quasarr 1.26.3__py3-none-any.whl → 1.26.4__py3-none-any.whl

quasarr/downloads/sources/dl.py

@@ -3,14 +3,35 @@
 # Project by https://github.com/rix1337
 
 import re
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from io import BytesIO
 
-from bs4 import BeautifulSoup
+from PIL import Image
+from bs4 import BeautifulSoup, NavigableString
 
 from quasarr.providers.log import info, debug
 from quasarr.providers.sessions.dl import retrieve_and_validate_session, fetch_via_requests_session, invalidate_session
 
 hostname = "dl"
 
+# Common TLDs to strip for mirror name comparison
+COMMON_TLDS = {'.com', '.net', '.io', '.cc', '.to', '.me', '.org', '.co', '.de', '.eu', '.info'}
+
+
+def normalize_mirror_name(name):
+    """
+    Normalize mirror name for comparison by lowercasing and removing TLDs.
+    e.g., "DDownload.com" -> "ddownload", "Rapidgator.net" -> "rapidgator"
+    """
+    if not name:
+        return ""
+    normalized = name.lower().strip()
+    for tld in COMMON_TLDS:
+        if normalized.endswith(tld):
+            normalized = normalized[:-len(tld)]
+            break
+    return normalized
+
 
 def extract_password_from_post(soup, host):
     """
@@ -60,52 +81,289 @@ def extract_mirror_name_from_link(link_element):
         '1fichier': ['1fichier'],
     }
 
-    if link_text and len(link_text) > 2:
+    # Skip if link text is a URL
+    if link_text and len(link_text) > 2 and not link_text.startswith('http'):
         cleaned = re.sub(r'[^\w\s-]', '', link_text).strip().lower()
         if cleaned and cleaned not in common_non_hosters:
             main_part = cleaned.split()[0] if ' ' in cleaned else cleaned
             if 2 < len(main_part) < 30:
                 return main_part
 
-    parent = link_element.parent
-    if parent:
-        for sibling in link_element.previous_siblings:
-            # Only process Tag elements, skip NavigableString (text nodes)
-            if not hasattr(sibling, 'name') or sibling.name is None:
-                continue
+    # Check previous siblings including text nodes
+    for sibling in link_element.previous_siblings:
+        # Handle text nodes (NavigableString)
+        if isinstance(sibling, NavigableString):
+            text = sibling.strip()
+            if text:
+                # Remove common separators like @ : -
+                cleaned = re.sub(r'[@:\-–—\s]+$', '', text).strip().lower()
+                cleaned = re.sub(r'[^\w\s.-]', '', cleaned).strip()
+                if cleaned and len(cleaned) > 2 and cleaned not in common_non_hosters:
+                    # Take the last word as mirror name (e.g., "Rapidgator" from "Rapidgator @")
+                    parts = cleaned.split()
+                    if parts:
+                        mirror = parts[-1]
+                        if 2 < len(mirror) < 30:
+                            return mirror
+            continue
 
-            # Skip spoiler elements entirely
-            classes = sibling.get('class', [])
-            if classes and any('spoiler' in str(c).lower() for c in classes):
-                continue
+        # Skip non-Tag elements
+        if not hasattr(sibling, 'name') or sibling.name is None:
+            continue
+
+        # Skip spoiler elements entirely
+        classes = sibling.get('class', [])
+        if classes and any('spoiler' in str(c).lower() for c in classes):
+            continue
+
+        # Check for images with hoster names in src/alt/data-url
+        img = sibling.find('img') if sibling.name != 'img' else sibling
+        if img:
+            img_identifiers = (img.get('src', '') + img.get('alt', '') + img.get('data-url', '')).lower()
+            for hoster, patterns in known_hosters.items():
+                if any(pattern in img_identifiers for pattern in patterns):
+                    return hoster
+
+        sibling_text = sibling.get_text(strip=True).lower()
+        # Skip if text is too long - likely NFO content or other non-mirror text
+        if len(sibling_text) > 30:
+            continue
+        if sibling_text and len(sibling_text) > 2 and sibling_text not in common_non_hosters:
+            cleaned = re.sub(r'[^\w\s-]', '', sibling_text).strip()
+            if cleaned and 2 < len(cleaned) < 30:
+                return cleaned.split()[0] if ' ' in cleaned else cleaned
+
+    return None
 
