diff --git a/downloader_utils.py b/downloader_utils.py index 7ffd68f..7552d08 100644 --- a/downloader_utils.py +++ b/downloader_utils.py @@ -9,7 +9,6 @@ import http.client import traceback from concurrent.futures import ThreadPoolExecutor, Future, CancelledError, as_completed import html - from PyQt5.QtCore import QObject, pyqtSignal, QThread, QMutex, QMutexLocker from urllib.parse import urlparse try: @@ -17,7 +16,6 @@ try: except ImportError: print("ERROR: Pillow library not found. Please install it: pip install Pillow") Image = None - try: from multipart_downloader import download_file_in_parts MULTIPART_DOWNLOADER_AVAILABLE = True @@ -25,37 +23,27 @@ except ImportError as e: print(f"Warning: multipart_downloader.py not found or import error: {e}. Multi-part downloads will be disabled.") MULTIPART_DOWNLOADER_AVAILABLE = False def download_file_in_parts(*args, **kwargs): return False, 0, None, None # Dummy function - 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" SKIP_SCOPE_POSTS = "posts" SKIP_SCOPE_BOTH = "both" - CHAR_SCOPE_TITLE = "title" CHAR_SCOPE_FILES = "files" CHAR_SCOPE_BOTH = "both" CHAR_SCOPE_COMMENTS = "comments" - FILE_DOWNLOAD_STATUS_SUCCESS = "success" FILE_DOWNLOAD_STATUS_SKIPPED = "skipped" FILE_DOWNLOAD_STATUS_FAILED_RETRYABLE_LATER = "failed_retry_later" - fastapi_app = None KNOWN_NAMES = [] # This will now store dicts: {'name': str, 'is_group': bool, 'aliases': list[str]} - 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', '.heic', '.heif', '.svg', '.ico', '.jfif', '.pjpeg', '.pjp', '.avif' @@ -71,7 +59,13 @@ AUDIO_EXTENSIONS = { '.mp3', '.wav', '.aac', '.flac', '.ogg', '.wma', '.m4a', '.opus', '.aiff', '.ape', '.mid', '.midi' } - +FOLDER_NAME_STOP_WORDS = { + "a", "alone", "am", "an", "and", "at", "be", "blues", "but", "by", "com", + "for", "grown", "hard", "he", "her", "his", "hitting", "i", "im", "in", "is", "it", "its", + "me", "much", "my", "net", "not", "of", "on", "or", "org", "our", "please", + "right", "s", "she", "so", "technically", "tell", "the", "their", "they", "this", + "to", "ve", "was", "we", "well", "were", "with", "www", "year", "you", "your", +} def parse_cookie_string(cookie_string): """Parses a 'name=value; name2=value2' cookie string into a dict.""" cookies = {} @@ -84,7 +78,6 @@ def parse_cookie_string(cookie_string): if name: # Ensure name is not empty cookies[name] = value return cookies if cookies else None - def load_cookies_from_netscape_file(filepath, logger_func): """Loads cookies from a Netscape-formatted cookies.txt file.""" cookies = {} @@ -108,86 +101,62 @@ def load_cookies_from_netscape_file(filepath, logger_func): except Exception as e: logger_func(f" đŸĒ Error parsing cookie file '{os.path.basename(filepath)}': {e}") return None - def is_title_match_for_character(post_title, character_name_filter): if not post_title or not character_name_filter: return False safe_filter = str(character_name_filter).strip() if not safe_filter: return False - pattern = r"(?i)\b" + re.escape(safe_filter) + r"\b" match_result = bool(re.search(pattern, post_title)) return match_result - def is_filename_match_for_character(filename, character_name_filter): if not filename or not character_name_filter: return False - safe_filter = str(character_name_filter).strip().lower() if not safe_filter: return False - match_result = safe_filter in filename.lower() return match_result - - def clean_folder_name(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) - + cleaned = cleaned.strip() # Initial strip + cleaned = re.sub(r'\s+', ' ', cleaned) # Condense multiple spaces + if cleaned: # Only process if not empty + words = cleaned.split(' ') + filtered_words = [word for word in words if word.lower() not in FOLDER_NAME_STOP_WORDS and word] + cleaned = ' '.join(filtered_words) + cleaned = cleaned.strip() # Strip again in case stop words were at ends 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() # 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 "" text = html.unescape(html_text) clean_pattern = re.compile('<.*?>') cleaned_text = re.sub(clean_pattern, '', text) return cleaned_text.strip() - def extract_folder_name_from_title(title, unwanted_keywords): if not title: return 'Uncategorized' title_lower = title.lower() @@ -198,8 +167,6 @@ def extract_folder_name_from_title(title, unwanted_keywords): return clean_token cleaned_full_title = clean_folder_name(title) return cleaned_full_title if cleaned_full_title else 'Uncategorized' - - def match_folders_from_title(title, names_to_match, unwanted_keywords): """ Matches folder names from a title based on a list of known name objects. @@ -210,13 +177,11 @@ def match_folders_from_title(title, names_to_match, unwanted_keywords): title_lower = title.lower() matched_cleaned_names = set() sorted_name_objects = sorted(names_to_match, key=lambda x: len(x.get("name", "")), reverse=True) - for name_obj in sorted_name_objects: primary_folder_name = name_obj.get("name") aliases = name_obj.get("aliases", []) if not primary_folder_name or not aliases: continue - for alias in aliases: alias_lower = alias.lower() if not alias_lower: continue @@ -227,46 +192,31 @@ def match_folders_from_title(title, names_to_match, unwanted_keywords): matched_cleaned_names.add(cleaned_primary_name) break # Found a match for this primary name via one of its aliases return sorted(list(matched_cleaned_names)) - - def is_image(filename): if not filename: return False _, ext = os.path.splitext(filename) return ext.lower() in IMAGE_EXTENSIONS - - def is_video(filename): if not filename: return False _, ext = os.path.splitext(filename) return ext.lower() in VIDEO_EXTENSIONS - - def is_zip(filename): if not filename: return False return filename.lower().endswith('.zip') - - def is_rar(filename): if not filename: return False return filename.lower().endswith('.rar') - def is_archive(filename): if not filename: return False _, 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 return '/post/' in urlparse(url).path - - def extract_post_info(url_string): service, user_id, post_id = None, None, None if not isinstance(url_string, str) or not url_string.strip(): return None, None, None @@ -275,18 +225,14 @@ def extract_post_info(url_string): domain = parsed_url.netloc.lower() is_kemono = any(d in domain for d in ['kemono.su', 'kemono.party']) is_coomer = any(d in domain for d in ['coomer.su', 'coomer.party']) - if not (is_kemono or is_coomer): return None, None, None - path_parts = [part for part in parsed_url.path.strip('/').split('/') if part] - if len(path_parts) >= 3 and path_parts[1].lower() == 'user': service = path_parts[0] user_id = path_parts[2] if len(path_parts) >= 5 and path_parts[3].lower() == 'post': post_id = path_parts[4] return service, user_id, post_id - if len(path_parts) >= 5 and path_parts[0].lower() == 'api' and \ path_parts[1].lower() == 'v1' and path_parts[3].lower() == 'user': service = path_parts[2] @@ -294,18 +240,13 @@ def extract_post_info(url_string): if len(path_parts) >= 7 and path_parts[5].lower() == 'post': post_id = path_parts[6] return service, user_id, post_id - except Exception as e: print(f"Debug: Exception during extract_post_info for URL '{url_string}': {e}") return None, None, None - - def prepare_cookies_for_request(use_cookie_flag, cookie_text_input, selected_cookie_file_path, app_base_dir, logger_func): """Prepares a cookie dictionary from text input or cookies.txt file.""" if not use_cookie_flag: return None - - # Attempt 1: Selected cookie file if selected_cookie_file_path: logger_func(f" đŸĒ Attempting to load cookies from selected file: '{os.path.basename(selected_cookie_file_path)}'...") cookies = load_cookies_from_netscape_file(selected_cookie_file_path, logger_func) @@ -313,13 +254,7 @@ def prepare_cookies_for_request(use_cookie_flag, cookie_text_input, selected_coo return cookies else: logger_func(f" ⚠ī¸ 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 @@ -329,9 +264,6 @@ def prepare_cookies_for_request(use_cookie_flag, cookie_text_input, selected_coo return cookies elif not selected_cookie_file_path: # Log failure only if we tried default as primary file method logger_func(f" ⚠ī¸ 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(" đŸĒ Using cookies from UI text input (as file methods failed or were not applicable).") cookies = parse_cookie_string(cookie_text_input) @@ -339,15 +271,12 @@ def prepare_cookies_for_request(use_cookie_flag, cookie_text_input, selected_coo return cookies else: logger_func(" ⚠ī¸ UI cookie text input was provided but was empty or invalid.") - logger_func(" đŸĒ 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 logger(" Fetch cancelled before request.") raise RuntimeError("Fetch operation cancelled by user.") - if pause_event and pause_event.is_set(): # type: ignore logger(" Post fetching paused...") while pause_event.is_set(): @@ -356,7 +285,6 @@ def fetch_posts_paginated(api_url_base, headers, offset, logger, cancellation_ev raise RuntimeError("Fetch operation cancelled by user.") time.sleep(0.5) logger(" Post fetching resumed.") - paginated_url = f'{api_url_base}?o={offset}' logger(f" Fetching: {paginated_url} (Page approx. {offset // 50 + 1})") try: @@ -380,12 +308,10 @@ def fetch_posts_paginated(api_url_base, headers, offset, logger, cancellation_ev raise RuntimeError(f"Error decoding JSON from offset {offset} ({paginated_url}): {e}. Response text: {response.text[:200]}") except Exception as e: raise RuntimeError(f"Unexpected error fetching offset {offset} ({paginated_url}): {e}") - def fetch_post_comments(api_domain, service, user_id, post_id, headers, logger, cancellation_event=None, pause_event=None, cookies_dict=None): if cancellation_event and cancellation_event.is_set(): logger(" Comment fetch cancelled before request.") raise RuntimeError("Comment fetch operation cancelled by user.") - if pause_event and