Commit

src/core/Hentai2read_client.py

@@ -2,71 +2,206 @@
 
 import re
 import os
-import json
-import requests
+import time
 import cloudscraper
 from bs4 import BeautifulSoup
+from urllib.parse import urljoin
+from concurrent.futures import ThreadPoolExecutor
+import queue
 
-def fetch_hentai2read_data(url, logger, session):
+def run_hentai2read_download(start_url, output_dir, progress_callback, overall_progress_callback, check_pause_func):
     """
-    Scrapes a SINGLE Hentai2Read chapter page using a provided session.
+    Orchestrates the download process using a producer-consumer model.
+    The main thread scrapes image URLs and puts them in a queue.
+    A pool of worker threads consumes from the queue to download images concurrently.
     """
-    logger(f"Attempting to fetch chapter data from: {url}")
+    scraper = cloudscraper.create_scraper()
     
     try:
-        response = session.get(url, timeout=30)
-        response.raise_for_status()
+        progress_callback("   [Hentai2Read] Scraping series page for all metadata...")
+        top_level_folder_name, chapters_to_process = _get_series_metadata(start_url, progress_callback, scraper)
+
+        if not chapters_to_process:
+            progress_callback("❌ No chapters found to download. Aborting.")
+            return 0, 0
         
-        page_content_text = response.text
-        soup = BeautifulSoup(page_content_text, 'html.parser')
-
-        album_title = ""
-        title_tags = soup.select('span[itemprop="name"]')
-        if title_tags:
-            album_title = title_tags[-1].text.strip()
+        total_chapters = len(chapters_to_process)
+        overall_progress_callback(total_chapters, 0)
         
-        if not album_title:
-            title_tag = soup.select_one('h1.title')
-            if title_tag:
-                album_title = title_tag.text.strip()
+        total_downloaded_count = 0
+        total_skipped_count = 0
 
-        if not album_title:
-            logger("❌ Could not find album title on page.")
-            return None, None
+        for idx, chapter in enumerate(chapters_to_process):
+            if check_pause_func(): break
+
+            progress_callback(f"\n-- Processing and Downloading Chapter {idx + 1}/{total_chapters}: '{chapter['title']}' --")
+            
+            series_folder = re.sub(r'[\\/*?:"<>|]', "", top_level_folder_name).strip()
+            chapter_folder = re.sub(r'[\\/*?:"<>|]', "", chapter['title']).strip()
+            final_save_path = os.path.join(output_dir, series_folder, chapter_folder)
+            os.makedirs(final_save_path, exist_ok=True)
+            
+            # This function now scrapes and downloads simultaneously
+            dl_count, skip_count = _process_and_download_chapter(
+                chapter_url=chapter['url'],
+                save_path=final_save_path,
+                scraper=scraper,
+                progress_callback=progress_callback,
+                check_pause_func=check_pause_func
+            )
+
+            total_downloaded_count += dl_count
+            total_skipped_count += skip_count
+            
+            overall_progress_callback(total_chapters, idx + 1)
+            if check_pause_func(): break
         
-        image_urls = []
-        try:
-            start_index = page_content_text.index("'images' : ") + len("'images' : ")
-            end_index = page_content_text.index(",\n", start_index)
-            images_json_str = page_content_text[start_index:end_index]
-            image_paths = json.loads(images_json_str)
-            image_urls = ["https://hentaicdn.com/hentai" + part for part in image_paths]
-        except (ValueError, json.JSONDecodeError):
-            logger("❌ Could not find or parse image JSON data for this chapter.")
-            return None, None
+        return total_downloaded_count, total_skipped_count
 
-        if not image_urls:
-            logger("❌ No image URLs found for this chapter.")
-            return None, None
-
-        logger(f"   Found {len(image_urls)} images for album '{album_title}'.")
-
-        files_to_download = []
-        for i, img_url in enumerate(image_urls):
-            page_num = i + 1
-            extension = os.path.splitext(img_url)[1].split('?')[0]
-            if not extension: extension = ".jpg"
-            filename = f"{page_num:03d}{extension}"
-            files_to_download.append({'url': img_url, 'filename': filename})
-
-        return album_title, files_to_download
-
-    except requests.exceptions.HTTPError as e:
-        if e.response.status_code == 404:
-            logger(f"   Chapter not found (404 Error). This likely marks the end of the series.")
-        else:
-            logger(f"❌ An HTTP error occurred: {e}")
-        return None, None
     except Exception as e:
-        logger(f"❌ An unexpected error occurred while fetching data: {e}")
-        return None, None
+        progress_callback(f"❌ A critical error occurred in the Hentai2Read client: {e}")
+        return 0, 0
+
+def _get_series_metadata(start_url, progress_callback, scraper):
+    """
+    Scrapes the main series page to get the Artist Name, Series Title, and chapter list.
+    """
+    try:
+        response = scraper.get(start_url, timeout=30)
+        response.raise_for_status()
+        soup = BeautifulSoup(response.text, 'html.parser')
+
+        series_title = "Unknown Series"
+        artist_name = None
+        metadata_list = soup.select_one("ul.list.list-simple-mini")
+        
+        if metadata_list:
+            first_li = metadata_list.find('li', recursive=False)
+            if first_li and not first_li.find('a'):
+                series_title = first_li.get_text(strip=True)
+
+            for b_tag in metadata_list.find_all('b'):
+                label = b_tag.get_text(strip=True)
+                if label in ("Artist", "Author"):
+                    a_tag = b_tag.find_next_sibling('a')
+                    if a_tag:
+                        artist_name = a_tag.get_text(strip=True)
+                        if label == "Artist":
+                            break
+        
+        top_level_folder_name = artist_name if artist_name else series_title
+        
+        chapter_links = soup.select("div.media a.pull-left.font-w600")
+        if not chapter_links:
+            chapters_to_process = [{'url': start_url, 'title': series_title}]
+        else:
+            chapters_to_process = [
+                {'url': urljoin(start_url, link['href']), 'title': " ".join(link.stripped_strings)} 
+                for link in chapter_links
+            ]
+            chapters_to_process.reverse()
+
+        progress_callback(f"   [Hentai2Read] ✅ Found Artist/Series: '{top_level_folder_name}'")
+        progress_callback(f"   [Hentai2Read] ✅ Found {len(chapters_to_process)} chapters to process.")
+        
+        return top_level_folder_name, chapters_to_process
+
+    except Exception as e:
+        progress_callback(f"   [Hentai2Read] ❌ Error getting series metadata: {e}")
+        return "Unknown Series", []
+
+### NEW: This function contains the pipeline logic ###
+def _process_and_download_chapter(chapter_url, save_path, scraper, progress_callback, check_pause_func):
+    """
+    Uses a producer-consumer pattern to download a chapter.
+    The main thread (producer) scrapes URLs one by one.
+    Worker threads (consumers) download the URLs as they are found.
+    """
+    task_queue = queue.Queue()
+    num_download_threads = 8
+    
+    # These will be updated by the worker threads
+    download_stats = {'downloaded': 0, 'skipped': 0}
+
+    def downloader_worker():
+        """The function that each download thread will run."""
+        # Create a unique session for each thread to avoid conflicts
+        worker_scraper = cloudscraper.create_scraper()
+        while True:
+            try:
+                # Get a task from the queue
+                task = task_queue.get()
+                # The sentinel value to signal the end
+                if task is None:
+                    break
+                
+                filepath, img_url = task
+                if os.path.exists(filepath):
+                    progress_callback(f"   -> Skip: '{os.path.basename(filepath)}'")
+                    download_stats['skipped'] += 1
+                else:
+                    progress_callback(f"   Downloading: '{os.path.basename(filepath)}'...")
+                    response = worker_scraper.get(img_url, stream=True, timeout=60, headers={'Referer': chapter_url})
+                    response.raise_for_status()
+                    with open(filepath, 'wb') as f:
+                        for chunk in response.iter_content(chunk_size=8192):
+                            f.write(chunk)
+                    download_stats['downloaded'] += 1
+            except Exception as e:
+                progress_callback(f"   ❌ Download failed for task. Error: {e}")
+                download_stats['skipped'] += 1
+            finally:
+                task_queue.task_done()
+
+    # --- Start the downloader threads ---
+    executor = ThreadPoolExecutor(max_workers=num_download_threads, thread_name_prefix='H2R_Downloader')
+    for _ in range(num_download_threads):
+        executor.submit(downloader_worker)
+
+    # --- Main thread acts as the scraper (producer) ---
+    page_number = 1
+    while True:
+        if check_pause_func(): break
+        if page_number > 300: # Safety break
+            progress_callback("   [Hentai2Read] ⚠️ Safety break: Reached 300 pages.")
+            break
+        
+        page_url_to_check = f"{chapter_url}{page_number}/"
+        try:
+            response = scraper.get(page_url_to_check, timeout=30)
+            if response.history or response.status_code != 200:
+                progress_callback(f"   [Hentai2Read] End of chapter detected on page {page_number}.")
+                break
+
+            soup = BeautifulSoup(response.text, 'html.parser')
+            img_tag = soup.select_one("img#arf-reader")
+            img_src = img_tag.get("src") if img_tag else None
+
+            if not img_tag or img_src == "https://static.hentai.direct/hentai":
+                progress_callback(f"   [Hentai2Read] End of chapter detected (Placeholder image on page {page_number}).")
+                break
+            
+            normalized_img_src = urljoin(response.url, img_src)
+            ext = os.path.splitext(normalized_img_src.split('/')[-1])[-1] or ".jpg"
+            filename = f"{page_number:03d}{ext}"
+            filepath = os.path.join(save_path, filename)
+            
+            # Put the download task into the queue for a worker to pick up
+            task_queue.put((filepath, normalized_img_src))
+            
+            page_number += 1
+            time.sleep(0.1) # Small delay between scraping pages
+        except Exception as e:
+            progress_callback(f"   [Hentai2Read] ❌ Error while scraping page {page_number}: {e}")
+            break
+            
+    # --- Shutdown sequence ---
+    # Tell all worker threads to exit by sending the sentinel value
+    for _ in range(num_download_threads):
+        task_queue.put(None)
+    
+    # Wait for all download tasks to be completed
+    executor.shutdown(wait=True)
+    
+    progress_callback(f"   Found and processed {page_number - 1} images for this chapter.")
+    return download_stats['downloaded'], download_stats['skipped']

