webscout 8.2.9__py3-none-any.whl → 2026.1.19__py3-none-any.whl

webscout/Extra/YTToolkit/ytapi/patterns.py

@@ -1,61 +1,61 @@
-import re
-
-
-class _ChannelPatterns:
-    name = re.compile('channelMetadataRenderer\":{\"title\":\"(.*?)\"')
-    id = re.compile('channelId\":\"(.*?)\"')
-    verified = re.compile('"label":"Verified"')
-    check_live = re.compile('{"text":"LIVE"}')
-    live = re.compile("thumbnailOverlays\":\[(.*?)]")
-    video_id = re.compile('videoId\":\"(.*?)\"')
-    uploads = re.compile("gridVideoRenderer\":{\"videoId\":\"(.*?)\"")
-    subscribers = re.compile("\"subscriberCountText\":{\"accessibility\":(.*?),")
-    views = re.compile("viewCountText\":{\"simpleText\":\"(.*?)\"}")
-    creation = re.compile("{\"text\":\"Joined \"},{\"text\":\"(.*?)\"}")
-    country = re.compile("country\":{\"simpleText\":\"(.*?)\"}")
-    custom_url = re.compile("canonicalChannelUrl\":\"(.*?)\"")
-    description = re.compile("{\"description\":{\"simpleText\":\"(.*?)\"}")
-    avatar = re.compile("height\":88},{\"url\":\"(.*?)\"")
-    banner = re.compile("width\":1280,\"height\":351},{\"url\":\"(.*?)\"")
-    playlists = re.compile("{\"url\":\"/playlist\\?list=(.*?)\"")
-    video_count = re.compile("videoCountText\":{\"runs\":\[{\"text\":(.*?)}")
-    socials = re.compile("q=https%3A%2F%2F(.*?)\"")
-    upload_ids = re.compile("videoId\":\"(.*?)\"")
-    stream_ids = re.compile("videoId\":\"(.*?)\"")
-    upload_chunk = re.compile("gridVideoRenderer\":{(.*?)\"navigationEndpoint")
-    upload_chunk_fl_1 = re.compile("simpleText\":\"Streamed")
-    upload_chunk_fl_2 = re.compile("default_live.")
-    upcoming_check = re.compile("\"title\":\"Upcoming live streams\"")
-    upcoming = re.compile("gridVideoRenderer\":{\"videoId\":\"(.*?)\"")
-
-
-class _VideoPatterns:
-    video_id = re.compile('videoId\":\"(.*?)\"')
-    title = re.compile("title\":\"(.*?)\"")
-    duration = re.compile("approxDurationMs\":\"(.*?)\"")
-    upload_date = re.compile("uploadDate\":\"(.*?)\"")
-    author_id = re.compile("channelIds\":\[\"(.*?)\"")
-    description = re.compile("shortDescription\":\"(.*)\",\"isCrawlable")
-    tags = re.compile("<meta name=\"keywords\" content=\"(.*?)\">")
-    is_streamed = re.compile("simpleText\":\"Streamed live")
-    is_premiered = re.compile("dateText\":{\"simpleText\":\"Premiered")
-    views = re.compile("videoViewCountRenderer\":{\"viewCount\":{\"simpleText\":\"(.*?)\"")
-    likes = re.compile("toggledText\":{\"accessibility\":{\"accessibilityData\":{\"label\":\"(.*?) ")
-    thumbnail = re.compile("playerMicroformatRenderer\":{\"thumbnail\":{\"thumbnails\":\[{\"url\":\"(.*?)\"")
-
-
-class _PlaylistPatterns:
-    name = re.compile("{\"title\":\"(.*?)\"")
-    video_count = re.compile("stats\":\[{\"runs\":\[{\"text\":\"(.*?)\"")
-    video_id = re.compile("videoId\":\"(.*?)\"")
-    thumbnail = re.compile("og:image\" content=\"(.*?)\?")
-
-
-class _ExtraPatterns:
-    video_id = re.compile("videoId\":\"(.*?)\"")
-
-
-class _QueryPatterns:
-    channel_id = re.compile("channelId\":\"(.*?)\"")
-    video_id = re.compile("videoId\":\"(.*?)\"")