pause_event.is_set(): # type: ignore logger(" Comment fetching paused...") while pause_event.is_set(): @@ -394,7 +320,6 @@ def fetch_post_comments(api_domain, service, user_id, post_id, headers, logger, raise RuntimeError("Comment fetch operation cancelled by user.") time.sleep(0.5) logger(" Comment fetching resumed.") - comments_api_url = f"https://{api_domain}/api/v1/{service}/user/{user_id}/post/{post_id}/comments" logger(f" Fetching comments: {comments_api_url}") try: @@ -418,29 +343,21 @@ def fetch_post_comments(api_domain, service, user_id, post_id, headers, logger, raise RuntimeError(f"Error decoding JSON from comments API for post {post_id} ({comments_api_url}): {e}. Response text: {response.text[:200]}") except Exception as e: raise RuntimeError(f"Unexpected error fetching comments for post {post_id} ({comments_api_url}): {e}") - def download_from_api(api_url_input, logger=print, start_page=None, end_page=None, manga_mode=False, cancellation_event=None, pause_event=None, use_cookie=False, cookie_text="", selected_cookie_file=None, app_base_dir=None): headers = {'User-Agent': 'Mozilla/5.0', 'Accept': 'application/json'} service, user_id, target_post_id = extract_post_info(api_url_input) - if cancellation_event and cancellation_event.is_set(): logger(" Download_from_api cancelled at start.") return - - # --- Moved Up: Parse api_domain and prepare cookies early --- 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']): logger(f"⚠ī¸ Unrecognized domain '{api_domain}' from input URL. Defaulting to kemono.su for API calls.") api_domain = "kemono.su" # Default domain if input is unusual - cookies_for_api = None if use_cookie and app_base_dir: # app_base_dir is needed for cookies.txt path cookies_for_api = prepare_cookies_for_request(use_cookie, cookie_text, selected_cookie_file, app_base_dir, logger) - # --- End Moved Up --- - - # --- New: Attempt direct fetch for specific post URL first --- if target_post_id: direct_post_api_url = f"https://{api_domain}/api/v1/{service}/user/{user_id}/post/{target_post_id}" logger(f" Attempting direct fetch for target post: {direct_post_api_url}") @@ -448,22 +365,15 @@ def download_from_api(api_url_input, logger=print, start_page=None, end_page=Non direct_response = requests.get(direct_post_api_url, headers=headers, timeout=(10, 30), cookies=cookies_for_api) direct_response.raise_for_status() direct_post_data = direct_response.json() - - # The direct endpoint might return a single post object or a list containing one post. - # Check if it's a list and take the first item, or use the object directly. if isinstance(direct_post_data, list) and direct_post_data: direct_post_data = direct_post_data[0] - - # Check if the data is a dict and contains a 'post' key (new format) if isinstance(direct_post_data, dict) and 'post' in direct_post_data and isinstance(direct_post_data['post'], dict): direct_post_data = direct_post_data['post'] # Extract the nested post data - if isinstance(direct_post_data, dict) and direct_post_data.get('id') == target_post_id: # Now check the extracted/direct dict logger(f" ✅ Direct fetch successful for post {target_post_id}.") yield [direct_post_data] # Yield the single post data as a list return # Exit the generator, no need to paginate else: - # Log more details about the unexpected response response_type = type(direct_post_data).__name__ response_snippet = str(direct_post_data)[:200] # Log first 200 chars logger(f" ⚠ī¸ Direct fetch for post {target_post_id} returned unexpected data (Type: {response_type}, Snippet: '{response_snippet}'). Falling back to pagination.") @@ -471,40 +381,25 @@ def download_from_api(api_url_input, logger=print, start_page=None, end_page=Non logger(f" ⚠ī¸ Direct fetch failed for post {target_post_id}: {e}. Falling back to pagination.") except Exception as e: logger(f" ⚠ī¸ Unexpected error during direct fetch for post {target_post_id}: {e}. Falling back to pagination.") - # --- End New: Attempt direct fetch --- - if not service or not user_id: logger(f"❌ Invalid URL or could not extract service/user: {api_url_input}") return - if target_post_id and (start_page or end_page): logger("⚠ī¸ Page range (start/end page) is ignored when a specific post URL is provided (searching all pages for the post).") - # start_page = end_page = None # Keep these potentially for the fallback pagination - is_creator_feed_for_manga = manga_mode and not target_post_id - - # api_domain is already parsed and validated above - api_base_url = f"https://{api_domain}/api/v1/{service}/user/{user_id}" - - page_size = 50 - if is_creator_feed_for_manga: logger(" Manga Mode: Fetching posts to sort by date (oldest processed first)...") all_posts_for_manga_mode = [] - current_offset_manga = 0 - # Determine starting page and offset for manga mode if start_page and start_page > 1: current_offset_manga = (start_page - 1) * page_size logger(f" Manga Mode: Starting fetch from page {start_page} (offset {current_offset_manga}).") elif start_page: # start_page is 1 logger(f" Manga Mode: Starting fetch from page 1 (offset 0).") - if end_page: logger(f" Manga Mode: Will fetch up to page {end_page}.") - while True: if pause_event and pause_event.is_set(): logger(" Manga mode post fetching paused...") # type: ignore @@ -517,7 +412,6 @@ def download_from_api(api_url_input, logger=print, start_page=None, end_page=Non if cancellation_event and cancellation_event.is_set(): logger(" Manga mode post fetching cancelled.") break - current_page_num_manga = (current_offset_manga // page_size) + 1 if end_page and current_page_num_manga > end_page: logger(f" Manga Mode: Reached specified end page ({end_page}). Stopping post fetch.") @@ -547,17 +441,13 @@ def download_from_api(api_url_input, logger=print, start_page=None, end_page=Non 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 Mode: Fetched {len(all_posts_for_manga_mode)} total posts. Sorting by publication date (oldest first)...") - # ... (rest of sorting and yielding logic for manga mode remains the same) ... def sort_key_tuple(post): published_date_str = post.get('published') added_date_str = post.get('added') post_id_str = post.get('id', "0") - primary_sort_val = "0000-00-00T00:00:00" # Default for missing dates (effectively oldest) if published_date_str: primary_sort_val = published_date_str @@ -566,33 +456,26 @@ def download_from_api(api_url_input, logger=print, start_page=None, end_page=Non primary_sort_val = added_date_str else: logger(f" ⚠ī¸ Post ID {post_id_str} missing both 'published' and 'added' dates. Placing at start of sort (using default earliest date).") - secondary_sort_val = 0 # Default for non-integer IDs try: secondary_sort_val = int(post_id_str) except ValueError: logger(f" ⚠ī¸ Post ID '{post_id_str}' is not a valid integer for secondary sorting, using 0.") - return (primary_sort_val, secondary_sort_val) - all_posts_for_manga_mode.sort(key=sort_key_tuple) # Sorts ascending by (date, id) - for i in range(0, len(all_posts_for_manga_mode), page_size): if cancellation_event and cancellation_event.is_set(): logger(" Manga mode post yielding cancelled.") break yield all_posts_for_manga_mode[i:i + page_size] return - current_page_num = 1 current_offset = 0 processed_target_post_flag = False - if start_page and start_page > 1 and not target_post_id: # Only apply start_page if not targeting a specific post directly current_offset = (start_page - 1) * page_size current_page_num = start_page logger(f" Starting from page {current_page_num} (calculated offset {current_offset}).") - while True: if pause_event and pause_event.is_set(): logger(" Post fetching loop paused...") # type: ignore @@ -605,14 +488,11 @@ def download_from_api(api_url_input, logger=print, start_page=None, end_page=Non if cancellation_event and cancellation_event.is_set(): logger(" Post fetching loop cancelled.") break - if target_post_id and processed_target_post_flag: break - if not target_post_id and end_page and current_page_num > end_page: logger(f"✅ Reached specified end page ({end_page}) for creator feed. Stopping.") break - try: posts_batch = fetch_posts_paginated(api_base_url, headers, current_offset, logger, cancellation_event, pause_event, cookies_dict=cookies_for_api) if not isinstance(posts_batch, list): @@ -628,7 +508,6 @@ def download_from_api(api_url_input, logger=print, start_page=None, end_page=Non logger(f"❌ Unexpected error fetching page {current_page_num} (offset {current_offset}): {e}") traceback.print_exc() break - if not posts_batch: if target_post_id and not processed_target_post_flag: # Only log this if we were searching for a specific post logger(f"❌ Target post {target_post_id} not found after checking all available pages (API returned no more posts at offset {current_offset}).") @@ -638,7 +517,6 @@ def download_from_api(api_url_input, logger=print, start_page=None, end_page=Non else: logger(f"✅ Reached end of posts (no more content from API at offset {current_offset}).") break - if target_post_id and not processed_target_post_flag: matching_post = next((p for p in posts_batch if str(p.get('id')) == str(target_post_id)), None) if matching_post: @@ -647,18 +525,13 @@ def download_from_api(api_url_input, logger=print, start_page=None, end_page=Non processed_target_post_flag = True elif not target_post_id: yield posts_batch - if processed_target_post_flag: break - current_offset += page_size # Increment by page_size for the next API call's 'o' parameter current_page_num += 1 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).") - - def get_link_platform(url): try: domain = urlparse(url).netloc.lower() @@ -672,7 +545,6 @@ def get_link_platform(url): 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' - parts = domain.split('.') if len(parts) >= 2: if parts[-2] not in ['com', 'org', 'net', 'gov', 'edu', 'co'] or len(parts) == 2: @@ -683,16 +555,12 @@ def get_link_platform(url): return