src/core/allcomic_client.py

@@ -0,0 +1,116 @@
+import requests
+import re
+from bs4 import BeautifulSoup
+import cloudscraper
+import time 
+from urllib.parse import urlparse
+
+def get_chapter_list(series_url, logger_func):
+    """
+    Checks if a URL is a series page and returns a list of all chapter URLs if it is.
+    Includes a retry mechanism for robust connection.
+    """
+    logger_func(f"   [AllComic] Checking for chapter list at: {series_url}")
+    
+    scraper = cloudscraper.create_scraper()
+    response = None
+    max_retries = 8
+
+    for attempt in range(max_retries):
+        try:
+            response = scraper.get(series_url, timeout=30)
+            response.raise_for_status()
+            logger_func(f"   [AllComic] Successfully connected to series page on attempt {attempt + 1}.")
+            break # Success, exit the loop
+        except requests.RequestException as e:
+            logger_func(f"   [AllComic] ⚠️ Series page check attempt {attempt + 1}/{max_retries} failed: {e}")
+            if attempt < max_retries - 1:
+                wait_time = 2 * (attempt + 1)
+                logger_func(f"      Retrying in {wait_time} seconds...")
+                time.sleep(wait_time)
+            else:
+                logger_func(f"   [AllComic] ❌ All attempts to check series page failed.")
+                return [] # Return empty on final failure
+    
+    if not response:
+        return []
+
+    try:
+        soup = BeautifulSoup(response.text, 'html.parser')
+        chapter_links = soup.select('li.wp-manga-chapter a')
+        
+        if not chapter_links:
+            logger_func("   [AllComic] ℹ️ No chapter list found. Assuming this is a single chapter page.")
+            return []
+
+        chapter_urls = [link['href'] for link in chapter_links]
+        chapter_urls.reverse() # Reverse for oldest-to-newest reading order
+        
+        logger_func(f"   [AllComic] ✅ Found {len(chapter_urls)} chapters.")
+        return chapter_urls
+        
+    except Exception as e:
+        logger_func(f"   [AllComic] ❌ Error parsing chapters after successful connection: {e}")
+        return []
+
+def fetch_chapter_data(chapter_url, logger_func):
+    """
+    Fetches the comic title, chapter title, and image URLs for a single chapter page.
+    """
+    logger_func(f"   [AllComic] Fetching page: {chapter_url}")
+
+    scraper = cloudscraper.create_scraper(
+        browser={'browser': 'firefox', 'platform': 'windows', 'desktop': True}
+    )
+    headers = {'Referer': 'https://allporncomic.com/'}
+    
+    response = None
+    max_retries = 8
+    for attempt in range(max_retries):
+        try:
+            response = scraper.get(chapter_url, headers=headers, timeout=30)
+            response.raise_for_status()
+            break
+        except requests.RequestException as e:
+            if attempt < max_retries - 1:
+                time.sleep(2 * (attempt + 1))
+            else:
+                logger_func(f"   [AllComic] ❌ All connection attempts failed for chapter: {chapter_url}")
+                return None, None, None
+    
+    try:
+        soup = BeautifulSoup(response.text, 'html.parser')
+        title_element = soup.find('h1', class_='post-title')
+        comic_title = None
+        if title_element:
+            comic_title = title_element.text.strip()
+        else:
+            try:
+                path_parts = urlparse(chapter_url).path.strip('/').split('/')
+                if len(path_parts) >= 3 and path_parts[-3] == 'porncomic':
+                    comic_slug = path_parts[-2]
+                    comic_title = comic_slug.replace('-', ' ').title()
+            except Exception:
+                comic_title = "Unknown Comic"
+
+        chapter_slug = chapter_url.strip('/').split('/')[-1]
+        chapter_title = chapter_slug.replace('-', ' ').title()
+        
+        reading_container = soup.find('div', class_='reading-content')
+        list_of_image_urls = []
+        if reading_container:
+            image_elements = reading_container.find_all('img', class_='wp-manga-chapter-img')
+            for img in image_elements:
+                img_url = (img.get('data-src') or img.get('src', '')).strip()
+                if img_url:
+                    list_of_image_urls.append(img_url)
+
+        if not comic_title or comic_title == "Unknown Comic" or not list_of_image_urls:
+            logger_func(f"   [AllComic] ❌ Could not find a valid title or images on the page. Title found: '{comic_title}'")
+            return None, None, None
+
+        return comic_title, chapter_title, list_of_image_urls
+        
+    except Exception as e:
+        logger_func(f"   [AllComic] ❌ An unexpected error occurred while parsing the page: {e}")
+        return None, None, None

src/core/api_client.py

@@ -33,7 +33,7 @@ def fetch_posts_paginated(api_url_base, headers, offset, logger, cancellation_ev
         if cancellation_event and cancellation_event.is_set():
             raise RuntimeError("Fetch operation cancelled by user during retry loop.")
 