-            # Check for images with hoster names in src/alt/data-url
-            img = sibling.find('img') if sibling.name != 'img' else sibling
-            if img:
-                img_identifiers = (img.get('src', '') + img.get('alt', '') + img.get('data-url', '')).lower()
-                for hoster, patterns in known_hosters.items():
-                    if any(pattern in img_identifiers for pattern in patterns):
-                        return hoster
-
-            sibling_text = sibling.get_text(strip=True).lower()
-            # Skip if text is too long - likely NFO content or other non-mirror text
-            if len(sibling_text) > 30:
-                continue
-            if sibling_text and len(sibling_text) > 2 and sibling_text not in common_non_hosters:
-                cleaned = re.sub(r'[^\w\s-]', '', sibling_text).strip()
-                if cleaned and 2 < len(cleaned) < 30:
-                    return cleaned.split()[0] if ' ' in cleaned else cleaned
+
+def generate_status_url(href, crypter_type):
+    """
+    Generate a status URL for crypters that support it.
+    Returns None if status URL cannot be generated.
+    """
+    if crypter_type == "hide":
+        # hide.cx links: https://hide.cx/folder/{UUID} → https://hide.cx/state/{UUID}
+        match = re.search(r'hide\.cx/(?:folder/)?([a-f0-9-]{36})', href, re.IGNORECASE)
+        if match:
+            uuid = match.group(1)
+            return f"https://hide.cx/state/{uuid}"
+
+    elif crypter_type == "tolink":
+        # tolink links: https://tolink.to/f/{ID} → https://tolink.to/f/{ID}/s/status.png
+        match = re.search(r'tolink\.to/f/([a-zA-Z0-9]+)', href, re.IGNORECASE)
+        if match:
+            link_id = match.group(1)
+            return f"https://tolink.to/f/{link_id}/s/status.png"
+
+    return None
+
+
+def extract_status_url_from_html(link_element, crypter_type):
+    """
+    Extract status image URL from HTML near the link element.
+    Used primarily for FileCrypt where status URLs cannot be generated.
+    """
+    if crypter_type != "filecrypt":
+        return None
+
+    # Look for status image in the link itself
+    img = link_element.find('img')
+    if img:
+        for attr in ['src', 'data-url']:
+            url = img.get(attr, '')
+            if 'filecrypt.cc/Stat/' in url:
+                return url
+
+    # Look in siblings
+    for sibling in link_element.next_siblings:
+        if not hasattr(sibling, 'name') or sibling.name is None:
+            continue
+        if sibling.name == 'img':
+            for attr in ['src', 'data-url']:
+                url = sibling.get(attr, '')
+                if 'filecrypt.cc/Stat/' in url:
+                    return url
+        # Check nested images
+        nested_img = sibling.find('img') if hasattr(sibling, 'find') else None
+        if nested_img:
+            for attr in ['src', 'data-url']:
+                url = nested_img.get(attr, '')
+                if 'filecrypt.cc/Stat/' in url:
+                    return url
+        # Stop at next link
+        if sibling.name == 'a':
+            break
 