domain return 'external' except Exception: return 'unknown' - - class PostProcessorSignals(QObject): progress_signal = pyqtSignal(str) file_download_status_signal = pyqtSignal(bool) external_link_signal = pyqtSignal(str, str, str, str) file_progress_signal = pyqtSignal(str, object) missed_character_post_signal = pyqtSignal(str, str) # New: post_title, reason - - class PostProcessorWorker: def __init__(self, post_data, download_root, known_names, filter_character_list, emitter, # Changed signals to emitter @@ -745,18 +613,15 @@ class PostProcessorWorker: if not self.emitter: raise ValueError("PostProcessorWorker requires an emitter (signals object or queue).") self.skip_current_file_flag = skip_current_file_flag - self.downloaded_files = downloaded_files if downloaded_files is not None else set() self.downloaded_file_hashes = downloaded_file_hashes if downloaded_file_hashes is not None else set() self.downloaded_files_lock = downloaded_files_lock if downloaded_files_lock is not None else threading.Lock() self.downloaded_file_hashes_lock = downloaded_file_hashes_lock if downloaded_file_hashes_lock is not None else threading.Lock() - self.skip_words_list = skip_words_list if skip_words_list is not None else [] self.skip_words_scope = skip_words_scope self.show_external_links = show_external_links self.extract_links_only = extract_links_only self.num_file_threads = num_file_threads - self.manga_mode_active = manga_mode_active self.manga_filename_style = manga_filename_style self.char_filter_scope = char_filter_scope @@ -771,12 +636,9 @@ class PostProcessorWorker: 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("⚠ī¸ Image compression disabled: Pillow library not found.") self.compress_images = False - def _emit_signal(self, signal_type_str, *payload_args): """Helper to emit signal either directly or via queue.""" if isinstance(self.emitter, queue.Queue): @@ -786,13 +648,10 @@ class PostProcessorWorker: signal_attr.emit(*payload_args) else: print(f"(Worker Log - Unrecognized Emitter for {signal_type_str}): {payload_args[0] if payload_args else ''}") - def logger(self, message): self._emit_signal('progress', message) - def check_cancel(self): return self.cancellation_event.is_set() - def _check_pause(self, context_message="Operation"): if self.pause_event and self.pause_event.is_set(): # type: ignore self.logger(f" {context_message} paused...") @@ -803,19 +662,16 @@ class PostProcessorWorker: time.sleep(0.5) if not self.check_cancel(): self.logger(f" {context_message} resumed.") return False # Not cancelled during pause - def _download_single_file(self, file_info, target_folder_path, headers, original_post_id_for_log, skip_event, # skip_event is threading.Event post_title="", file_index_in_post=0, num_files_in_this_post=1, manga_date_file_counter_ref=None): # Added manga_date_file_counter_ref was_original_name_kept_flag = False manga_global_file_counter_ref = None # Placeholder, will be passed from process() final_filename_saved_for_return = "" - def _get_current_character_filters(self): 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, post_title="", file_index_in_post=0, num_files_in_this_post=1, # Added manga_date_file_counter_ref manga_date_file_counter_ref=None, @@ -824,17 +680,14 @@ class PostProcessorWorker: was_original_name_kept_flag = False final_filename_saved_for_return = "" retry_later_details = None # For storing info if retryable failure - if self._check_pause(f"File download prep for '{file_info.get('name', 'unknown file')}'"): return 0, 1, "", False if self.check_cancel() or (skip_event and skip_event.is_set()): return 0, 1, "", False - file_url = file_info.get('url') cookies_to_use_for_file = None if self.use_cookie: # This flag comes from the checkbox 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) api_original_filename = file_info.get('_original_name_for_log', file_info.get('name')) filename_to_save_in_main_path = "" - if forced_filename_override: filename_to_save_in_main_path = forced_filename_override self.logger(f" Retrying with forced filename: '{filename_to_save_in_main_path}'") @@ -845,21 +698,17 @@ class PostProcessorWorker: if skip_word.lower() in filename_to_check_for_skip_words: 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 - original_filename_cleaned_base, original_ext = os.path.splitext(clean_filename(api_original_filename)) if not original_ext.startswith('.'): original_ext = '.' + original_ext if original_ext else '' - 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"⚠ī¸ 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(): @@ -877,14 +726,12 @@ class PostProcessorWorker: self.logger(f"⚠ī¸ Manga mode (Post Title Style): Post title missing for post {original_post_id_for_log}. Using cleaned original filename '{filename_to_save_in_main_path}'.") elif self.manga_filename_style == STYLE_DATE_BASED: current_thread_name = threading.current_thread().name - if manga_date_file_counter_ref is not None and len(manga_date_file_counter_ref) == 2: counter_val_for_filename = -1 counter_lock = manga_date_file_counter_ref[1] with counter_lock: counter_val_for_filename = manga_date_file_counter_ref[0] 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()) @@ -905,7 +752,6 @@ 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") filename_to_save_in_main_path = f"{cleaned_post_title_base_for_global}_{counter_val_for_filename:03d}{original_ext}" else: @@ -914,7 +760,6 @@ class PostProcessorWorker: else: self.logger(f"⚠ī¸ Manga mode: Unknown filename style '{self.manga_filename_style}'. Defaulting to original filename for '{api_original_filename}'.") filename_to_save_in_main_path = clean_filename(api_original_filename) - if not filename_to_save_in_main_path: filename_to_save_in_main_path = f"manga_file_{original_post_id_for_log}_{file_index_in_post + 1}{original_ext}" self.logger(f"⚠ī¸ Manga mode: Generated filename was empty. Using generic fallback: '{filename_to_save_in_main_path}'.") @@ -922,7 +767,6 @@ class PostProcessorWorker: else: filename_to_save_in_main_path = clean_filename(api_original_filename) was_original_name_kept_flag = False - 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) modified_base_name = base_name_for_removal @@ -930,7 +774,6 @@ 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) - # 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 @@ -938,13 +781,11 @@ class PostProcessorWorker: filename_to_save_in_main_path = modified_base_name + ext_for_removal else: filename_to_save_in_main_path = base_name_for_removal + ext_for_removal - if not self.download_thumbnails: 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: self.logger(f" -> Filter Skip (Archive Mode): '{api_original_filename}' (Not an Archive).") @@ -961,7 +802,6 @@ class PostProcessorWorker: 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).") return 0, 1, api_original_filename, False, FILE_DOWNLOAD_STATUS_SKIPPED, None @@ -981,7 +821,6 @@ class PostProcessorWorker: total_size_bytes = 0 download_successful_flag = False last_exception_for_retry_later = None - for attempt_num_single_stream in range(max_retries + 1): 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 @@ -989,18 +828,14 @@ class PostProcessorWorker: 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) response.raise_for_status() total_size_bytes = int(response.headers.get('Content-Length', 0)) - num_parts_for_file = min(self.num_file_threads, MAX_PARTS_FOR_MULTIPART_DOWNLOAD) 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 'bytes' in response.headers.get('Accept-Ranges', '').lower()) - if self._check_pause(f"Multipart decision for '{api_original_filename}'"): break # Check pause before potentially long operation if attempt_multipart: response.close() @@ -1023,13 +858,11 @@ class PostProcessorWorker: self.logger(f" Multi-part download attempt failed for '{api_original_filename}'. Retrying with single stream.") else: download_successful_flag = False; break - self.logger(f"âŦ‡ī¸ Downloading (Single Stream): '{api_original_filename}' (Size: {total_size_bytes / (1024*1024):.2f} MB if known) [Base Name: '{filename_to_save_in_main_path}']") file_content_buffer = BytesIO() current_attempt_downloaded_bytes = 0 md5_hasher = hashlib.md5() last_progress_time = time.time() - for chunk in response.iter_content(chunk_size=1 * 1024 * 1024): if self._check_pause(f"Chunk download for '{api_original_filename}'"): break if self.check_cancel() or (skip_event and skip_event.is_set()): break @@ -1039,10 +872,8 @@ class PostProcessorWorker: if time.time() - last_progress_time > 1 and total_size_bytes > 0: self._emit_signal('file_progress', api_original_filename, (current_attempt_downloaded_bytes, total_size_bytes)) last_progress_time = time.time() - if self.check_cancel() or (skip_event and skip_event.is_set()) or (self.pause_event and self.pause_event.is_set()): if file_content_buffer: file_content_buffer.close(); break - if current_attempt_downloaded_bytes > 0 or (total_size_bytes == 0 and response.status_code == 200): calculated_file_hash = md5_hasher.hexdigest() downloaded_size_bytes = current_attempt_downloaded_bytes @@ -1051,7 +882,6 @@ class PostProcessorWorker: download_successful_flag = True; break else: if file_content_buffer: file_content_buffer.close() - except (requests.exceptions.ConnectionError, requests.exceptions.Timeout, http.client.IncompleteRead) as e: self.logger(f" ❌ Download Error (Retryable): {api_original_filename}. Error: {e}") last_exception_for_retry_later = e # Store this specific exception @@ -1072,12 +902,10 @@ class PostProcessorWorker: 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 self._emit_signal('file_progress', api_original_filename, (downloaded_size_bytes, final_total_for_progress)) - if self.check_cancel() or (skip_event and skip_event.is_set()) or (self.pause_event and self.pause_event.is_set() and not download_successful_flag): self.logger(f" ⚠ī¸ Download process interrupted for {api_original_filename}.") if file_content_bytes: file_content_bytes.close() return 0, 1, filename_to_save_in_main_path, was_original_name_kept_flag, FILE_DOWNLOAD_STATUS_SKIPPED, None - if not download_successful_flag: self.logger(f"❌ Download failed for '{api_original_filename}' after {max_retries + 1} attempts.") if file_content_bytes: file_content_bytes.close() @@ -1097,7 +925,6 @@ class PostProcessorWorker: } return 0, 1, filename_to_save_in_main_path, was_original_name_kept_flag, FILE_DOWNLOAD_STATUS_FAILED_RETRYABLE_LATER, retry_later_details return 0, 1, filename_to_save_in_main_path, was_original_name_kept_flag, FILE_DOWNLOAD_STATUS_SKIPPED, None # Generic failure - if self._check_pause(f"Post-download hash check for '{api_original_filename}'"): return 0, 1, filename_to_save_in_main_path, was_original_name_kept_flag, FILE_DOWNLOAD_STATUS_SKIPPED, None with self.downloaded_file_hashes_lock: if calculated_file_hash in self.downloaded_file_hashes: @@ -1112,7 +939,6 @@ class PostProcessorWorker: return 0, 1, filename_to_save_in_main_path, was_original_name_kept_flag, FILE_DOWNLOAD_STATUS_SKIPPED, None effective_save_folder = target_folder_path # Default: main character/post folder filename_after_styling_and_word_removal = filename_to_save_in_main_path - try: # Ensure the chosen save folder (main or Duplicate) exists os.makedirs(effective_save_folder, exist_ok=True) except OSError as e: @@ -1124,7 +950,6 @@ class PostProcessorWorker: return 0, 1, api_original_filename, False, FILE_DOWNLOAD_STATUS_SKIPPED, None data_to_write_after_compression = file_content_bytes filename_after_compression = filename_after_styling_and_word_removal - is_img_for_compress_check = is_image(api_original_filename) if is_img_for_compress_check and self.compress_images and Image and downloaded_size_bytes > (1.5 * 1024 * 1024): self.logger(f" Compressing '{api_original_filename}' ({downloaded_size_bytes / (1024*1024):.2f} MB)...") @@ -1137,7 +962,6 @@ class PostProcessorWorker: compressed_bytes_io = BytesIO() img_obj.save(compressed_bytes_io, format='WebP', quality=80, method=4) compressed_size = compressed_bytes_io.getbuffer().nbytes - if compressed_size < downloaded_size_bytes * 0.9: # If significantly smaller self.logger(f" Compression success: {compressed_size / (1024*1024):.2f} MB.") data_to_write_after_compression = compressed_bytes_io; data_to_write_after_compression.seek(0) @@ -1161,9 +985,7 @@ class PostProcessorWorker: self.logger(f" Applied numeric suffix in '{os.path.basename(effective_save_folder)}': '{final_filename_on_disk}' (was '{filename_after_compression}')") if self._check_pause(f"File saving for '{final_filename_on_disk}'"): return 0, 1, final_filename_on_disk, was_original_name_kept_flag, FILE_DOWNLOAD_STATUS_SKIPPED, None final_save_path = os.path.join(effective_save_folder, final_filename_on_disk) - try: - if data_to_write_after_compression is file_content_bytes and not isinstance(file_content_bytes, BytesIO): original_part_file_actual_path = file_content_bytes.name file_content_bytes.close() # Close handle first @@ -1178,7 +1000,6 @@ class PostProcessorWorker: if os.path.exists(original_part_file_actual_path): try: os.remove(original_part_file_actual_path) except OSError as e_rem: self.logger(f" -> Failed to remove .part after compression: {e_rem}") - with self.downloaded_file_hashes_lock: self.downloaded_file_hashes.add(calculated_file_hash) with self.downloaded_files_lock: self.downloaded_files.add(filename_to_save_in_main_path) # Track by logical name final_filename_saved_for_return = final_filename_on_disk @@ -1199,43 +1020,33 @@ class PostProcessorWorker: if not file_content_bytes.closed: # Check if already closed file_content_bytes.close() except Exception: pass # Ignore errors on close if already handled - - def process(self): if self._check_pause(f"Post processing for ID {self.post.get('id', 'N/A')}"): return 0,0,[], [] if self.check_cancel(): return 0, 0, [], [] current_character_filters = self._get_current_character_filters() - kept_original_filenames_for_log = [] retryable_failures_this_post = [] # New list to store retryable failure details total_downloaded_this_post = 0 total_skipped_this_post = 0 - 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"""]*>(.*?)""", 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', []) post_content_html = post_data.get('content', '') - self.logger(f"\n--- Processing Post {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 char_filter_that_matched_title = None post_is_candidate_by_comment_char_match = False post_is_candidate_by_file_char_match_in_comment_scope = False char_filter_that_matched_file_in_comment_scope = None char_filter_that_matched_comment = None - if current_character_filters and \ (self.char_filter_scope == CHAR_SCOPE_TITLE or self.char_filter_scope == CHAR_SCOPE_BOTH): if self._check_pause(f"Character title filter for post {post_id}"): return 0, num_potential_files_in_post, [], [] @@ -1245,9 +1056,7 @@ class PostProcessorWorker: if filter_item_obj["is_group"]: if filter_item_obj["name"] not in terms_to_check_for_title: terms_to_check_for_title.append(filter_item_obj["name"]) - unique_terms_for_title_check = list(set(terms_to_check_for_title)) - for term_to_match in unique_terms_for_title_check: match_found_for_term = is_title_match_for_character(post_title, term_to_match) if match_found_for_term: @@ -1260,19 +1069,15 @@ class PostProcessorWorker: 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 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: all_files_from_post_api_for_char_check.append({'_original_name_for_log': original_api_name}) - for att_info in post_attachments: if isinstance(att_info, dict) and att_info.get('path'): original_api_att_name = att_info.get('name') or os.path.basename(att_info['path'].lstrip('/')) 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: 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}"): return 0, num_potential_files_in_post, [], [] @@ -1284,7 +1089,6 @@ class PostProcessorWorker: terms_to_check = list(filter_item_obj["aliases"]) if filter_item_obj["is_group"] and filter_item_obj["name"] not in terms_to_check: terms_to_check.append(filter_item_obj["name"]) - for term_to_match in terms_to_check: if is_filename_match_for_character(current_api_original_filename_for_check, term_to_match): post_is_candidate_by_file_char_match_in_comment_scope = True @@ -1294,7 +1098,6 @@ class PostProcessorWorker: if post_is_candidate_by_file_char_match_in_comment_scope: break 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 not post_is_candidate_by_file_char_match_in_comment_scope: if self._check_pause(f"Comment check for post {post_id}"): return 0, num_potential_files_in_post, [], [] @@ -1305,7 +1108,6 @@ class PostProcessorWorker: if not any(d in api_domain_for_comments.lower() for d in ['kemono.su', 'kemono.party', 'coomer.su', 'coomer.party']): self.logger(f"⚠ī¸ 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" - 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, # Pass pause_event @@ -1319,15 +1121,12 @@ class PostProcessorWorker: if self.check_cancel(): break raw_comment_content = comment_item.get('content', '') if not raw_comment_content: continue - cleaned_comment_text = strip_html_tags(raw_comment_content) if not cleaned_comment_text.strip(): continue - for filter_item_obj in current_character_filters: terms_to_check_comment = list(filter_item_obj["aliases"]) if filter_item_obj["is_group"] and filter_item_obj["name"] not in terms_to_check_comment: terms_to_check_comment.append(filter_item_obj["name"]) - for term_to_match_comment in terms_to_check_comment: if is_title_match_for_character(cleaned_comment_text, term_to_match_comment): # Re-use title matcher post_is_candidate_by_comment_char_match = True @@ -1339,7 +1138,6 @@ class PostProcessorWorker: if post_is_candidate_by_comment_char_match: break else: self.logger(f" No comments found or fetched for post {post_id} to check against character filters.") - except RuntimeError as e_fetch_comment: self.logger(f" ⚠ī¸ Error fetching or processing comments for post {post_id}: {e_fetch_comment}") except Exception as e_generic_comment: @@ -1359,7 +1157,6 @@ class PostProcessorWorker: if self.emitter and hasattr(self.emitter, 'missed_character_post_signal'): # Check emitter self._emit_signal('missed_character_post', post_title, "No character match in files or comments (Comments scope)") return 0, num_potential_files_in_post, [], [] - if self.skip_words_list and (self.skip_words_scope == SKIP_SCOPE_POSTS or self.skip_words_scope == SKIP_SCOPE_BOTH): if self._check_pause(f"Skip words (post title) for post {post_id}"): return 0, num_potential_files_in_post, [], [] post_title_lower = post_title.lower() @@ -1367,24 +1164,20 @@ class PostProcessorWorker: if skip_word.lower() in post_title_lower: self.logger(f" -> Skip Post (Keyword in Title '{skip_word}'): '{post_title[:50]}...'