-        log_message = f"   Fetching post list: {paginated_url} (Page approx. {offset // 50 + 1})"
+        log_message = f"   Fetching post list: {api_url_base} (Page approx. {offset // 50 + 1})"
         if attempt > 0:
             log_message += f" (Attempt {attempt + 1}/{max_retries})"
         logger(log_message)
@@ -247,7 +247,7 @@ def download_from_api(
                     break
                 all_posts_for_manga_mode.extend(posts_batch_manga)
                 
-                logger(f"MANGA_FETCH_PROGRESS:{len(all_posts_for_manga_mode)}:{current_page_num_manga}")
+                logger(f"RENAMING_MODE_FETCH_PROGRESS:{len(all_posts_for_manga_mode)}:{current_page_num_manga}")
 
                 current_offset_manga += page_size
                 time.sleep(0.6)
@@ -265,7 +265,7 @@ def download_from_api(
         if cancellation_event and cancellation_event.is_set(): return
         
         if all_posts_for_manga_mode:
-            logger(f"MANGA_FETCH_COMPLETE:{len(all_posts_for_manga_mode)}")
+            logger(f"RENAMING_MODE_FETCH_COMPLETE:{len(all_posts_for_manga_mode)}")
 
         if all_posts_for_manga_mode:
             if processed_post_ids:

src/core/booru_client.py

@@ -0,0 +1,375 @@
+# src/core/booru_client.py
+
+import os
+import re
+import time
+import datetime
+import urllib.parse
+import requests
+import logging
+import cloudscraper
+# --- Start of Combined Code from 1.py ---
+
+# Part 1: Essential Utilities & Exceptions
+
+class BooruClientException(Exception):
+    """Base class for exceptions in this client."""
+    pass
+
+class HttpError(BooruClientException):
+    """HTTP request during data extraction failed."""
+    def __init__(self, message="", response=None):
+        self.response = response
+        self.status = response.status_code if response else 0
+        if response and not message:
+            message = f"'{response.status_code} {response.reason}' for '{response.url}'"
+        super().__init__(message)
+
+class NotFoundError(BooruClientException):
+    pass
+
+def unquote(s):
+    return urllib.parse.unquote(s)
+
+def parse_datetime(date_string, fmt):
+    try:
+        # Assumes date_string is in a format that strptime can handle with timezone
+        return datetime.datetime.strptime(date_string, fmt)
+    except (ValueError, TypeError):
+        return None
+
+def nameext_from_url(url, data=None):
+    if data is None: data = {}
+    try:
+        path = urllib.parse.urlparse(url).path
+        filename = unquote(os.path.basename(path))
+        if '.' in filename:
+            name, ext = filename.rsplit('.', 1)
+            data["filename"], data["extension"] = name, ext.lower()
+        else:
+            data["filename"], data["extension"] = filename, ""
+    except Exception:
+        data["filename"], data["extension"] = "", ""
+    return data
+
+USERAGENT_FIREFOX = "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/118.0"
+
+# Part 2: Core Extractor Logic
+
+class Extractor:
+    category = ""
+    subcategory = ""
+    directory_fmt = ("{category}", "{id}")
+    filename_fmt = "{filename}.{extension}"
+    _retries = 3
+    _timeout = 30
+
+    def __init__(self, match, logger_func=print):
+        self.url = match.string
+        self.match = match
+        self.groups = match.groups()
+        self.session = cloudscraper.create_scraper()
+        self.session.headers["User-Agent"] = USERAGENT_FIREFOX
+        self.log = logger_func
+        self.api_key = None
+        self.user_id = None
+
+    def set_auth(self, api_key, user_id):
+        self.api_key = api_key
+        self.user_id = user_id
+        self._init_auth()
+
+    def _init_auth(self):
+        """Placeholder for extractor-specific auth setup."""
+        pass
+
+    def request(self, url, method="GET", fatal=True, **kwargs):
+        for attempt in range(self._retries + 1):
+            try:
+                response = self.session.request(method, url, timeout=self._timeout, **kwargs)
+                if response.status_code < 400:
+                    return response
+                if response.status_code == 404 and fatal:
+                    raise NotFoundError(f"Resource not found at {url}")
+                self.log(f"Request for {url} failed with status {response.status_code}. Retrying...")
+            except requests.exceptions.RequestException as e:
+                self.log(f"Request for {url} failed: {e}. Retrying...")
+            if attempt < self._retries:
+                time.sleep(2 ** attempt)
+        if fatal:
+            raise HttpError(f"Failed to retrieve {url} after {self._retries} retries.")
+        return None
+
+    def request_json(self, url, **kwargs):
+        response = self.request(url, **kwargs)
+        try:
+            return response.json()
+        except (ValueError, TypeError) as exc:
+            self.log(f"Failed to decode JSON from {url}: {exc}")
+            raise BooruClientException("Invalid JSON response")
+
+    def items(self):
+        data = self.metadata()
+        for item in self.posts():
+            # Check for our special page update message
+            if isinstance(item, tuple) and item[0] == 'PAGE_UPDATE':
+                yield item
+                continue
+
+            # Otherwise, process it as a post
+            post = item
+            url = post.get("file_url")
+            if not url: continue
+            
+            nameext_from_url(url, post)
+            post["date"] = parse_datetime(post.get("created_at"), "%Y-%m-%dT%H:%M:%S.%f%z")
+
+            if url.startswith("/"):
+                url = self.root + url
+            post['file_url'] = url # Ensure full URL
+            
+            post.update(data)
+            yield post
+
+class BaseExtractor(Extractor):
+    instances = ()
+
+    def __init__(self, match, logger_func=print):
+        super().__init__(match, logger_func)
+        self._init_category()
+
+    def _init_category(self):
+        parsed_url = urllib.parse.urlparse(self.url)
+        self.root = f"{parsed_url.scheme}://{parsed_url.netloc}"
+        for i, group in enumerate(self.groups):
+            if group is not None:
+                try:
+                    self.category = self.instances[i][0]
+                    return
+                except IndexError:
+                    continue
+    
+    @classmethod
+    def update(cls, instances):
+        pattern_list = []
+        instance_list = cls.instances = []
+        for category, info in instances.items():
+            root = info["root"].rstrip("/") if info["root"] else ""
+            instance_list.append((category, root, info))
+            pattern = info.get("pattern", re.escape(root.partition("://")[2]))
+            pattern_list.append(f"({pattern})") 
+        return r"(?:https?://)?(?:" + "|".join(pattern_list) + r")"
+
+# Part 3: Danbooru Extractor
+
+class DanbooruExtractor(BaseExtractor):
+    filename_fmt = "{category}_{id}_{filename}.{extension}"
+    per_page = 200
+
+    def __init__(self, match, logger_func=print):
+        super().__init__(match, logger_func)
+        self._auth_logged = False
+
+    def _init_auth(self):
+        if self.user_id and self.api_key:
+            if not self._auth_logged:
+                self.log("Danbooru auth set.")
+                self._auth_logged = True
+            self.session.auth = (self.user_id, self.api_key)
+
+
+    def items(self):
+        data = self.metadata()
+        for item in self.posts():
+            # Check for our special page update message
+            if isinstance(item, tuple) and item[0] == 'PAGE_UPDATE':
+                yield item
+                continue
+
+            # Otherwise, process it as a post
+            post = item
+            url = post.get("file_url")
+            if not url: continue
+            
+            nameext_from_url(url, post)
+            post["date"] = parse_datetime(post.get("created_at"), "%Y-%m-%dT%H:%M:%S.%f%z")
+
+            if url.startswith("/"):
+                url = self.root + url
+            post['file_url'] = url # Ensure full URL
+            
+            post.update(data)
+            yield post
+
+    def metadata(self):
+        return {}
+
+    def posts(self):
+        return []
+
+    def _pagination(self, endpoint, params, prefix="b"):
+        url = self.root + endpoint
+        params["limit"] = self.per_page
+        params["page"] = 1
+        threshold = self.per_page - 20
+
+        while True:
+            posts = self.request_json(url, params=params)
+            if not posts: break
+            yield ('PAGE_UPDATE', len(posts)) 
+            yield from posts
+            if len(posts) < threshold: return
+            if prefix:
+                params["page"] = f"{prefix}{posts[-1]['id']}"
+            else:
+                params["page"] += 1
+
+BASE_PATTERN = DanbooruExtractor.update({
+    "danbooru": {"root": None, "pattern": r"(?:danbooru|safebooru)\.donmai\.us"},
+})
+
+class DanbooruTagExtractor(DanbooruExtractor):
+    subcategory = "tag"
+    directory_fmt = ("{category}", "{search_tags}")
+    pattern = BASE_PATTERN + r"(/posts\?(?:[^&#]*&)*tags=([^&#]*))"
+    
+    def metadata(self):
+        self.tags = unquote(self.groups[-1].replace("+", " ")).strip()
+        sanitized_tags = re.sub(r'[\\/*?:"<>|]', "_", self.tags)
+        return {"search_tags": sanitized_tags}
+
+    def posts(self):
+        return self._pagination("/posts.json", {"tags": self.tags})
+
+class DanbooruPostExtractor(DanbooruExtractor):
+    subcategory = "post"
+    pattern = BASE_PATTERN + r"(/post(?:s|/show)/(\d+))"
+    
+    def posts(self):
+        post_id = self.groups[-1]
+        url = f"{self.root}/posts/{post_id}.json"
+        post = self.request_json(url)
+        return (post,) if post else ()
+
+class GelbooruBase(Extractor):
+    category = "gelbooru"
+    root = "https://gelbooru.com"
+
+    def __init__(self, match, logger_func=print):
+        super().__init__(match, logger_func)
+        self._auth_logged = False
+    
+    def _api_request(self, params, key="post"):
+        # Auth is now added dynamically
+        if self.api_key and self.user_id:
+            if not self._auth_logged:
+                self.log("Gelbooru auth set.")
+                self._auth_logged = True
+            params.update({"api_key": self.api_key, "user_id": self.user_id})
+
+        url = self.root + "/index.php?page=dapi&q=index&json=1"
+        data = self.request_json(url, params=params)
+        
+        if not key: return data
+        posts = data.get(key, [])
+        return posts if isinstance(posts, list) else [posts] if posts else []
+
+    def items(self):
+        base_data = self.metadata()
+        base_data['category'] = self.category
+        
+        for item in self.posts():
+            # Check for our special page update message
+            if isinstance(item, tuple) and item[0] == 'PAGE_UPDATE':
+                yield item
+                continue
+
+            # Otherwise, process it as a post
+            post = item
+            url = post.get("file_url")
+            if not url: continue
+            
+            data = base_data.copy()
+            data.update(post)
+            nameext_from_url(url, data)
+            yield data
+
+    def metadata(self): return {}
+    def posts(self): return []
+
+GELBOORU_PATTERN = r"(?:https?://)?(?:www\.)?gelbooru\.com"
+
+class GelbooruTagExtractor(GelbooruBase):
+    subcategory = "tag"
+    directory_fmt = ("{category}", "{search_tags}")
+    filename_fmt = "{category}_{id}_{md5}.{extension}"
+    pattern = GELBOORU_PATTERN + r"(/index\.php\?page=post&s=list&tags=([^&#]*))"
+    
+    def metadata(self):
+        self.tags = unquote(self.groups[-1].replace("+", " ")).strip()
+        sanitized_tags = re.sub(r'[\\/*?:"<>|]', "_", self.tags)
+        return {"search_tags": sanitized_tags}
+
+    def posts(self):
+        """Scrapes HTML search pages as API can be restrictive for tags."""
+        pid = 0
+        posts_per_page = 42
+        search_url = self.root + "/index.php"
+        params = {"page": "post", "s": "list", "tags": self.tags}
+        
+        while True:
+            params['pid'] = pid
+            self.log(f"Scraping search results page (offset: {pid})...")
+            response = self.request(search_url, params=params)
+            html_content = response.text
+            post_ids = re.findall(r'id="p(\d+)"', html_content)
+            
+            if not post_ids:
+                self.log("No more posts found on page. Ending scrape.")
+                break
+            yield ('PAGE_UPDATE', len(post_ids))             
+            for post_id in post_ids:
+                post_data = self._api_request({"s": "post", "id": post_id})
+                yield from post_data
+            
+            pid += posts_per_page
+
+class GelbooruPostExtractor(GelbooruBase):
+    subcategory = "post"
+    filename_fmt = "{category}_{id}_{md5}.{extension}"
+    pattern = GELBOORU_PATTERN + r"(/index\.php\?page=post&s=view&id=(\d+))"
+
+    def posts(self):
+        post_id = self.groups[-1]
+        return self._api_request({"s": "post", "id": post_id})
+
+# --- Main Entry Point ---
+
+EXTRACTORS = [
+    DanbooruTagExtractor,
+    DanbooruPostExtractor,
+    GelbooruTagExtractor,
+    GelbooruPostExtractor,
+]
+
+def find_extractor(url, logger_func):
+    for extractor_cls in EXTRACTORS:
+        match = re.search(extractor_cls.pattern, url)
+        if match:
+            return extractor_cls(match, logger_func)
+    return None
+
+def fetch_booru_data(url, api_key, user_id, logger_func):
+    """
+    Main function to find an extractor and yield image data.
+    """
+    extractor = find_extractor(url, logger_func)
+    if not extractor:
+        logger_func(f"No suitable Booru extractor found for URL: {url}")
+        return
+
+    logger_func(f"Using extractor: {extractor.__class__.__name__}")
+    extractor.set_auth(api_key, user_id)
+    
+    # The 'items' method will now yield the data dictionaries directly
+    yield from extractor.items()

src/core/bunkr_client.py

@@ -207,7 +207,7 @@ def get_bunkr_extractor(url, logger):
 def fetch_bunkr_data(url, logger):
     """
     Main function to be called from the GUI.
-    It extracts all file information from a Bunkr URL.
+    It extracts all file information from a Bunkr URL, now handling both albums and direct file links.
     