     return None
 
 
+def build_filecrypt_status_map(soup):
+    """
+    Build a map of mirror names to FileCrypt status URLs.
+    Handles cases where status images are in a separate section from links.
+    Returns dict: {mirror_name_lowercase: status_url}
+    """
+    status_map = {}
+
+    # Find all FileCrypt status images in the post
+    for img in soup.find_all('img'):
+        status_url = None
+        for attr in ['src', 'data-url']:
+            url = img.get(attr, '')
+            if 'filecrypt.cc/Stat/' in url:
+                status_url = url
+                break
+
+        if not status_url:
+            continue
+
+        # Look for associated mirror name in previous text/siblings
+        mirror_name = None
+
+        # Check parent's previous siblings and text nodes
+        parent = img.parent
+        if parent:
+            # Get all previous text content before this image
+            prev_text = ""
+            for prev in parent.previous_siblings:
+                if hasattr(prev, 'get_text'):
+                    prev_text = prev.get_text(strip=True)
+                elif isinstance(prev, NavigableString):
+                    prev_text = prev.strip()
+                if prev_text:
+                    break
+
+            # Also check text directly before within parent
+            for prev in img.previous_siblings:
+                if isinstance(prev, NavigableString) and prev.strip():
+                    prev_text = prev.strip()
+                    break
+                elif hasattr(prev, 'get_text'):
+                    text = prev.get_text(strip=True)
+                    if text:
+                        prev_text = text
+                        break
+
+            if prev_text:
+                # Clean up the text to get mirror name
+                cleaned = re.sub(r'[^\w\s.-]', '', prev_text).strip().lower()
+                # Take last word/phrase as it's likely the mirror name
+                parts = cleaned.split()
+                if parts:
+                    mirror_name = parts[-1] if len(parts[-1]) > 2 else cleaned
+
+        if mirror_name and mirror_name not in status_map:
+            status_map[mirror_name] = status_url
+            debug(f"Mapped status image for mirror: {mirror_name} -> {status_url}")
+
+    return status_map
+
+
+def image_has_green(image_data):
+    """
+    Analyze image data to check if it contains green pixels.
+    Returns True if any significant green is detected (indicating online status).
+    """
+    try:
+        img = Image.open(BytesIO(image_data))
+        img = img.convert('RGB')
+
+        pixels = list(img.getdata())
+
+        for r, g, b in pixels:
+            # Check if pixel is greenish: green channel is dominant
+            # and has a reasonable absolute value
+            if g > 100 and g > r * 1.3 and g > b * 1.3:
+                return True
+
+        return False
+    except Exception as e:
+        debug(f"Error analyzing status image: {e}")
+        # If we can't analyze, assume online to not skip valid links
+        return True
+
+
+def fetch_status_image(status_url):
+    """
+    Fetch a status image and return (status_url, image_data).
+    Returns (status_url, None) on failure.
+    """
+    try:
+        import requests
+        response = requests.get(status_url, timeout=10)
+        if response.status_code == 200:
+            return (status_url, response.content)
+    except Exception as e:
+        debug(f"Error fetching status image {status_url}: {e}")
+    return (status_url, None)
+
+
+def check_links_online_status(links_with_status):
+    """
+    Check online status for links that have status URLs.
+    Returns list of links that are online (or have no status URL to check).
+
+    links_with_status: list of [href, identifier, status_url] where status_url can be None
+    """
+
+    links_to_check = [(i, link) for i, link in enumerate(links_with_status) if link[2]]
+
+    if not links_to_check:
+        # No status URLs to check, return all links as potentially online
+        return [[link[0], link[1]] for link in links_with_status]
+
+    # Batch fetch status images
+    status_results = {}  # status_url -> has_green
+    status_urls = list(set(link[2] for _, link in links_to_check))
+
+    batch_size = 10
+    for i in range(0, len(status_urls), batch_size):
+        batch = status_urls[i:i + batch_size]
+        with ThreadPoolExecutor(max_workers=batch_size) as executor:
+            futures = [executor.submit(fetch_status_image, url) for url in batch]
+            for future in as_completed(futures):
+                try:
+                    status_url, image_data = future.result()
+                    if image_data:
+                        status_results[status_url] = image_has_green(image_data)
+                    else:
+                        # Could not fetch, assume online
+                        status_results[status_url] = True
+                except Exception as e:
+                    debug(f"Error checking status: {e}")
+
+    # Filter to online links
+    online_links = []
+
+    for link in links_with_status:
+        href, identifier, status_url = link
+        if not status_url:
+            # No status URL, include link (keeplinks case)
+            online_links.append([href, identifier])
+        elif status_url in status_results:
+            if status_results[status_url]:
+                online_links.append([href, identifier])
+                debug(f"Link online: {identifier} ({href})")
+            else:
+                debug(f"Link offline: {identifier} ({href})")
+        else:
+            # Status check failed, include link
+            online_links.append([href, identifier])
+
+    return online_links
+
+
 def extract_links_and_password_from_post(post_content, host):
     """
     Extract download links and password from a forum post.
+    Returns links with status URLs for online checking.
     """
-    links = []
+    links = []  # [href, identifier, status_url]
     soup = BeautifulSoup(post_content, 'html.parser')
 
+    # Build status map for FileCrypt links (handles separated status images)
+    filecrypt_status_map = build_filecrypt_status_map(soup)
+
     for link in soup.find_all('a', href=True):
         href = link.get('href')
 
@@ -127,12 +385,29 @@ def extract_links_and_password_from_post(post_content, host):
         mirror_name = extract_mirror_name_from_link(link)
         identifier = mirror_name if mirror_name else crypter_type
 