. Scope: {self.skip_words_scope}") return 0, num_potential_files_in_post, [], [] - 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)") return 0, num_potential_files_in_post, [], [] - if not isinstance(post_attachments, list): self.logger(f"⚠ī¸ Corrupt attachment data for post {post_id} (expected list, got {type(post_attachments)}). Skipping attachments.") post_attachments = [] - base_folder_names_for_post_content = [] if not self.extract_links_only and self.use_subfolders: if self._check_pause(f"Subfolder determination for post {post_id}"): return 0, num_potential_files_in_post, [] primary_char_filter_for_folder = None # type: ignore log_reason_for_folder = "" - if self.char_filter_scope == CHAR_SCOPE_COMMENTS and char_filter_that_matched_comment: if post_is_candidate_by_file_char_match_in_comment_scope and char_filter_that_matched_file_in_comment_scope: primary_char_filter_for_folder = char_filter_that_matched_file_in_comment_scope @@ -1407,7 +1200,6 @@ class PostProcessorWorker: if not base_folder_names_for_post_content or not base_folder_names_for_post_content[0]: base_folder_names_for_post_content = [clean_folder_name(post_title if post_title else "untitled_creator_content")] self.logger(f" Base folder name(s) for post content (Generic title parsing - no char filters): {', '.join(base_folder_names_for_post_content)}") - if not self.extract_links_only and self.use_subfolders and self.skip_words_list: if self._check_pause(f"Folder keyword skip check for post {post_id}"): return 0, num_potential_files_in_post, [] for folder_name_to_check in base_folder_names_for_post_content: # type: ignore @@ -1416,7 +1208,6 @@ class PostProcessorWorker: matched_skip = next((sw for sw in self.skip_words_list if sw.lower() in folder_name_to_check.lower()), "unknown_skip_word") 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: # type: ignore if self._check_pause(f"External link extraction for post {post_id}"): return 0, num_potential_files_in_post, [], [] try: @@ -1425,39 +1216,29 @@ class PostProcessorWorker: link_url = match.group(1).strip() link_url = html.unescape(link_url) # Decode HTML entities in the URL link_inner_text = match.group(2) - if not any(ext in link_url.lower() for ext in ['.css', '.js', '.ico', '.xml', '.svg']) \ and not link_url.startswith('javascript:') \ and link_url not in unique_links_data: - clean_link_text = re.sub(r'<.*?>', '', link_inner_text) clean_link_text = html.unescape(clean_link_text).strip() - display_text = clean_link_text if clean_link_text else "[Link]" unique_links_data[link_url] = display_text - links_emitted_count = 0 scraped_platforms = {'kemono', 'coomer', 'patreon'} - for link_url, link_text in unique_links_data.items(): platform = get_link_platform(link_url) if platform not in scraped_platforms: self._emit_signal('external_link', post_title, link_text, link_url, platform) links_emitted_count +=1 - if links_emitted_count > 0: self.logger(f" 🔗 Found {links_emitted_count} potential external link(s) in post content.") except Exception as e: self.logger(f"⚠ī¸ Error parsing post content for links: {e}\n{traceback.format_exc(limit=2)}") - if self.extract_links_only: self.logger(f" Extract Links Only mode: Finished processing post {post_id} for links.") return 0, 0, [], [] - 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 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) @@ -1469,7 +1250,6 @@ class PostProcessorWorker: '_is_thumbnail': is_image(original_api_name) # Mark if it's an image from API }) else: self.logger(f" ⚠ī¸ 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'): # Ensure att_info is a dict att_path = att_info['path'].lstrip('/') @@ -1483,30 +1263,20 @@ class PostProcessorWorker: }) else: self.logger(f" ⚠ī¸ Skipping attachment {idx+1} for post {post_id}: Missing name (Path: {att_path})") else: self.logger(f" ⚠ī¸ 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 tags (captures src content) img_tag_src_pattern_str = r"""]*?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 @@ -1514,16 +1284,13 @@ class PostProcessorWorker: 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: @@ -1535,7 +1302,6 @@ class PostProcessorWorker: 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, @@ -1549,42 +1315,28 @@ class PostProcessorWorker: 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: 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() return [int(text) if text.isdigit() else text for text in re.split('([0-9]+)', name)] - all_files_from_post_api.sort(key=natural_sort_key_for_files) self.logger(f" Manga Date Mode: Sorted {len(all_files_from_post_api)} files within post {post_id} by original name for sequential numbering.") - - if not all_files_from_post_api: self.logger(f" No files found to download for post {post_id}.") return 0, 0, [], [] - files_to_download_info_list = [] processed_original_filenames_in_this_post = set() for file_info in all_files_from_post_api: @@ -1596,27 +1348,19 @@ class PostProcessorWorker: files_to_download_info_list.append(file_info) if current_api_original_filename: processed_original_filenames_in_this_post.add(current_api_original_filename) - if not files_to_download_info_list: self.logger(f" All files for post {post_id} were duplicate original names or skipped earlier.") return 0, total_skipped_this_post, [], [] - - num_files_in_this_post_for_naming = len(files_to_download_info_list) self.logger(f" Identified {num_files_in_this_post_for_naming} unique original file(s) for potential download from post {post_id}.") - - with ThreadPoolExecutor(max_workers=self.num_file_threads, thread_name_prefix=f'P{post_id}File_') as file_pool: futures_list = [] for file_idx, file_info_to_dl in enumerate(files_to_download_info_list): if self._check_pause(f"File processing loop for post {post_id}, file {file_idx}"): break if self.check_cancel(): break - current_api_original_filename = file_info_to_dl.get('_original_name_for_log') - file_is_candidate_by_char_filter_scope = False char_filter_info_that_matched_file = None - if not current_character_filters: file_is_candidate_by_char_filter_scope = True else: @@ -1626,7 +1370,6 @@ class PostProcessorWorker: if filter_item_obj["is_group"] and filter_item_obj["name"] not in terms_to_check_for_file: terms_to_check_for_file.append(filter_item_obj["name"]) unique_terms_for_file_check = list(set(terms_to_check_for_file)) - for term_to_match in unique_terms_for_file_check: if is_filename_match_for_character(current_api_original_filename, term_to_match): file_is_candidate_by_char_filter_scope = True @@ -1650,7 +1393,6 @@ class PostProcessorWorker: if filter_item_obj_both_file["is_group"] and filter_item_obj_both_file["name"] not in terms_to_check_for_file_both: terms_to_check_for_file_both.append(filter_item_obj_both_file["name"]) unique_terms_for_file_both_check = list(set(terms_to_check_for_file_both)) - for term_to_match in unique_terms_for_file_both_check: if is_filename_match_for_character(current_api_original_filename, term_to_match): file_is_candidate_by_char_filter_scope = True @@ -1667,14 +1409,11 @@ class PostProcessorWorker: file_is_candidate_by_char_filter_scope = True char_filter_info_that_matched_file = char_filter_that_matched_comment # Use the filter that matched comments self.logger(f" File '{current_api_original_filename}' is candidate because post comments matched char filter (Overall Scope: Comments).") - if not file_is_candidate_by_char_filter_scope: self.logger(f" -> Skip File (Char Filter Scope '{self.char_filter_scope}'): '{current_api_original_filename}' no match.") total_skipped_this_post += 1 continue - 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 if self.target_post_id_from_initial_url and self.custom_folder_name: @@ -1685,17 +1424,13 @@ class PostProcessorWorker: char_title_subfolder_name = clean_folder_name(char_filter_that_matched_title["name"]) elif base_folder_names_for_post_content: char_title_subfolder_name = base_folder_names_for_post_content[0] - if char_title_subfolder_name: current_path_for_file = os.path.join(current_path_for_file, char_title_subfolder_name) - if self.use_post_subfolders: cleaned_title_for_subfolder = clean_folder_name(post_title) post_specific_subfolder_name = cleaned_title_for_subfolder # Use only the cleaned title current_path_for_file = os.path.join(current_path_for_file, post_specific_subfolder_name) - target_folder_path_for_this_file = current_path_for_file - manga_date_counter_to_pass = None manga_global_counter_to_pass = None if self.manga_mode_active: @@ -1703,7 +1438,6 @@ class PostProcessorWorker: manga_date_counter_to_pass = self.manga_date_file_counter_ref elif self.manga_filename_style == STYLE_POST_TITLE_GLOBAL_NUMBERING: manga_global_counter_to_pass = self.manga_global_file_counter_ref if self.manga_global_file_counter_ref is not None else self.manga_date_file_counter_ref - futures_list.append(file_pool.submit( self._download_single_file, file_info_to_dl, @@ -1717,7 +1451,6 @@ class PostProcessorWorker: file_index_in_post=file_idx, # Changed to keyword argument num_files_in_this_post=num_files_in_this_post_for_naming # Changed to keyword argument )) - for future in as_completed(futures_list): if self.check_cancel(): for f_to_cancel in futures_list: @@ -1739,13 +1472,9 @@ class PostProcessorWorker: self.logger(f"❌ File download task for post {post_id} resulted in error: {exc_f}") total_skipped_this_post += 1 self._emit_signal('file_progress', "", None) - if self.check_cancel(): self.logger(f" Post {post_id} processing interrupted/cancelled."); else: self.logger(f" Post {post_id} Summary: Downloaded={total_downloaded_this_post}, Skipped Files={total_skipped_this_post}") - return total_downloaded_this_post, total_skipped_this_post, kept_original_filenames_for_log, retryable_failures_this_post - - class DownloadThread(QThread): progress_signal = pyqtSignal(str) # Already QObject, no need to change add_character_prompt_signal = pyqtSignal(str) @@ -1755,8 +1484,6 @@ class DownloadThread(QThread): file_progress_signal = pyqtSignal(str, object) retryable_file_failed_signal = pyqtSignal(list) # New: list of retry_details dicts missed_character_post_signal = pyqtSignal(str, str) # New: post_title, reason - - def __init__(self, api_url_input, output_dir, known_names_copy, cancellation_event, pause_event, filter_character_list=None, dynamic_character_filter_holder=None, # Added pause_event and holder @@ -1814,10 +1541,8 @@ class DownloadThread(QThread): self.downloaded_files_lock = downloaded_files_lock self.downloaded_file_hashes = downloaded_file_hashes self.downloaded_file_hashes_lock = downloaded_file_hashes_lock - self._add_character_response = None self.prompt_mutex = QMutex() - self.show_external_links = show_external_links self.extract_links_only = extract_links_only