-    playlist_id = re.compile("playlistId\":\"(.*?)\"")
+import re
+
+
+class _ChannelPatterns:
+    name = re.compile(r'channelMetadataRenderer\":{\"title\":\"(.*?)\"')
+    id = re.compile(r'channelId\":\"(.*?)\"')
+    verified = re.compile(r'"label":"Verified"')
+    check_live = re.compile(r'{"text":"LIVE"}')
+    live = re.compile(r"thumbnailOverlays\":\[(.*?)]")
+    video_id = re.compile(r'videoId\":\"(.*?)\"')
+    uploads = re.compile(r"gridVideoRenderer\":{\"videoId\":\"(.*?)\"")
+    subscribers = re.compile(r"\"subscriberCountText\":{\"accessibility\":(.*?),")
+    views = re.compile(r"viewCountText\":{\"simpleText\":\"(.*?)\"}")
+    creation = re.compile(r"{\"text\":\"Joined \"},{\"text\":\"(.*?)\"}")
+    country = re.compile(r"country\":{\"simpleText\":\"(.*?)\"}")
+    custom_url = re.compile(r"canonicalChannelUrl\":\"(.*?)\"")
+    description = re.compile(r"{\"description\":{\"simpleText\":\"(.*?)\"}")
+    avatar = re.compile(r"height\":88},{\"url\":\"(.*?)\"")
+    banner = re.compile(r"width\":1280,\"height\":351},{\"url\":\"(.*?)\"")
+    playlists = re.compile(r"{\"url\":\"/playlist\?list=(.*?)\"")
+    video_count = re.compile(r"videoCountText\":{\"runs\":\[{\"text\":(.*?)}")
+    socials = re.compile(r"q=https%3A%2F%2F(.*?)\"")
+    upload_ids = re.compile(r"videoId\":\"(.*?)\"")
+    stream_ids = re.compile(r"videoId\":\"(.*?)\"")
+    upload_chunk = re.compile(r"gridVideoRenderer\":{(.*?)\"navigationEndpoint")
+    upload_chunk_fl_1 = re.compile(r"simpleText\":\"Streamed")
+    upload_chunk_fl_2 = re.compile(r"default_live.")
+    upcoming_check = re.compile(r"\"title\":\"Upcoming live streams\"")
+    upcoming = re.compile(r"gridVideoRenderer\":{\"videoId\":\"(.*?)\"")
+
+
+class _VideoPatterns:
+    video_id = re.compile(r'videoId\":\"(.*?)\"')
+    title = re.compile(r"title\":\"(.*?)\"")
+    duration = re.compile(r"approxDurationMs\":\"(.*?)\"")
+    upload_date = re.compile(r"uploadDate\":\"(.*?)\"")
+    author_id = re.compile(r"channelIds\":\[\"(.*?)\"")
+    description = re.compile(r"shortDescription\":\"(.*)\",\"isCrawlable")
+    tags = re.compile(r"<meta name=\"keywords\" content=\"(.*?)\">")
+    is_streamed = re.compile(r"simpleText\":\"Streamed live")
+    is_premiered = re.compile(r"dateText\":{\"simpleText\":\"Premiered")
+    views = re.compile(r"videoViewCountRenderer\":{\"viewCount\":{\"simpleText\":\"(.*?)\"")
+    likes = re.compile(r"toggledText\":{\"accessibility\":{\"accessibilityData\":{\"label\":\"(.*?) ")
+    thumbnail = re.compile(r"playerMicroformatRenderer\":{\"thumbnail\":{\"thumbnails\":\[{\"url\":\"(.*?)\"")
+
+
+class _PlaylistPatterns:
+    name = re.compile(r"{\"title\":\"(.*?)\"")
+    video_count = re.compile(r"stats\":\[{\"runs\":\[{\"text\":\"(.*?)\"")
+    video_id = re.compile(r"videoId\":\"(.*?)\"")
+    thumbnail = re.compile(r"og:image\" content=\"(.*?)\?")
+
+
+class _ExtraPatterns:
+    video_id = re.compile(r"videoId\":\"(.*?)\"")
+
+
+class _QueryPatterns:
+    channel_id = re.compile(r"channelId\":\"(.*?)\"")
+    video_id = re.compile(r"videoId\":\"(.*?)\"")
+    playlist_id = re.compile(r"playlistId\":\"(.*?)\"")