     Returns:
         A tuple of (album_name, list_of_files)
@@ -215,6 +215,30 @@ def fetch_bunkr_data(url, logger):
         - list_of_files (list): A list of dicts, each containing 'url', 'name', and '_http_headers'.
         Returns (None, None) on failure.
     """
+    # --- START: New logic to handle direct CDN file URLs ---
+    try:
+        parsed_url = urllib.parse.urlparse(url)
+        # Check if the hostname contains 'cdn' and the path has a common file extension
+        is_direct_cdn_file = (parsed_url.hostname and 'cdn' in parsed_url.hostname and 'bunkr' in parsed_url.hostname and
+                              any(parsed_url.path.lower().endswith(ext) for ext in ['.mp4', '.mkv', '.webm', '.jpg', '.jpeg', '.png', '.gif', '.zip', '.rar']))
+
+        if is_direct_cdn_file:
+            logger.info("Bunkr direct file URL detected.")
+            filename = os.path.basename(parsed_url.path)
+            # Use the filename (without extension) as a sensible album name
+            album_name = os.path.splitext(filename)[0]
+            
+            files_to_download = [{
+                'url': url,
+                'name': filename,
+                '_http_headers': {'Referer': 'https://bunkr.ru/'} # Use a generic Referer
+            }]
+            return album_name, files_to_download
+    except Exception as e:
+        logger.warning(f"Could not parse Bunkr URL for direct file check: {e}")
+    # --- END: New logic ---
+
+    # This is the original logic for album and media pages
     extractor = get_bunkr_extractor(url, logger)
     if not extractor:
         return None, None
@@ -238,4 +262,4 @@ def fetch_bunkr_data(url, logger):
     
     except Exception as e:
         logger.error(f"An error occurred while extracting Bunkr info: {e}", exc_info=True)
-        return None, None
+        return None, None

src/core/fap_nation_client.py

@@ -0,0 +1,125 @@
+import re
+import os
+import cloudscraper
+from urllib.parse import urlparse, urljoin
+from ..utils.file_utils import clean_folder_name
+
+def fetch_fap_nation_data(album_url, logger_func):
+    """
+    Scrapes a fap-nation page by prioritizing HLS streams first, then falling
+    back to direct download links. Selects the highest quality available.
+    """
+    logger_func(f"   [Fap-Nation] Fetching album data from: {album_url}")
+    scraper = cloudscraper.create_scraper()
+    
+    try:
+        response = scraper.get(album_url, timeout=45)
+        response.raise_for_status()
+        html_content = response.text
+        
+        title_match = re.search(r'<h1[^>]*itemprop="name"[^>]*>(.*?)</h1>', html_content, re.IGNORECASE)
+        album_slug = clean_folder_name(os.path.basename(urlparse(album_url).path.strip('/')))
+        album_title = clean_folder_name(title_match.group(1).strip()) if title_match else album_slug
+
+        files_to_download = []
+        final_url = None
+        link_type = None
+        filename_from_video_tag = None
+
+        video_tag_title_match = re.search(r'data-plyr-config=.*?&quot;title&quot;:.*?&quot;([^&]+?\.mp4)&quot;', html_content, re.IGNORECASE)
+        if video_tag_title_match:
+            filename_from_video_tag = clean_folder_name(video_tag_title_match.group(1))
+            logger_func(f"   [Fap-Nation] Found high-quality filename in video tag: {filename_from_video_tag}")
+
+        # --- REVISED LOGIC: HLS FIRST ---
+
+        # 1. Prioritize finding an HLS stream.
+        logger_func("   [Fap-Nation] Priority 1: Searching for HLS stream...")
+        iframe_match = re.search(r'<iframe[^>]+src="([^"]+mediadelivery\.net[^"]+)"', html_content, re.IGNORECASE)
+        
+        if iframe_match:
+            iframe_url = iframe_match.group(1)
+            logger_func(f"   [Fap-Nation] Found video iframe. Visiting: {iframe_url}")
+            try:
+                iframe_response = scraper.get(iframe_url, timeout=30)
+                iframe_response.raise_for_status()
+                iframe_html = iframe_response.text
+                
+                playlist_match = re.search(r'<source[^>]+src="([^"]+\.m3u8)"', iframe_html, re.IGNORECASE)
+                if playlist_match:
+                    final_url = playlist_match.group(1)
+                    link_type = 'hls'
+                    logger_func(f"   [Fap-Nation] Found embedded HLS stream in iframe: {final_url}")
+            except Exception as e:
+                logger_func(f"   [Fap-Nation] ⚠️ Error fetching or parsing iframe content: {e}")
+        
+        if not final_url:
+            logger_func("   [Fap-Nation] No stream found in iframe. Checking main page content as a last resort...")
+            js_var_match = re.search(r'"(https?://[^"]+\.m3u8)"', html_content, re.IGNORECASE)
+            if js_var_match:
+                final_url = js_var_match.group(1)
+                link_type = 'hls'
+                logger_func(f"   [Fap-Nation] Found HLS stream on main page: {final_url}")
+
+        # 2. Fallback: If no HLS stream was found, search for direct links.
+        if not final_url:
+            logger_func("   [Fap-Nation] No HLS stream found. Priority 2 (Fallback): Searching for direct download links...")
+            direct_link_pattern = r'<a\s+[^>]*href="([^"]+\.(?:mp4|webm|mkv|mov))"[^>]*>'
+            direct_links_found = re.findall(direct_link_pattern, html_content, re.IGNORECASE)
+
+            if direct_links_found:
+                logger_func(f"   [Fap-Nation] Found {len(direct_links_found)} direct media link(s). Selecting the best quality...")
+                best_link = direct_links_found[0]
+                for link in direct_links_found:
+                    if '1080p' in link.lower():
+                        best_link = link
+                        break
+                final_url = best_link
+                link_type = 'direct'
+                logger_func(f"   [Fap-Nation] Identified direct media link: {final_url}")
+
+        # If after all checks, we still have no URL, then fail.
+        if not final_url:
+            logger_func("   [Fap-Nation] ❌ Stage 1 Failed: Could not find any HLS stream or direct link.")
+            return None, []
+
+        # --- HLS Quality Selection Logic ---
+        if link_type == 'hls' and final_url:
+            logger_func("   [Fap-Nation] HLS stream found. Checking for higher quality variants...")
+            try:
+                master_playlist_response = scraper.get(final_url, timeout=20)
+                master_playlist_response.raise_for_status()
+                playlist_content = master_playlist_response.text
+
+                streams = re.findall(r'#EXT-X-STREAM-INF:.*?RESOLUTION=(\d+)x(\d+).*?\n(.*?)\s', playlist_content)
+                
+                if streams:
+                    best_stream = max(streams, key=lambda s: int(s[0]) * int(s[1]))
+                    height = best_stream[1]
+                    relative_path = best_stream[2]
+                    new_final_url = urljoin(final_url, relative_path)
+                    
+                    logger_func(f"   [Fap-Nation] ✅ Best quality found: {height}p. Updating URL to: {new_final_url}")
+                    final_url = new_final_url
+                else:
+                    logger_func("   [Fap-Nation] ℹ️ No alternate quality streams found in playlist. Using original.")
+            except Exception as e:
+                logger_func(f"   [Fap-Nation] ⚠️ Could not parse HLS master playlist for quality selection: {e}. Using original URL.")
+
+        if final_url and link_type:
+            if filename_from_video_tag:
+                base_name, _ = os.path.splitext(filename_from_video_tag)
+                new_filename = f"{base_name}.mp4"
+            else:
+                new_filename = f"{album_slug}.mp4"
+            
+            files_to_download.append({'url': final_url, 'filename': new_filename, 'type': link_type})
+            logger_func(f"   [Fap-Nation] ✅ Ready to download '{new_filename}' ({link_type} method).")
+            return album_title, files_to_download
+        
+        logger_func(f"   [Fap-Nation] ❌ Could not determine a valid download link.")
+        return None, []
+        
+    except Exception as e:
+        logger_func(f"   [Fap-Nation] ❌ Error fetching Fap-Nation data: {e}")
+        return None, []

