkbox, "**Scan Content for Images**," has been added to the UI (grouped with "Download Thumbnails Only" and "Compress Large Images").
+- **How it Works:**
+    - When enabled, the downloader meticulously scans the HTML content of each post's description or body.
+    - It searches for images in two main ways:
+        - **Directly linked absolute URLs** (e.g., `https://externalsite.com/image.png`) that end with a common image extension (jpg, png, gif, etc.).
+        - **Images embedded using HTML `<img>` tags.** The downloader extracts the `src` attribute from these tags and can resolve various path types:
+            - Absolute URLs (e.g., `http://...` or `https://...`)
+            - Protocol-relative URLs (e.g., `//cdn.example.com/image.jpg`)
+            - Root-relative paths (e.g., `/data/user_content/image.gif`), which are resolved against the site's base URL (like `https://kemono.su/data/user_content/image.gif`).
+    - This is particularly useful for capturing images that are part of the post's narrative but not formally listed in the API's file or attachment sections.
+- **Default State:** This option is **unchecked by default**.
+- **Key Interaction with "Download Thumbnails Only":** This new feature works closely with the existing "Download Thumbnails Only" option:
+    - If you enable "Download Thumbnails Only":
+        - The "Scan Content for Images" checkbox will **automatically become checked and disabled** (locked).
+        - The downloader then **exclusively downloads images discovered through the content scan**. Any API-listed thumbnails are bypassed, giving priority to images embedded directly in the post.
+    - If you disable "Download Thumbnails Only":
+        - The "Scan Content for Images" checkbox will become **enabled again and revert to being unchecked**. You can then manually enable it if you wish to scan content without being in thumbnail-only mode.
+
+This feature ensures a more comprehensive download experience, especially for posts where images are integrated directly into the text.
+
+### New "🎧 Only Audio" Filter Mode
+
+Alongside image discovery, v4.1.1 also introduces/enhances a dedicated filter mode for audio enthusiasts:
+
+-   **Focused Audio Downloads:** The "🎧 Only Audio" option in the "Filter Files" radio button group allows you to download exclusively common audio file types. This includes formats like MP3, WAV, FLAC, M4A, OGG, and more.
+-   **Streamlined UI:** When "🎧 Only Audio" mode is active:
+    -   Irrelevant UI options such as the "Skip Scope" button (for word-based post/file skipping) and the "Multi-part Download" toggle are hidden to simplify the interface.
+    -   The "Show External Links in Log" checkbox is automatically disabled, as link extraction is not the focus of this mode.
+-   **Archive Handling:** Unlike the "📦 Only Archives" mode (which disables archive skipping), the "Skip .zip" and "Skip .rar" checkboxes remain enabled and configurable when "🎧 Only Audio" is selected. This gives you the flexibility to also exclude any archives encountered while in audio-only mode if desired.
+-   **Purpose:** This mode is perfect for users who primarily want to collect audio tracks, podcasts, or sound effects from posts without downloading other media types.
+
+
+---
+
+##  Previous Update: What's New in v4.0.1?
+
+Version 4.0.1 focuses on enhancing access to content and providing even smarter organization:
 
 ###  Cookie Management
 
@@ -71,13 +111,30 @@ This field allows for dynamic filtering for the current download session and pro
 - **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.
+- **Using Known Names to Populate Filters (via "Add to Filter" Button):**
+  - Next to the "Add" button in the `Known.txt` management section, a "⤵️ Add to Filter" button provides a quick way to use your existing known names.
+  - Clicking this opens a popup window displaying all entries from your `Known.txt` file, each with a checkbox.
+  - The popup includes:
+    - A search bar to quickly filter the list of names.
+    - "Select All" and "Deselect All" buttons for convenience.
+  - After selecting the desired names, click "Add Selected".
+  - The chosen names will be inserted into the "Filter by Character(s)" input field.
+  - **Important Formatting:** If a selected entry from `Known.txt` is a group (e.g., originally `(Boa Hancock)` in `Known.txt`, which implies aliases "Boa" and "Hancock"), it will be added to the filter field as `(Boa, Hancock)~`. Simple names are added as-is.
+
 