self.num_file_threads_for_worker = num_file_threads_for_worker @@ -1842,13 +1567,10 @@ class DownloadThread(QThread): if self.compress_images and Image is None: self.logger("⚠ī¸ Image compression disabled: Pillow library not found (DownloadThread).") self.compress_images = False - def logger(self, message): self.progress_signal.emit(str(message)) - def isInterruptionRequested(self): return self.cancellation_event.is_set() or super().isInterruptionRequested() - def _check_pause_self(self, context_message="DownloadThread operation"): if self.pause_event and self.pause_event.is_set(): self.logger(f" {context_message} paused...") @@ -1859,14 +1581,11 @@ class DownloadThread(QThread): time.sleep(0.5) if not self.isInterruptionRequested(): self.logger(f" {context_message} resumed.") return False - def skip_file(self): if self.isRunning() and self.skip_current_file_flag: self.logger("⏭ī¸ Skip requested for current file (single-thread mode).") self.skip_current_file_flag.set() else: self.logger("ℹī¸ Skip file: No download active or skip flag not available for current context.") - - def run(self): grand_total_downloaded_files = 0 grand_total_skipped_files = 0 @@ -1883,7 +1602,6 @@ class DownloadThread(QThread): elif self.service and self.user_id: creator_based_folder_name = clean_folder_name(self.user_id) series_scan_dir = os.path.join(series_scan_dir, creator_based_folder_name) - highest_num = 0 if os.path.isdir(series_scan_dir): self.logger(f"ℹī¸ [Thread] Manga Date Mode: Scanning for existing files in '{series_scan_dir}'...") @@ -1895,12 +1613,8 @@ class DownloadThread(QThread): current_manga_date_file_counter_ref = [highest_num + 1, threading.Lock()] self.logger(f"ℹī¸ [Thread] Manga Date Mode: Initialized counter at {current_manga_date_file_counter_ref[0]}.") elif self.manga_mode_active and self.manga_filename_style == STYLE_POST_TITLE_GLOBAL_NUMBERING and not self.extract_links_only and current_manga_date_file_counter_ref is None: # Use current_manga_date_file_counter_ref for STYLE_POST_TITLE_GLOBAL_NUMBERING as well - # For global numbering, we always start from 1 for the session unless a ref is passed. - # If you need to resume global numbering across sessions, similar scanning logic would be needed. - # For now, it starts at 1 per session if no ref is provided. current_manga_date_file_counter_ref = [1, threading.Lock()] # Start global numbering at 1 self.logger(f"ℹī¸ [Thread] Manga Title+GlobalNum Mode: Initialized counter at {current_manga_date_file_counter_ref[0]}.") - worker_signals_obj = PostProcessorSignals() try: worker_signals_obj.progress_signal.connect(self.progress_signal) @@ -1908,7 +1622,6 @@ class DownloadThread(QThread): worker_signals_obj.file_progress_signal.connect(self.file_progress_signal) worker_signals_obj.external_link_signal.connect(self.external_link_signal) worker_signals_obj.missed_character_post_signal.connect(self.missed_character_post_signal) - self.logger(" Starting post fetch (single-threaded download process)...") post_generator = download_from_api( self.api_url_input, @@ -1923,14 +1636,12 @@ class DownloadThread(QThread): selected_cookie_file=self.selected_cookie_file, app_base_dir=self.app_base_dir ) - for posts_batch_data in post_generator: if self._check_pause_self("Post batch processing"): was_process_cancelled = True; break if self.isInterruptionRequested(): was_process_cancelled = True; break for individual_post_data in posts_batch_data: if self._check_pause_self(f"Individual post processing for {individual_post_data.get('id', 'N/A')}"): was_process_cancelled = True; break if self.isInterruptionRequested(): was_process_cancelled = True; break - post_processing_worker = PostProcessorWorker( post_data=individual_post_data, download_root=self.output_dir, @@ -1989,17 +1700,13 @@ class DownloadThread(QThread): num_potential_files_est = len(individual_post_data.get('attachments', [])) + \ (1 if individual_post_data.get('file') else 0) grand_total_skipped_files += num_potential_files_est - if self.skip_current_file_flag and self.skip_current_file_flag.is_set(): self.skip_current_file_flag.clear() self.logger(" Skip current file flag was processed and cleared by DownloadThread.") - self.msleep(10) if was_process_cancelled: break - if not was_process_cancelled and not self.isInterruptionRequested(): self.logger("✅ All posts processed or end of content reached by DownloadThread.") - except Exception as main_thread_err: self.logger(f"\n❌ Critical error within DownloadThread run loop: {main_thread_err}") traceback.print_exc() @@ -2014,9 +1721,7 @@ class DownloadThread(QThread): worker_signals_obj.missed_character_post_signal.disconnect(self.missed_character_post_signal) except (TypeError, RuntimeError) as e: self.logger(f"ℹī¸ Note during DownloadThread signal disconnection: {e}") - self.finished_signal.emit(grand_total_downloaded_files, grand_total_skipped_files, self.isInterruptionRequested(), grand_list_of_kept_original_filenames) - def receive_add_character_result(self, result): with QMutexLocker(self.prompt_mutex): self._add_character_response = result diff --git a/main.py b/main.py index 14a67fc..d50f950 100644 --- a/main.py +++ b/main.py @@ -329,8 +329,8 @@ class FavoriteArtistsDialog(QDialog): self.selected_artist_urls = [] self.setWindowTitle("Favorite Artists") - self.setModal(True) - self.setMinimumSize(500, 600) + self.setModal(True) # type: ignore + self.setMinimumSize(500, 500) # Reduced minimum height if hasattr(self.parent_app, 'get_dark_theme'): self.setStyleSheet(self.parent_app.get_dark_theme()) @@ -349,6 +349,7 @@ class FavoriteArtistsDialog(QDialog): self.search_input.textChanged.connect(self._filter_artist_list_display) main_layout.addWidget(self.search_input) + self.artist_list_widget = QListWidget() self.artist_list_widget.setStyleSheet(""" QListWidget::item { @@ -357,7 +358,14 @@ class FavoriteArtistsDialog(QDialog): padding-bottom: 4px; }""") main_layout.addWidget(self.artist_list_widget) + self.artist_list_widget.setAlternatingRowColors(True) + # Initially hide list and search until content is loaded + self.search_input.setVisible(False) + self.artist_list_widget.setVisible(False) + + self.status_label.setText("âŗ Loading favorite artists...") # Initial loading message + self.status_label.setAlignment(Qt.AlignCenter) combined_buttons_layout = QHBoxLayout() self.select_all_button = QPushButton("Select All") @@ -390,6 +398,11 @@ class FavoriteArtistsDialog(QDialog): else: print(f"[FavArtistsDialog] {message}") + def _show_content_elements(self, show): + """Helper to show/hide content-related widgets.""" + self.search_input.setVisible(show) + self.artist_list_widget.setVisible(show) + def _fetch_favorite_artists(self): fav_url = "https://kemono.su/api/v1/account/favorites?type=artist" self._logger(f"Attempting to fetch favorite artists from: {fav_url}") @@ -404,8 +417,10 @@ class FavoriteArtistsDialog(QDialog): if self.cookies_config['use_cookie'] and not cookies_dict: self.status_label.setText("Error: Cookies enabled but could not be loaded. Cannot fetch favorites.") + self._show_content_elements(False) self._logger("Error: Cookies enabled but could not be loaded.") QMessageBox.warning(self, "Cookie Error", "Cookies are enabled, but no valid cookies could be loaded. Please check your cookie settings or file.") + self.download_button.setEnabled(False) return try: @@ -417,6 +432,7 @@ class FavoriteArtistsDialog(QDialog): if not isinstance(artists_data, list): self.status_label.setText("Error: API did not return a list of artists.") + self._show_content_elements(False) self._logger(f"Error: Expected a list from API, got {type(artists_data)}") QMessageBox.critical(self, "API Error", "The favorite artists API did not return the expected data format (list).") return @@ -435,17 +451,28 @@ class FavoriteArtistsDialog(QDialog): self.all_fetched_artists.sort(key=lambda x: x['name'].lower()) self._populate_artist_list_widget() - self.status_label.setText(f"{len(self.all_fetched_artists)} favorite artist(s) found.") - self.download_button.setEnabled(len(self.all_fetched_artists) > 0) + + if self.all_fetched_artists: + self.status_label.setText(f"Found {len(self.all_fetched_artists)} favorite artist(s).") + self._show_content_elements(True) + self.download_button.setEnabled(True) + else: + self.status_label.setText("No favorite artists found.") + self._show_content_elements(False) + self.download_button.setEnabled(False) except requests.exceptions.RequestException as e: self.status_label.setText(f"Error fetching favorites: {e}") + self._show_content_elements(False) self._logger(f"Error fetching favorites: {e}") QMessageBox.critical(self, "Fetch Error", f"Could not fetch favorite artists: {e}") + self.download_button.setEnabled(False) except Exception as e: self.status_label.setText(f"An unexpected error occurred: {e}") + self._show_content_elements(False) self._logger(f"Unexpected error: {e}") QMessageBox.critical(self, "Error", f"An unexpected error occurred: {e}") + self.download_button.setEnabled(False) def _populate_artist_list_widget(self, artists_to_display=None): self.artist_list_widget.clear() @@ -498,12 +525,11 @@ class FavoritePostsFetcherThread(QThread): progress_bar_update = pyqtSignal(int, int) # value, maximum finished = pyqtSignal(list, str) # list of posts, error message (or None) - def __init__(self, cookies_config, parent_logger_func, parent_get_domain_func): + def __init__(self, cookies_config, parent_logger_func): # Removed parent_get_domain_func super().