src/core/mangadex_client.py

@@ -0,0 +1,189 @@
+# src/core/mangadex_client.py
+
+import os
+import re
+import time
+import cloudscraper
+from collections import defaultdict
+from ..utils.file_utils import clean_folder_name
+
+def fetch_mangadex_data(start_url, output_dir, logger_func, file_progress_callback, overall_progress_callback, pause_event, cancellation_event):
+    """
+    Fetches and downloads all content from a MangaDex series or chapter URL.
+    Returns a tuple of (downloaded_count, skipped_count).
+    """
+    grand_total_dl = 0
+    grand_total_skip = 0
+    
+    api = _MangadexAPI(logger_func)
+
+    def _check_pause():
+        if cancellation_event and cancellation_event.is_set(): return True
+        if pause_event and pause_event.is_set():
+            logger_func("   Download paused...")
+            while pause_event.is_set():
+                if cancellation_event and cancellation_event.is_set(): return True
+                time.sleep(0.5)
+            logger_func("   Download resumed.")
+        return cancellation_event.is_set()
+
+    series_match = re.search(r"mangadex\.org/(?:title|manga)/([0-9a-f-]+)", start_url)
+    chapter_match = re.search(r"mangadex\.org/chapter/([0-9a-f-]+)", start_url)
+
+    chapters_to_process = []
+    if series_match:
+        series_id = series_match.group(1)
+        logger_func(f"   Series detected. Fetching chapter list for ID: {series_id}")
+        chapters_to_process = api.get_manga_chapters(series_id, cancellation_event, pause_event)
+    elif chapter_match:
+        chapter_id = chapter_match.group(1)
+        logger_func(f"   Single chapter detected. Fetching info for ID: {chapter_id}")
+        chapter_info = api.get_chapter_info(chapter_id)
+        if chapter_info:
+            chapters_to_process = [chapter_info]
+    
+    if not chapters_to_process:
+        logger_func("❌ No chapters found or failed to fetch chapter info.")
+        return 0, 0
+
+    logger_func(f"✅ Found {len(chapters_to_process)} chapter(s) to download.")
+    if overall_progress_callback:
+        overall_progress_callback.emit(len(chapters_to_process), 0)
+
+    for chap_idx, chapter_json in enumerate(chapters_to_process):
+        if _check_pause(): break
+        try:
+            metadata = api.transform_chapter_data(chapter_json)
+            logger_func("-" * 40)
+            logger_func(f"Processing Chapter {chap_idx + 1}/{len(chapters_to_process)}: Vol. {metadata['volume']} Ch. {metadata['chapter']}{metadata['chapter_minor']} - {metadata['title']}")
+            
+            server_info = api.get_at_home_server(chapter_json["id"])
+            if not server_info:
+                logger_func("   ❌ Could not get image server for this chapter. Skipping.")
+                continue
+            
+            base_url = f"{server_info['baseUrl']}/data/{server_info['chapter']['hash']}/"
+            image_files = server_info['chapter']['data']
+
+            series_folder = clean_folder_name(metadata['manga'])
+            chapter_folder_title = metadata['title'] or ''
+            chapter_folder = clean_folder_name(f"Vol {metadata['volume']:02d} Chap {metadata['chapter']:03d}{metadata['chapter_minor']} - {chapter_folder_title}".strip().strip('-').strip())
+            final_save_path = os.path.join(output_dir, series_folder, chapter_folder)
+            os.makedirs(final_save_path, exist_ok=True)
+
+            for img_idx, filename in enumerate(image_files):
+                if _check_pause(): break
+                
+                full_img_url = base_url + filename
+                img_path = os.path.join(final_save_path, f"{img_idx + 1:03d}{os.path.splitext(filename)[1]}")
+
+                if os.path.exists(img_path):
+                    logger_func(f"   -> Skip ({img_idx+1}/{len(image_files)}): '{os.path.basename(img_path)}' already exists.")
+                    grand_total_skip += 1
+                    continue
+                
+                logger_func(f"   Downloading ({img_idx+1}/{len(image_files)}): '{os.path.basename(img_path)}'...")
+                
+                try:
+                    response = api.session.get(full_img_url, stream=True, timeout=60, headers={'Referer': 'https://mangadex.org/'})
+                    response.raise_for_status()
+                    total_size = int(response.headers.get('content-length', 0))
+                    
+                    if file_progress_callback:
+                        file_progress_callback.emit(os.path.basename(img_path), (0, total_size))
+
+                    with open(img_path, 'wb') as f:
+                        downloaded_bytes = 0
+                        for chunk in response.iter_content(chunk_size=8192):
+                            if _check_pause(): break
+                            f.write(chunk)
+                            downloaded_bytes += len(chunk)
+                            if file_progress_callback:
+                                file_progress_callback.emit(os.path.basename(img_path), (downloaded_bytes, total_size))
+                    
+                    if _check_pause():
+                        if os.path.exists(img_path): os.remove(img_path)
+                        break
+                    
+                    grand_total_dl += 1
+                except Exception as e:
+                    logger_func(f"      ❌ Failed to download page {img_idx+1}: {e}")
+                    grand_total_skip += 1
+            
+            if overall_progress_callback:
+                overall_progress_callback.emit(len(chapters_to_process), chap_idx + 1)
+            time.sleep(1)
+
+        except Exception as e:
+            logger_func(f"   ❌ An unexpected error occurred while processing chapter {chapter_json.get('id')}: {e}")
+
+    return grand_total_dl, grand_total_skip
+
+class _MangadexAPI:
+    def __init__(self, logger_func):
+        self.logger_func = logger_func
+        self.session = cloudscraper.create_scraper()
+        self.root = "https://api.mangadex.org"
+
+    def _call(self, endpoint, params=None, cancellation_event=None):
+        if cancellation_event and cancellation_event.is_set(): return None
+        try:
+            response = self.session.get(f"{self.root}{endpoint}", params=params, timeout=30)
+            if response.status_code == 429:
+                retry_after = int(response.headers.get("X-RateLimit-Retry-After", 5))
+                self.logger_func(f"   ⚠️ Rate limited. Waiting for {retry_after} seconds...")
+                time.sleep(retry_after)
+                return self._call(endpoint, params, cancellation_event)
+            response.raise_for_status()
+            return response.json()
+        except Exception as e:
+            self.logger_func(f"   ❌ API call to '{endpoint}' failed: {e}")
+            return None
+
+    def get_manga_chapters(self, series_id, cancellation_event, pause_event):
+        all_chapters = []
+        offset = 0
+        limit = 500
+        base_params = {
+            "limit": limit, "order[volume]": "asc", "order[chapter]": "asc",
+            "translatedLanguage[]": ["en"], "includes[]": ["scanlation_group", "user", "manga"]
+        }
+        while True:
+            if cancellation_event.is_set(): break
+            while pause_event.is_set(): time.sleep(0.5)
+            
+            params = {**base_params, "offset": offset}
+            data = self._call(f"/manga/{series_id}/feed", params, cancellation_event)
+            if not data or data.get("result") != "ok": break
+            
+            results = data.get("data", [])
+            all_chapters.extend(results)
+            
+            if (offset + limit) >= data.get("total", 0): break
+            offset += limit
+        return all_chapters
+
+    def get_chapter_info(self, chapter_id):
+        params = {"includes[]": ["scanlation_group", "user", "manga"]}
+        data = self._call(f"/chapter/{chapter_id}", params)
+        return data.get("data") if data and data.get("result") == "ok" else None
+
+    def get_at_home_server(self, chapter_id):
+        return self._call(f"/at-home/server/{chapter_id}")
+
+    def transform_chapter_data(self, chapter):
+        relationships = {item["type"]: item for item in chapter.get("relationships", [])}
+        manga = relationships.get("manga", {})
+        c_attrs = chapter.get("attributes", {})
+        m_attrs = manga.get("attributes", {})
+        
+        chapter_num_str = c_attrs.get("chapter", "0") or "0"
+        chnum, sep, minor = chapter_num_str.partition(".")
+        
+        return {
+            "manga": (m_attrs.get("title", {}).get("en") or next(iter(m_attrs.get("title", {}).values()), "Unknown Series")),
+            "title": c_attrs.get("title", ""),
+            "volume": int(float(c_attrs.get("volume", 0) or 0)),
+            "chapter": int(float(chnum or 0)),
+            "chapter_minor": sep + minor if minor else ""
+        }