webscout/Extra/YTToolkit/ytapi/playlist.py

@@ -1,59 +1,59 @@
-import re
-from typing import Dict, Any
-
-from .pool import collect
-from .utils import dup_filter
-from .https import playlist_data
-from .patterns import _PlaylistPatterns as Patterns
-
-
-class Playlist:
-
-    def __init__(self, playlist_id: str):
-        """
-        Represents a YouTube Playlist
-
-        Parameters
-        ----------
-        playlist_id : str
-            The id or url of the playlist
-        """
-        pattern = re.compile('=(.+?)$|^PL(.+?)$')
-        match = pattern.search(playlist_id)
-        if not match:
-            raise ValueError(f'Invalid playlist id: {playlist_id}')
-        if match.group(1):
-            self.id = match.group(1)
-        elif match.group(2):
-            self.id = 'PL' + match.group(2)
-        self._playlist_data = playlist_data(self.id)
-
-    def __repr__(self):
-        return f'<Playlist {self.id}>'
-
-    @property
-    def metadata(self) -> Dict[str, Any]:
-        """
-        Fetches playlist metadata in a dict format
-
-        Returns
-        -------
-        Dict
-            Playlist metadata in a dict format containing keys: id, url, name, video_count, thumbnail,
-        """
-        patterns = [
-            Patterns.name,
-            Patterns.video_count,
-            Patterns.thumbnail,
-            Patterns.video_id,
-        ]
-        ext = collect(lambda x: x.findall(self._playlist_data) or None, patterns)
-        data = [e[0] if e else None for e in ext]
-        return {
-            'id': self.id,
-            'url': 'https://www.youtube.com/playlist?list=' + self.id,
-            'name': data[0] if data else None,
-            'video_count': data[1] if data else None,
-            'thumbnail': data[2] if data else None,
-            'videos': dup_filter(ext[3])
-        }
+import re
+from typing import Any, Dict, Optional
+
+from .https import playlist_data
+from .patterns import _PlaylistPatterns as Patterns
+from .pool import collect
+from .utils import dup_filter
+
+
+class Playlist:
+
+    def __init__(self, playlist_id: str):
+        """
+        Represents a YouTube Playlist
+
+        Parameters
+        ----------
+        playlist_id : str
+            The id or url of the playlist
+        """
+        pattern = re.compile('=(.+?)$|^PL(.+?)$')
+        match = pattern.search(playlist_id)
+        if not match:
+            raise ValueError(f'Invalid playlist id: {playlist_id}')
+        if match.group(1):
+            self.id = match.group(1)
+        elif match.group(2):
+            self.id = 'PL' + match.group(2)
+        self._playlist_data = playlist_data(self.id)
+
+    def __repr__(self):
+        return f'<Playlist {self.id}>'
+
+    @property
+    def metadata(self) -> Dict[str, Any]:
+        """
+        Fetches playlist metadata in a dict format
+
+        Returns
+        -------
+        Dict
+            Playlist metadata in a dict format containing keys: id, url, name, video_count, thumbnail,
+        """
+        patterns = [
+            Patterns.name,
+            Patterns.video_count,
+            Patterns.thumbnail,
+            Patterns.video_id,
+        ]
+        ext = collect(lambda x: x.findall(self._playlist_data) or None, patterns)
+        data = [e[0] if e else None for e in ext]
+        return {
+            'id': self.id,
+            'url': 'https://www.youtube.com/playlist?list=' + self.id,
+            'name': data[0] if data else None,
+            'video_count': data[1] if data else None,
+            'thumbnail': data[2] if data else None,
+            'videos': dup_filter(ext[3])
+        }

webscout/Extra/YTToolkit/ytapi/pool.py

@@ -1,8 +1,8 @@
-import concurrent.futures
-from typing import Callable, List, Any
-
-
-def collect(func: Callable, args: List[Any]) -> List[Any]:
-    max_workers = len(args) or 1
-    with concurrent.futures.ThreadPoolExecutor(max_workers) as exe:
-        return list(exe.map(func, args))
+import concurrent.futures
+from typing import Any, Callable, List, Optional
+
+
+def collect(func: Callable, args: List[Any]) -> List[Any]:
+    max_workers = len(args) or 1
+    with concurrent.futures.ThreadPoolExecutor(max_workers) as exe:
+        return list(exe.map(func, args))