 ---
 ##  What's in v3.5.0? (Previous Update)
-This version brings significant enhancements to manga/comic downloading, filtering capabilities, and user experience:
+This version brought significant enhancements to manga/comic downloading, filtering capabilities, and user experience:
 
 ###  Enhanced Manga/Comic Mode
 
+- **Optional Filename Prefix:**
+  - When using the "Date Based" or "Original File Name" manga styles, an optional prefix can be specified in the UI.
+  - This prefix will be prepended to each filename generated by these styles.
+  - **Example (Date Based):** If prefix is `MySeries_`, files become `MySeries_001.jpg`, `MySeries_002.png`, etc.
+  - **Example (Original File Name):** If prefix is `Comic_Vol1_`, an original file `page_01.jpg` becomes `Comic_Vol1_page_01.jpg`.
+  - This input field appears automatically when either of these two manga naming styles is selected.
+
 - **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.
@@ -87,6 +144,13 @@ This version brings significant enhancements to manga/comic downloading, filteri
   - **Guaranteed Order:** Disables multi-threading for post processing to ensure sequential accuracy.
 
   - Works alongside the existing "Post Title" and "Original File Name" styles.
+- **New "Title+G.Num (Post Title + Global Numbering)" Filename Style:**
+  - Ideal for series where you want each file to be prefixed by its post title but still maintain a global sequential number across all posts from a single download session.
+  - **Naming Convention:** Files are named using the cleaned post title as a prefix, followed by an underscore and a globally incrementing number (e.g., `Post Title_001.ext`, `Post Title_002.ext`).
+  - **Example:**
+    - Post "Chapter 1: The Adventure Begins" (contains 2 files: `imageA.jpg`, `imageB.png`) -> `Chapter 1 The Adventure Begins_001.jpg`, `Chapter 1 The Adventure Begins_002.png`
+    - Next Post "Chapter 2: New Friends" (contains 1 file: `cover.jpg`) -> `Chapter 2 New Friends_003.jpg`
+  - **Sequential Integrity:** Multithreading for post processing is automatically disabled when this style is selected to ensure the global numbering is strictly sequential.
 
 ---
 
@@ -169,6 +233,7 @@ This version brings significant enhancements to manga/comic downloading, filteri
     - `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`)
+  - A "⤵️ Add to Filter" button (near the `Known.txt` management UI) allows you to quickly populate this field by selecting from your existing `Known.txt` entries via a popup with search and checkbox selection.
   - See "Advanced `Known.txt` and Character Filtering" for full details.
   - **Filter Scopes:**
     - `Files`
@@ -200,6 +265,7 @@ This version brings significant enhancements to manga/comic downloading, filteri
   - `Name: Post Title (Default)`
   - `Name: Original File`
   - `Name: Date Based (New)`
+  - `Name: Title+G.Num (Post Title + Global Numbering)`
 
 - **Best With:** Character filters set to manga/series title
 
@@ -217,12 +283,17 @@ This version brings significant enhancements to manga/comic downloading, filteri
 ---
 
 ### Thumbnail & Compression Tools
-
-- **Download Thumbnails Only**
-
+- **Download Thumbnails Only:**
+  - Downloads small preview images from the API instead of full-sized files (if available).
+  - **Interaction with "Scan Content for Images" (New in v4.1.1):** When "Download Thumbnails Only" is active, "Scan Content for Images" is auto-enabled, and only images found by the content scan are downloaded. See "What's New in v4.1.1" for details.
+- **Scan Content for Images (New in v4.1.1):**
+  - A UI option to scan the HTML content of posts for embedded image URLs (from `<img>` tags or direct links).
+  - Resolves relative paths and helps capture images not listed in the API's formal attachments.
+  - See the "What's New in v4.1.1?" section for a comprehensive explanation.
 - **Compress to WebP** (via Pillow)
   - Converts large images to smaller WebP versions
 
+
 ---
 
 ###  Performance Features