src/core/pixeldrain_client.py

@@ -0,0 +1,93 @@
+import os
+import re
+import cloudscraper
+from ..utils.file_utils import clean_folder_name
+# --- ADDED IMPORTS ---
+from requests.adapters import HTTPAdapter
+from urllib3.util.retry import Retry
+
+def fetch_pixeldrain_data(url: str, logger):
+    """
+    Scrapes a given Pixeldrain URL to extract album or file information.
+    Handles single files (/u/), albums/lists (/l/), and folders (/d/).
+    """
+    logger(f"Fetching data for Pixeldrain URL: {url}")
+    scraper = cloudscraper.create_scraper()
+    root = "https://pixeldrain.com"
+
+    # --- START OF FIX: Add a robust retry strategy ---
+    try:
+        retry_strategy = Retry(
+            total=5,  # Total number of retries
+            backoff_factor=1,  # Wait 1s, 2s, 4s, 8s between retries
+            status_forcelist=[429, 500, 502, 503, 504], # Retry on these server errors
+            allowed_methods=["HEAD", "GET"]
+        )
+        adapter = HTTPAdapter(max_retries=retry_strategy)
+        scraper.mount("https://", adapter)
+        scraper.mount("http://", adapter)
+        logger("   [Pixeldrain] Configured retry strategy for network requests.")
+    except Exception as e:
+        logger(f"   [Pixeldrain] ⚠️ Could not configure retry strategy: {e}")
+    # --- END OF FIX ---
+
+    file_match = re.search(r"/u/(\w+)", url)
+    album_match = re.search(r"/l/(\w+)", url)
+    folder_match = re.search(r"/d/([^?]+)", url)
+
+    try:
+        if file_match:
+            file_id = file_match.group(1)
+            logger(f"   Detected Pixeldrain File ID: {file_id}")
+            api_url = f"{root}/api/file/{file_id}/info"
+            data = scraper.get(api_url).json()
+            
+            title = data.get("name", file_id)
+            
+            files = [{
+                'url': f"{root}/api/file/{file_id}?download",
+                'filename': data.get("name", f"{file_id}.tmp")
+            }]
+            return title, files
+
+        elif album_match:
+            album_id = album_match.group(1)
+            logger(f"   Detected Pixeldrain Album ID: {album_id}")
+            api_url = f"{root}/api/list/{album_id}"
+            data = scraper.get(api_url).json()
+
+            title = data.get("title", album_id)
+            
+            files = []
+            for file_info in data.get("files", []):
+                files.append({
+                    'url': f"{root}/api/file/{file_info['id']}?download",
+                    'filename': file_info.get("name", f"{file_info['id']}.tmp")
+                })
+            return title, files
+
+        elif folder_match:
+            path_id = folder_match.group(1)
+            logger(f"   Detected Pixeldrain Folder Path: {path_id}")
+            api_url = f"{root}/api/filesystem/{path_id}?stat"
+            data = scraper.get(api_url).json()
+
+            path_info = data["path"][data["base_index"]]
+            title = path_info.get("name", path_id)
+
+            files = []
+            for child in data.get("children", []):
+                if child.get("type") == "file":
+                    files.append({
+                        'url': f"{root}/api/filesystem{child['path']}?attach",
+                        'filename': child.get("name")
+                    })
+            return title, files
+
+        else:
+            logger("   ❌ Could not identify Pixeldrain URL type (file, album, or folder).")
+            return None, []
+
+    except Exception as e:
+        logger(f"❌ An error occurred while fetching Pixeldrain data: {e}")
+        return None, []