webscout/Extra/YTToolkit/ytapi/query.py

@@ -1,40 +1,143 @@
-from .utils import dup_filter
-from .video import Video
-from .channel import Channel
-from .playlist import Playlist
-from .patterns import _QueryPatterns as Patterns
-from typing import Optional, Dict, Any, List
-from .https import find_videos, find_channels, find_playlists
-
-
-class Search:
-
-    @staticmethod
-    def video(keywords: str) -> Optional[Video]:
-        video_ids = Patterns.video_id.findall(find_videos(keywords))
-        return Video(video_ids[0]) if video_ids else None
-
-    @staticmethod
-    def channel(keywords: str) -> Optional[Channel]:
-        channel_ids = Patterns.channel_id.findall(find_channels(keywords))
-        return Channel(channel_ids[0]) if channel_ids else None
-
-    @staticmethod
-    def playlist(keywords: str) -> Optional[Playlist]:
-        playlist_ids = Patterns.playlist_id.findall(find_playlists(keywords))
-        return Playlist(playlist_ids[0]) if playlist_ids else None
-
-    @staticmethod
-    def videos(keywords: str, limit: int = 20) -> Optional[List[str]]:
-        return dup_filter(Patterns.video_id.findall(find_videos(keywords)), limit)
-
-    @staticmethod
-    def channels(keywords: str, limit: int = 20) -> Optional[List[str]]:
-        return dup_filter(Patterns.channel_id.findall(find_channels(keywords)), limit)
-
-    @staticmethod
-    def playlists(keywords: str, limit: int = 20) -> Optional[List[str]]:
-        return dup_filter(Patterns.playlist_id.findall(find_playlists(keywords)), limit)
-
-if __name__ == "__main__":
-    print(Search.videos("java"))
+from typing import List, Optional
+from urllib.parse import quote
+
+from .channel import Channel
+from .https import find_channels, find_playlists, find_videos
+from .patterns import _QueryPatterns as Patterns
+from .playlist import Playlist
+from .utils import dup_filter, request
+from .video import Video
+
+
+class Search:
+
+    @staticmethod
+    def video(keywords: str) -> Optional[Video]:
+        video_ids = Patterns.video_id.findall(find_videos(keywords))
+        return Video(video_ids[0]) if video_ids else None
+
+    @staticmethod
+    def channel(keywords: str) -> Optional[Channel]:
+        channel_ids = Patterns.channel_id.findall(find_channels(keywords))
+        return Channel(channel_ids[0]) if channel_ids else None
+
+    @staticmethod
+    def playlist(keywords: str) -> Optional[Playlist]:
+        playlist_ids = Patterns.playlist_id.findall(find_playlists(keywords))
+        return Playlist(playlist_ids[0]) if playlist_ids else None
+
+    @staticmethod
+    def videos(keywords: str, limit: int = 20) -> Optional[List[str]]:
+        return dup_filter(Patterns.video_id.findall(find_videos(keywords)), limit)
+
+    @staticmethod
+    def channels(keywords: str, limit: int = 20) -> Optional[List[str]]:
+        return dup_filter(Patterns.channel_id.findall(find_channels(keywords)), limit)
+
+    @staticmethod
+    def playlists(keywords: str, limit: int = 20) -> Optional[List[str]]:
+        return dup_filter(Patterns.playlist_id.findall(find_playlists(keywords)), limit)
+
+    @staticmethod
+    def shorts(keywords: str, limit: int = 20) -> Optional[List[str]]:
+        """
+        Search for YouTube Shorts.
+
+        Args:
+            keywords: Search query
+            limit: Maximum number of results
+
+        Returns:
+            List of video IDs for matching Shorts
+        """
+        # sp=EgIYAQ%253D%253D is the filter for Shorts
+        url = f"https://www.youtube.com/results?search_query={quote(keywords)}&sp=EgIYAQ%253D%253D"
+        try:
+            html = request(url)
+            return dup_filter(Patterns.video_id.findall(html), limit)
+        except Exception:
+            return []
+
+    @staticmethod
+    def live_streams(keywords: str, limit: int = 20) -> Optional[List[str]]:
+        """
+        Search for live streams.
+
+        Args:
+            keywords: Search query
+            limit: Maximum number of results
+
+        Returns:
+            List of video IDs for live streams
+        """
+        # sp=EgJAAQ%253D%253D is the filter for live streams
+        url = f"https://www.youtube.com/results?search_query={quote(keywords)}&sp=EgJAAQ%253D%253D"
+        try:
+            html = request(url)
+            return dup_filter(Patterns.video_id.findall(html), limit)
+        except Exception:
+            return []
+
+    @staticmethod
+    def videos_by_duration(keywords: str, duration: str = "short", limit: int = 20) -> Optional[List[str]]:
+        """
+        Search videos filtered by duration.
+
+        Args:
+            keywords: Search query
+            duration: Duration filter - "short" (<4 min), "medium" (4-20 min), "long" (>20 min)
+            limit: Maximum number of results
+
+        Returns:
+            List of video IDs
+        """
+        duration_filters = {
+            "short": "EgIYAQ%253D%253D",    # Under 4 minutes
+            "medium": "EgIYAw%253D%253D",   # 4-20 minutes
+            "long": "EgIYAg%253D%253D"      # Over 20 minutes
+        }
+        sp = duration_filters.get(duration, "")
+        url = f"https://www.youtube.com/results?search_query={quote(keywords)}&sp={sp}"
+        try:
+            html = request(url)
+            return dup_filter(Patterns.video_id.findall(html), limit)
+        except Exception:
+            return []
+
+    @staticmethod
+    def videos_by_upload_date(keywords: str, when: str = "today", limit: int = 20) -> Optional[List[str]]:
+        """
+        Search videos filtered by upload date.
+
+        Args:
+            keywords: Search query
+            when: Time filter - "hour", "today", "week", "month", "year"
+            limit: Maximum number of results
+
+        Returns:
+            List of video IDs
+        """
+        date_filters = {
+            "hour": "EgIIAQ%253D%253D",
+            "today": "EgIIAg%253D%253D",
+            "week": "EgIIAw%253D%253D",
+            "month": "EgIIBA%253D%253D",
+            "year": "EgIIBQ%253D%253D"
+        }
+        sp = date_filters.get(when, "")
+        url = f"https://www.youtube.com/results?search_query={quote(keywords)}&sp={sp}"
+        try:
+            html = request(url)
+            return dup_filter(Patterns.video_id.findall(html), limit)
+        except Exception:
+            return []
+
+
+if __name__ == "__main__":
+    print("Testing Search.shorts:")
+    shorts = Search.shorts("funny", 5)
+    print(f"  Found: {shorts}")
+
+    print("\nTesting Search.live_streams:")
+    live = Search.live_streams("music", 5)
+    print(f"  Found: {live}")