-        if [href, identifier] not in links:
-            links.append([href, identifier])
+        # Get status URL - try extraction first, then status map, then generation
+        status_url = extract_status_url_from_html(link, crypter_type)
+
+        if not status_url and crypter_type == "filecrypt" and mirror_name:
+            # Try to find in status map by mirror name (normalized, case-insensitive, TLD-stripped)
+            mirror_normalized = normalize_mirror_name(mirror_name)
+            for map_key, map_url in filecrypt_status_map.items():
+                map_key_normalized = normalize_mirror_name(map_key)
+                if mirror_normalized in map_key_normalized or map_key_normalized in mirror_normalized:
+                    status_url = map_url
+                    break
+
+        if not status_url:
+            status_url = generate_status_url(href, crypter_type)
+
+        # Avoid duplicates (check href and identifier)
+        if not any(l[0] == href and l[1] == identifier for l in links):
+            links.append([href, identifier, status_url])
+            status_info = f"status: {status_url}" if status_url else "no status URL"
             if mirror_name:
-                debug(f"Found {crypter_type} link for mirror: {mirror_name}")
+                debug(f"Found {crypter_type} link for mirror: {mirror_name} ({status_info})")
             else:
-                debug(f"Found {crypter_type} link (no mirror name detected)")
+                debug(f"Found {crypter_type} link ({status_info})")
 
     password = ""
     if links:
@@ -146,6 +421,7 @@ def get_dl_download_links(shared_state, url, mirror, title, password):
     KEEP THE SIGNATURE EVEN IF SOME PARAMETERS ARE UNUSED!
 
     DL source handler - extracts links and password from forum thread.
+    Iterates through posts to find one with online links.
 
     Note: The password parameter is unused intentionally - password must be extracted from the post.
     """
@@ -166,24 +442,35 @@ def get_dl_download_links(shared_state, url, mirror, title, password):
 
         soup = BeautifulSoup(response.text, 'html.parser')
 
-        first_post = soup.select_one('article.message--post')
-        if not first_post:
-            info(f"Could not find first post in thread: {url}")
+        # Get all posts in thread
+        posts = soup.select('article.message--post')
+        if not posts:
+            info(f"Could not find any posts in thread: {url}")
             return {"links": [], "password": ""}
 
-        post_content = first_post.select_one('div.bbWrapper')
-        if not post_content:
-            info(f"Could not find post content in thread: {url}")
-            return {"links": [], "password": ""}
+        # Iterate through posts to find one with online links
+        for post_index, post in enumerate(posts):
+            post_content = post.select_one('div.bbWrapper')
+            if not post_content:
+                continue
 
-        links, extracted_password = extract_links_and_password_from_post(str(post_content), host)
+            links_with_status, extracted_password = extract_links_and_password_from_post(str(post_content), host)
 
-        if not links:
-            info(f"No supported download links found in thread: {url}")
-            return {"links": [], "password": ""}
+            if not links_with_status:
+                continue
+
+            # Check which links are online
+            online_links = check_links_online_status(links_with_status)
 
-        debug(f"Found {len(links)} download link(s) for: {title} (password: {extracted_password})")
-        return {"links": links, "password": extracted_password}
+            if online_links:
+                post_info = "first post" if post_index == 0 else f"post #{post_index + 1}"
+                debug(f"Found {len(online_links)} online link(s) in {post_info} for: {title}")
+                return {"links": online_links, "password": extracted_password}
+            else:
+                debug(f"All links in post #{post_index + 1} are offline, checking next post...")
+
+        info(f"No online download links found in any post: {url}")
+        return {"links": [], "password": ""}
 
     except Exception as e:
         info(f"Error extracting download links from {url}: {e}")

quasarr/providers/version.py

@@ -8,7 +8,7 @@ import requests
 
 
 def get_version():
-    return "1.26.3"
+    return "1.26.4"
 
 
 def get_latest_version():

{quasarr-1.26.3.dist-info → quasarr-1.26.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: quasarr
-Version: 1.26.3
+Version: 1.26.4
 Summary: Quasarr connects JDownloader with Radarr, Sonarr and LazyLibrarian. It also decrypts links protected by CAPTCHAs.
 Home-page: https://github.com/rix1337/Quasarr
 Author: rix1337
@@ -10,7 +10,7 @@ Classifier: License :: OSI Approved :: MIT License
 Classifier: Operating System :: OS Independent
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: beautifulsoup4>=4.14.2
+Requires-Dist: beautifulsoup4>=4.14.3
 Requires-Dist: bottle>=0.13.4
 Requires-Dist: dukpy>=0.5.0
 Requires-Dist: pillow>=12.0.0