__init__() self.cookies_config = cookies_config self.parent_logger_func = parent_logger_func - self.parent_get_domain_func = parent_get_domain_func - self.cancellation_event = threading.Event() # For potential future cancellation + self.cancellation_event = threading.Event() def _logger(self, message): self.parent_logger_func(f"[FavPostsFetcherThread] {message}") @@ -553,53 +579,9 @@ class FavoritePostsFetcherThread(QThread): else: self._logger(f"Warning: Skipping favorite post entry due to missing data: {post_entry}") - unique_creators = {} - for post_data in all_fetched_posts_temp: - creator_key = (post_data['service'], post_data['creator_id']) - if creator_key not in unique_creators: - unique_creators[creator_key] = None - - creator_name_cache_local = {} - if unique_creators: - self.status_update.emit(f"Found {len(all_fetched_posts_temp)} posts. Fetching {len(unique_creators)} unique creator names...") - self.progress_bar_update.emit(0, len(unique_creators)) # Set max for creator name fetching - - fetched_names_count = 0 - total_unique_creators = len(unique_creators) - for (service, creator_id_val) in unique_creators.keys(): - if self.cancellation_event.is_set(): - self.finished.emit([], "Fetching cancelled.") - return - - creator_api_url = f"https://{self.parent_get_domain_func(service)}/api/v1/{service}/user/{creator_id_val}?o=0" - try: - creator_response = requests.get(creator_api_url, headers=headers, cookies=cookies_dict, timeout=10) - creator_response.raise_for_status() - creator_info_list = creator_response.json() - if isinstance(creator_info_list, list) and creator_info_list: - creator_name_from_api = creator_info_list[0].get("user_name") - creator_name = html.unescape(creator_name_from_api.strip()) if creator_name_from_api else creator_id_val - creator_name_cache_local[(service, creator_id_val)] = creator_name - fetched_names_count += 1 - self.status_update.emit(f"Fetched {fetched_names_count}/{total_unique_creators} creator names...") - self.progress_bar_update.emit(fetched_names_count, total_unique_creators) - else: - self._logger(f"Warning: Could not get name for {service}/{creator_id_val}. API response not a list or empty.") - creator_name_cache_local[(service, creator_id_val)] = creator_id_val - time.sleep(0.1) # Be polite - except requests.exceptions.RequestException as e_creator: - self._logger(f"Error fetching name for {service}/{creator_id_val}: {e_creator}") - creator_name_cache_local[(service, creator_id_val)] = creator_id_val # Fallback - except Exception as e_gen_creator: - self._logger(f"Unexpected error fetching name for {service}/{creator_id_val}: {e_gen_creator}") - creator_name_cache_local[(service, creator_id_val)] = creator_id_val # Fallback - - for post_data in all_fetched_posts_temp: - post_data['creator_name'] = creator_name_cache_local.get( - (post_data['service'], post_data['creator_id']), post_data['creator_id'] - ) - - all_fetched_posts_temp.sort(key=lambda x: x.get('added_date', ''), reverse=True) + # Creator name fetching logic removed. + # Sort by service, then creator_id, then date for consistent grouping + all_fetched_posts_temp.sort(key=lambda x: (x.get('service','').lower(), x.get('creator_id','').lower(), x.get('added_date', '')), reverse=False) self.finished.emit(all_fetched_posts_temp, None) except requests.exceptions.RequestException as e: @@ -627,25 +609,27 @@ class PostListItemWidget(QWidget): self.layout.addWidget(self.info_label, 1) self._setup_display_text() - def _setup_display_text(self): - creator_display = self.post_data.get('creator_name', self.post_data.get('creator_id', 'N/A')) - post_title_text = self.post_data.get('title', 'Untitled Post') + suffix_plain = self.post_data.get('suffix_for_display', "") # Changed from prefix_for_display + title_plain = self.post_data.get('title', 'Untitled Post') - known_char_name = self.parent_dialog._find_known_character_in_title(post_title_text) - known_line_text = f"Known - {known_char_name}" if known_char_name else "Known - " - - service_val = self.post_data.get('service', 'N/A').capitalize() - added_date_str = self.post_data.get('added_date', 'N/A') - added_date_formatted = added_date_str.split('T')[0] if added_date_str and 'T' in added_date_str else added_date_str - details_line_text = f"{service_val} - Added: {added_date_formatted}" + # Escape them for HTML display + escaped_suffix = html.escape(suffix_plain) # Changed from escaped_prefix + escaped_title = html.escape(title_plain) - line1_html = f"{html.escape(creator_display)} - {html.escape(post_title_text)}" - line2_html = html.escape(known_line_text) - line3_html = html.escape(details_line_text) - - display_html = f"{line1_html}
{line2_html}
{line3_html}" - self.info_label.setText(display_html) + # Styles + p_style_paragraph = "font-size:10.5pt; margin:0; padding:0;" # Base paragraph style (size, margins) + title_span_style = "font-weight:bold; color:#E0E0E0;" # Style for the title part (bold, bright white) + suffix_span_style = "color:#999999; font-weight:normal; font-size:9.5pt;" # Style for the suffix (dimmer gray, normal weight, slightly smaller) + + if escaped_suffix: + # Title part is bold and bright, suffix part is normal weight and dimmer + display_html_content = f"

{escaped_title}{escaped_suffix}

" + else: + # Only title part + display_html_content = f"

{escaped_title}

" + + self.info_label.setText(display_html_content) def isChecked(self): return self.checkbox.isChecked() def setCheckState(self, state): self.checkbox.setCheckState(state) @@ -660,11 +644,12 @@ class FavoritePostsDialog(QDialog): self.all_fetched_posts = [] self.selected_posts_data = [] self.known_names_list_ref = known_names_list_ref # Store reference to global KNOWN_NAMES + self.displayable_grouped_posts = {} # For storing posts grouped by artist self.fetcher_thread = None # For the worker thread - self.setWindowTitle("Favorite Posts") - self.setModal(True) - self.setMinimumSize(600, 600) # Slightly wider for post titles + self.setWindowTitle("Favorite Posts") # type: ignore + self.setModal(True) # type: ignore + self.setMinimumSize(600, 600) # Reduced minimum height if hasattr(self.parent_app, 'get_dark_theme'): self.setStyleSheet(self.parent_app.get_dark_theme()) @@ -695,6 +680,7 @@ class FavoritePostsDialog(QDialog): padding-top: 4px; padding-bottom: 4px; }""") + self.post_list_widget.setAlternatingRowColors(True) main_layout.addWidget(self.post_list_widget) combined_buttons_layout = QHBoxLayout() @@ -731,11 +717,10 @@ class FavoritePostsDialog(QDialog): self.fetcher_thread = FavoritePostsFetcherThread( self.cookies_config, self.parent_app.log_signal.emit, # Pass parent's logger - self._get_domain_for_service # Pass method reference - ) - self.fetcher_thread.progress_bar_update.connect(self._set_progress_bar_value) + ) # Removed _get_domain_for_service self.fetcher_thread.status_update.connect(self.status_label.setText) self.fetcher_thread.finished.connect(self._on_fetch_completed) + self.fetcher_thread.progress_bar_update.connect(self._set_progress_bar_value) # Connect the missing signal self.progress_bar.setVisible(True) self.fetcher_thread.start() @@ -757,94 +742,142 @@ class FavoritePostsDialog(QDialog): self.progress_bar.setVisible(False) self.all_fetched_posts = fetched_posts_list - self._populate_post_list_widget() + self._populate_post_list_widget() # This will now group and display self.status_label.setText(f"{len(self.all_fetched_posts)} favorite post(s) found.") self.download_button.setEnabled(len(self.all_fetched_posts) > 0) - + if self.fetcher_thread: self.fetcher_thread.quit() self.fetcher_thread.wait() self.fetcher_thread = None - - def _get_domain_for_service(self, service_name): - # Basic heuristic, might need refinement if more domains are supported - if service_name and "coomer" in service_name.lower(): # e.g. if service is 'coomer_onlyfans' - return "coomer.su" # Or coomer.party - return "kemono.su" # Default - - def _find_known_character_in_title(self, post_title): - if not post_title or not self.known_names_list_ref: + def _find_best_known_name_match_in_title(self, title_raw): + if not title_raw or not self.known_names_list_ref: return None - - # Sort by length of primary name to prioritize more specific matches. - sorted_known_names = sorted(self.known_names_list_ref, key=lambda x: len(x.get("name", "")), reverse=True) - for known_entry in sorted_known_names: - aliases_to_check = known_entry.get("aliases", []) - if not aliases_to_check and known_entry.get("name"): - aliases_to_check = [known_entry.get("name")] + title_lower = title_raw.lower() + best_match_known_name_primary = None + longest_match_len = 0 - for alias in aliases_to_check: - if not alias: + for known_entry in self.known_names_list_ref: + aliases_to_check = set() + # Add all explicit aliases from the known entry + for alias_val in known_entry.get("aliases", []): + aliases_to_check.add(alias_val) + # For non-group entries, the primary name is also a key alias + if not known_entry.get("is_group", False): + aliases_to_check.add(known_entry["name"]) + + # Sort this entry's aliases by length (longest first) + # to prioritize more specific aliases within the same known_entry + sorted_aliases_for_entry = sorted(list(aliases_to_check), key=len, reverse=True) + + for alias in sorted_aliases_for_entry: + alias_lower = alias.lower() + if not alias_lower: continue - pattern = r"(?i)\b" + re.escape(alias) + r"\b" - if re.search(pattern, post_title): - return known_entry.get("name") - return None + + # Check for whole word match using regex + if re.search(r'\b' + re.escape(alias_lower) + r'\b', title_lower): + if len(alias_lower) > longest_match_len: + longest_match_len = len(alias_lower) + best_match_known_name_primary = known_entry["name"] # Store the primary name + # Since aliases for this entry are sorted by length, first match is the best for this entry + break # Move to the next known_entry + return best_match_known_name_primary def _populate_post_list_widget(self, posts_to_display=None): self.post_list_widget.clear() - source_list = posts_to_display if posts_to_display is not None else self.all_fetched_posts - for post_data in source_list: - creator_display = post_data.get('creator_name', post_data.get('creator_id', 