src/core/simpcity_client.py

@@ -0,0 +1,100 @@
+# src/core/simpcity_client.py
+
+import cloudscraper
+from bs4 import BeautifulSoup
+from urllib.parse import urlparse, unquote
+import os
+import re
+from ..utils.file_utils import clean_folder_name
+import urllib.parse 
+
+def fetch_single_simpcity_page(url, logger_func, cookies=None, post_id=None):
+    """
+    Scrapes a single SimpCity page for images, external links, video tags, and iframes.
+    """
+    scraper = cloudscraper.create_scraper()
+    headers = {'Referer': 'https://simpcity.cr/'}
+    
+    try:
+        response = scraper.get(url, timeout=30, headers=headers, cookies=cookies)
+        if response.status_code == 404:
+            return None, []
+        response.raise_for_status()
+        soup = BeautifulSoup(response.text, 'html.parser')
+
+        album_title = None
+        title_element = soup.find('h1', class_='p-title-value')
+        if title_element:
+            album_title = title_element.text.strip()
+        
+        search_scope = soup
+        if post_id:
+            post_content_container = soup.find('div', attrs={'data-lb-id': f'post-{post_id}'})
+            if post_content_container:
+                logger_func(f"   [SimpCity] ✅ Isolating search to post content container for ID {post_id}.")
+                search_scope = post_content_container
+            else:
+                logger_func(f"   [SimpCity] ⚠️ Could not find content container for post ID {post_id}.")
+
+        jobs_on_page = []
+
+        # Find native SimpCity images
+        image_tags = search_scope.find_all('img', class_='bbImage')
+        for img_tag in image_tags:
+            thumbnail_url = img_tag.get('src')
+            if not thumbnail_url or not isinstance(thumbnail_url, str) or 'saint2.su' in thumbnail_url: continue
+            full_url = thumbnail_url.replace('.md.', '.')
+            filename = img_tag.get('alt', '').replace('.md.', '.') or os.path.basename(unquote(urlparse(full_url).path))
+            jobs_on_page.append({'type': 'image', 'filename': filename, 'url': full_url})
+            
+        # Find links in <a> tags, now with redirect handling
+        link_tags = search_scope.find_all('a', href=True)
+        for link in link_tags:
+            href = link.get('href', '')
+            
+            actual_url = href
+            if '/misc/goto?url=' in href:
+                try:
+                    # Extract and decode the real URL from the 'url' parameter
+                    parsed_href = urlparse(href)
+                    query_params = dict(urllib.parse.parse_qsl(parsed_href.query))
+                    if 'url' in query_params:
+                        actual_url = unquote(query_params['url'])
+                except Exception:
+                    actual_url = href # Fallback if parsing fails
+            
+            # Perform all checks on the 'actual_url' which is now the real destination
+            if re.search(r'pixeldrain\.com/[lud]/', actual_url): jobs_on_page.append({'type': 'pixeldrain', 'url': actual_url})
+            elif re.search(r'saint2\.(su|pk|cr|to)/embed/', actual_url): jobs_on_page.append({'type': 'saint2', 'url': actual_url})
+            elif re.search(r'bunkr\.(?:cr|si|la|ws|is|ru|su|red|black|media|site|to|ac|ci|fi|pk|ps|sk|ph)|bunkrr\.ru', actual_url): jobs_on_page.append({'type': 'bunkr', 'url': actual_url})
+            elif re.search(r'mega\.(nz|io)', actual_url): jobs_on_page.append({'type': 'mega', 'url': actual_url})
+            elif re.search(r'gofile\.io', actual_url): jobs_on_page.append({'type': 'gofile', 'url': actual_url})
+
+        # Find direct Saint2 video embeds in <video> tags
+        video_tags = search_scope.find_all('video')
+        for video in video_tags:
+            source_tag = video.find('source')
+            if source_tag and source_tag.get('src'):
+                src_url = source_tag['src']
+                if re.search(r'saint2\.(su|pk|cr|to)', src_url):
+                    jobs_on_page.append({'type': 'saint2_direct', 'url': src_url})
+        
+        # Find embeds in <iframe> tags (as a fallback)
+        iframe_tags = search_scope.find_all('iframe')
+        for iframe in iframe_tags:
+            src_url = iframe.get('src')
+            if src_url and isinstance(src_url, str):
+                if re.search(r'saint2\.(su|pk|cr|to)/embed/', src_url):
+                    jobs_on_page.append({'type': 'saint2', 'url': src_url})
+
+        if jobs_on_page:
+            # We use a set to remove duplicate URLs that might be found in multiple ways
+            unique_jobs = list({job['url']: job for job in jobs_on_page}.values())
+            logger_func(f"   [SimpCity] Scraper found jobs: {[job['type'] for job in unique_jobs]}")
+            return album_title, unique_jobs
+
+        return album_title, []
+
+    except Exception as e:
+        logger_func(f"   [SimpCity] ❌ Error fetching page {url}: {e}")
+        raise e

src/core/toonily_client.py

@@ -0,0 +1,73 @@
+import cloudscraper
+from bs4 import BeautifulSoup
+import time
+
+def get_chapter_list(series_url, logger_func):
+    logger_func(f"   [Toonily] Scraping series page for chapter list: {series_url}")
+    scraper = cloudscraper.create_scraper()
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36',
+        'Referer': 'https://toonily.com/'
+    }
+    
+    try:
+        response = scraper.get(series_url, timeout=30, headers=headers)
+        response.raise_for_status()
+        soup = BeautifulSoup(response.content, 'html.parser')
+        chapter_links = soup.select('li.wp-manga-chapter > a')
+
+        if not chapter_links:
+            logger_func("   [Toonily] ❌ Could not find any chapter links on the page.")
+            return []
+
+        urls = [link['href'] for link in chapter_links]
+        urls.reverse() 
+        logger_func(f"   [Toonily] Found {len(urls)} chapters.")
+        return urls
+
+    except Exception as e:
+        logger_func(f"   [Toonily] ❌ Error getting chapter list: {e}")
+        return []
+
+
+def fetch_chapter_data(chapter_url, logger_func, scraper_session):
+    """
+    Scrapes a single Toonily.com chapter page for its title and image URLs.
+    """
+    main_series_url = chapter_url.rsplit('/', 2)[0] + '/'
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36',
+        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
+        'Accept-Language': 'en-US,en;q=0.9',
+        'Referer': main_series_url
+    }
+    
+    try:
+        response = scraper_session.get(chapter_url, timeout=30, headers=headers)
+        response.raise_for_status()
+        soup = BeautifulSoup(response.content, 'html.parser')
+
+        title_element = soup.select_one('h1#chapter-heading')
+        image_container = soup.select_one('div.reading-content')
+        
+        if not title_element or not image_container:
+            logger_func("   [Toonily] ❌ Page structure invalid. Could not find title or image container.")
+            return None, None, []
+
+        full_chapter_title = title_element.text.strip()
+        
+        if " - Chapter" in full_chapter_title:
+            series_title = full_chapter_title.split(" - Chapter")[0].strip()
+        else:
+            series_title = full_chapter_title.strip()
+
+        chapter_title = full_chapter_title # The full string is best for the chapter folder name
+        
+        image_elements = image_container.select('img')
+        image_urls = [img.get('data-src', img.get('src')).strip() for img in image_elements if img.get('data-src') or img.get('src')]
+        
+        return series_title, chapter_title, image_urls
+
+    except Exception as e:
+        logger_func(f"   [Toonily] ❌ An error occurred scraping chapter '{chapter_url}': {e}")
+        return None, None, []