{quasarr-1.26.3.dist-info → quasarr-1.26.4.dist-info}/RECORD

@@ -16,7 +16,7 @@ quasarr/downloads/sources/al.py,sha256=tb7HpMWFnW3VZCAjsk4tFZsh56xygDVmPgpv5cW1q
 quasarr/downloads/sources/by.py,sha256=kmUTn3izayRCV7W-t0E4kYE8qTbt3L3reCLozfvRGcU,3807
 quasarr/downloads/sources/dd.py,sha256=8X2tOle3qTq0b60Aa3o0uqp2vNELDHYYj99ERI7U_X0,2971
 quasarr/downloads/sources/dj.py,sha256=wY00hVRNhucZBG1hfExKqayhP1ISD8FFQm7wHYxutOk,404
-quasarr/downloads/sources/dl.py,sha256=-8q3vjgdmLykptLtcehB7NLCAn5YANGWRDrLJu2Xg00,7174
+quasarr/downloads/sources/dl.py,sha256=P11c6P2Pxf8EMZdxBFcnY0y_Z35IAE1cJfTEx1Wkkw0,17995
 quasarr/downloads/sources/dt.py,sha256=80yIHAivsqoPKAaFdZ4wPFBVGCbHNUO130pv7EO2LTM,2605
 quasarr/downloads/sources/dw.py,sha256=_28-E58Hs9NVwHyLt2M1oYUxVZ-wpE5dQv8gMNhiAPM,2622
 quasarr/downloads/sources/he.py,sha256=AA6OrIkD3KS_w1ClvXyW1_9hujM6A8P_5VcMHRM6ngg,3680
@@ -39,7 +39,7 @@ quasarr/providers/notifications.py,sha256=bohT-6yudmFnmZMc3BwCGX0n1HdzSVgQG_LDZm
 quasarr/providers/obfuscated.py,sha256=xPI3WrteOiZN5BgNDp0CURcYfkRrdnRCz_cT7BpzIJU,1363310
 quasarr/providers/shared_state.py,sha256=-TIiH2lkCfovq7bzUZicpUjXEjS87ZHCcevsFgySOqw,29944
 quasarr/providers/statistics.py,sha256=cEQixYnDMDqtm5wWe40E_2ucyo4mD0n3SrfelhQi1L8,6452
-quasarr/providers/version.py,sha256=vB7GtEbW1DfhRSEYx_GSfI0llKYAfVu3VTVFVwRZGW8,4004
+quasarr/providers/version.py,sha256=GAEHoTd_JPGHtyBwvxPAOOhjEUro28TLorMoV9n2yXs,4004
 quasarr/providers/web_server.py,sha256=AYd0KRxdDWMBr87BP8wlSMuL4zZo0I_rY-vHBai6Pfg,1688
 quasarr/providers/sessions/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 quasarr/providers/sessions/al.py,sha256=F1d76eAJcbTvb6YvAIlQ4gfrYC_256QAKiWEQcuWe8k,10612
@@ -69,9 +69,9 @@ quasarr/storage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 quasarr/storage/config.py,sha256=hOI7vvIo1YaML3dtAkTmp0HSedWF6brVhRk3d8pJtXI,6300
 quasarr/storage/setup.py,sha256=V_dWfyCYxRE_ahmBtD-DmHOKP2L6brBcVYydPRcHjns,21448
 quasarr/storage/sqlite_database.py,sha256=yMqFQfKf0k7YS-6Z3_7pj4z1GwWSXJ8uvF4IydXsuTE,3554
-quasarr-1.26.3.dist-info/licenses/LICENSE,sha256=QQFCAfDgt7lSA8oSWDHIZ9aTjFbZaBJdjnGOHkuhK7k,1060
-quasarr-1.26.3.dist-info/METADATA,sha256=FEvSChsXKwehAV-G8x14lOP3v1cDw5-qpsK0YTdmAwY,12805
-quasarr-1.26.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-quasarr-1.26.3.dist-info/entry_points.txt,sha256=gXi8mUKsIqKVvn-bOc8E5f04sK_KoMCC-ty6b2Hf-jc,40
-quasarr-1.26.3.dist-info/top_level.txt,sha256=dipJdaRda5ruTZkoGfZU60bY4l9dtPlmOWwxK_oGSF0,8
-quasarr-1.26.3.dist-info/RECORD,,
+quasarr-1.26.4.dist-info/licenses/LICENSE,sha256=QQFCAfDgt7lSA8oSWDHIZ9aTjFbZaBJdjnGOHkuhK7k,1060
+quasarr-1.26.4.dist-info/METADATA,sha256=WctqxWiUX7TalmsjliMVQoB1cQmT3kmCF4pYqJ7KsCk,12805
+quasarr-1.26.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+quasarr-1.26.4.dist-info/entry_points.txt,sha256=gXi8mUKsIqKVvn-bOc8E5f04sK_KoMCC-ty6b2Hf-jc,40
+quasarr-1.26.4.dist-info/top_level.txt,sha256=dipJdaRda5ruTZkoGfZU60bY4l9dtPlmOWwxK_oGSF0,8
+quasarr-1.26.4.dist-info/RECORD,,