'N/A')) # Use creator_name - post_title_text = post_data.get('title', 'Untitled Post') - # The HTML generation is now inside PostListItemWidget + + source_list_for_grouping = posts_to_display if posts_to_display is not None else self.all_fetched_posts - list_item = QListWidgetItem(self.post_list_widget) # Parent it to the list widget - custom_widget = PostListItemWidget(post_data, self) # Pass self (FavoritePostsDialog) - - list_item.setSizeHint(custom_widget.sizeHint()) # Set size hint for the QListWidgetItem - list_item.setData(Qt.UserRole, post_data) - self.post_list_widget.addItem(list_item) - self.post_list_widget.setItemWidget(list_item, custom_widget) # Set the custom widget + # Group posts by (service, creator_id) + grouped_posts = {} + for post in source_list_for_grouping: + service = post.get('service', 'unknown_service') + creator_id = post.get('creator_id', 'unknown_id') + group_key = (service, creator_id) # Use tuple as key + if group_key not in grouped_posts: + grouped_posts[group_key] = [] + grouped_posts[group_key].append(post) + + sorted_group_keys = sorted(grouped_posts.keys(), key=lambda x: (x[0].lower(), x[1].lower())) + + self.displayable_grouped_posts = { + key: sorted(grouped_posts[key], key=lambda p: p.get('added_date', ''), reverse=True) + for key in sorted_group_keys + } + for service, creator_id_val in sorted_group_keys: + artist_name = f"{service.capitalize()} / {creator_id_val}" # Display service and ID + # Add artist header item + artist_header_item = QListWidgetItem(f"🎨 {artist_name}") + artist_header_item.setFlags(Qt.NoItemFlags) # Not selectable, not checkable + font = artist_header_item.font() + font.setBold(True) + font.setPointSize(font.pointSize() + 1) # Make it a bit larger + artist_header_item.setFont(font) + artist_header_item.setForeground(Qt.cyan) # Style for header + self.post_list_widget.addItem(artist_header_item) + + # Add post items for this artist + for post_data in self.displayable_grouped_posts[(service, creator_id_val)]: + post_title_raw = post_data.get('title', 'Untitled Post') + + # Find if a known name is in the title and prepare prefix + found_known_name_primary = self._find_best_known_name_match_in_title(post_title_raw) + + plain_text_title_for_list_item = post_title_raw + if found_known_name_primary: + suffix_text = f" [Known - {found_known_name_primary}]" # Changed to suffix format + post_data['suffix_for_display'] = suffix_text # Store as suffix_for_display + plain_text_title_for_list_item = post_title_raw + suffix_text # Append suffix + else: + post_data.pop('suffix_for_display', None) # Ensure suffix key is removed if no match + + list_item = QListWidgetItem(self.post_list_widget) # Parent it + list_item.setText(plain_text_title_for_list_item) # Use plain text (possibly prefixed) + list_item.setFlags(list_item.flags() | Qt.ItemIsUserCheckable) + list_item.setCheckState(Qt.Unchecked) + list_item.setData(Qt.UserRole, post_data) # Store full data for this post + self.post_list_widget.addItem(list_item) def _filter_post_list_display(self): search_text = self.search_input.text().lower().strip() if not search_text: - self._populate_post_list_widget() + self._populate_post_list_widget(self.all_fetched_posts) # Repopulate with all, which will group return - filtered_posts = [ - post for post in self.all_fetched_posts - if search_text in post['title'].lower() or \ - search_text in post.get('creator_name', post.get('creator_id', '')).lower() or \ - search_text in post['service'].lower() - ] - self._populate_post_list_widget(filtered_posts) + filtered_posts_to_group = [] + for post in self.all_fetched_posts: + # Check if search text matches post title, creator name, creator ID, or service + matches_post_title = search_text in post.get('title', '').lower() + matches_creator_name = False # Creator name is no longer fetched + matches_creator_id = search_text in post.get('creator_id', '').lower() + matches_service = search_text in post['service'].lower() + + if matches_post_title or matches_creator_name or matches_creator_id or matches_service: + filtered_posts_to_group.append(post) + + self._populate_post_list_widget(filtered_posts_to_group) # Repopulate with filtered, which will group def _select_all_items(self): for i in range(self.post_list_widget.count()): item = self.post_list_widget.item(i) - widget = self.post_list_widget.itemWidget(item) - if widget and hasattr(widget, 'setCheckState'): - widget.setCheckState(Qt.Checked) + if item and item.flags() & Qt.ItemIsUserCheckable: # Only check actual post items + item.setCheckState(Qt.Checked) def _deselect_all_items(self): for i in range(self.post_list_widget.count()): item = self.post_list_widget.item(i) - widget = self.post_list_widget.itemWidget(item) - if widget and hasattr(widget, 'setCheckState'): - widget.setCheckState(Qt.Unchecked) + if item and item.flags() & Qt.ItemIsUserCheckable: # Only uncheck actual post items + item.setCheckState(Qt.Unchecked) def _accept_selection_action(self): self.selected_posts_data = [] for i in range(self.post_list_widget.count()): item = self.post_list_widget.item(i) - widget = self.post_list_widget.itemWidget(item) # Get the custom widget - if widget and hasattr(widget, 'isChecked') and widget.isChecked(): - # Retrieve post_data from the custom widget or the item's UserRole - post_data_for_download = widget.get_post_data() if hasattr(widget, 'get_post_data') else item.data(Qt.UserRole) + if item and item.checkState() == Qt.Checked: + post_data_for_download = item.data(Qt.UserRole) self.selected_posts_data.append(post_data_for_download) if not self.selected_posts_data: @@ -855,6 +888,7 @@ class FavoritePostsDialog(QDialog): def get_selected_posts(self): return self.selected_posts_data + class HelpGuideDialog(QDialog): """A multi-page dialog for displaying the feature guide.""" def __init__(self, steps_data, parent=None): @@ -1543,7 +1577,19 @@ class DownloaderApp(QWidget): self.log_signal.emit("ℹī¸ Local API server functionality has been removed.") self.log_signal.emit("ℹī¸ 'Skip Current File' button has been removed.") if hasattr(self, 'character_input'): - self.character_input.setToolTip("Names, comma-separated. Group aliases: (alias1, alias2, alias3) becomes folder name 'alias1 alias2 alias3' (after cleaning).\nAll names in the group are used as aliases for matching.\nE.g., yor, (Boa, Hancock, Snake Princess)") + self.character_input.setToolTip("Enter character names (comma-separated). Supports advanced grouping and affects folder naming " + "if 'Separate Folders' is enabled.\n\n" + "Examples:\n" + "- Nami → Matches 'Nami', creates folder 'Nami'.\n" + "- (Ulti, Vivi) → Matches either, folder 'Ulti Vivi', adds both to Known.txt separately.\n" + "- (Boa, Hancock)~ → Matches either, folder 'Boa Hancock', adds as one group in Known.txt.\n\n" + "Names are treated as aliases for matching.\n\n" + "Filter Modes (button cycles):\n" + "- Files: Filters by filename.\n" + "- Title: Filters by post title.\n" + "- Both: Title first, then filename.\n" + "- Comments (Beta): Filename first, then post comments." + ) self.log_signal.emit(f"ℹī¸ Manga filename style loaded: '{self.manga_filename_style}'") self.log_signal.emit(f"ℹī¸ Skip words scope loaded: '{self.skip_words_scope}'") self.log_signal.emit(f"ℹī¸ Character filter scope set to default: '{self.char_filter_scope}'") @@ -1949,10 +1995,19 @@ class DownloaderApp(QWidget): self.character_input = QLineEdit() self.character_input.setPlaceholderText("e.g., Tifa, Aerith, (Cloud, Zack)") self.character_input.setToolTip( - self._get_tooltip_for_character_input() + "Enter character names, comma-separated (e.g., Tifa, Aerith).\n" + "Group aliases for a combined folder name: (alias1, alias2, alias3) becomes folder 'alias1 alias2 alias3'.\n" + "All names in the group are used as aliases for matching content.\n\n" + "The 'Filter: [Type]' button next to this input cycles how this filter applies:\n" + "- Filter: Files: Checks individual filenames. Only matching files are downloaded.\n" + "- Filter: Title: Checks post titles. All files from a matching post are downloaded.\n" + "- Filter: Both: Checks post title first. If no match, then checks filenames.\n" + "- Filter: Comments (Beta): Checks filenames first. If no match, then checks post comments.\n\n" + "This filter also influences folder naming if 'Separate Folders by Name/Title' is enabled." ) char_input_and_button_layout.addWidget(self.character_input, 3) + self.char_filter_scope_toggle_button = QPushButton() self._update_char_filter_scope_button_text() self.char_filter_scope_toggle_button.setStyleSheet("padding: 6px 10px;") @@ -1998,13 +2053,17 @@ class DownloaderApp(QWidget): skip_input_and_button_layout.setContentsMargins(0, 0, 0, 0) skip_input_and_button_layout.setSpacing(10) self.skip_words_input = QLineEdit() + # Updated tooltip for skip_words_input self.skip_words_input.setToolTip( - "Enter words, comma-separated, to skip downloading certain files or posts.\n" - "The 'Scope' button determines if this applies to file names, post titles, or both.\n" - "Example: WIP, sketch, preview, text post" + "Enter words, comma-separated, to skip downloading certain content (e.g., WIP, sketch, preview).\n\n" + "The 'Scope: [Type]' button next to this input cycles how this filter applies:\n" + "- Scope: Files: Skips individual files if their names contain any of these words.\n" + "- Scope: Posts: Skips entire posts if their titles contain any of these words.\n" + "- Scope: Both: Applies both (post title first, then individual files if post title is okay)." ) self.skip_words_input.setPlaceholderText("e.g., WM, WIP, sketch, preview") skip_input_and_button_layout.addWidget(self.skip_words_input, 1) + self.skip_scope_toggle_button = QPushButton() self._update_skip_scope_button_text() self.skip_scope_toggle_button.setStyleSheet("padding: 6px 10px;")