webscout/Extra/YTToolkit/ytapi/shorts.py

@@ -0,0 +1,122 @@
+"""YouTube Shorts functionality."""
+import re
+from typing import List, Optional
+from urllib.error import HTTPError
+from urllib.request import Request, urlopen
+
+from .patterns import _ExtraPatterns as Patterns
+from .utils import dup_filter, request
+
+try:
+    from webscout.litagent.agent import LitAgent
+    _USER_AGENT = LitAgent().random()
+except ImportError:
+    _USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"
+
+
+class Shorts:
+    """Class for YouTube Shorts operations."""
+
+    SHORTS_URL = "https://www.youtube.com/shorts"
+
+    @staticmethod
+    def is_short(video_id: str) -> bool:
+        """
+        Check if a video is a YouTube Short.
+
+        Args:
+            video_id: YouTube video ID
+
+        Returns:
+            True if video is a Short, False otherwise
+        """
+        if not video_id:
+            return False
+
+        # Clean video ID
+        if "youtube.com" in video_id or "youtu.be" in video_id:
+            match = re.search(r'(?:v=|shorts/|youtu\.be/)([a-zA-Z0-9_-]{11})', video_id)
+            if match:
+                video_id = match.group(1)
+
+        url = f"https://www.youtube.com/shorts/{video_id}"
+
+        try:
+            headers = {
+                "User-Agent": _USER_AGENT,
+                "Accept": "text/html"
+            }
+            req = Request(url, headers=headers, method='HEAD')
+            response = urlopen(req, timeout=10)
+            # If we get a 200 and URL contains /shorts/, it's a Short
+            final_url = response.geturl()
+            return "/shorts/" in final_url
+        except HTTPError as e:
+            if e.code == 303 or e.code == 302:
+                # Redirect means it's not a Short (redirects to /watch)
+                return False
+            return False
+        except Exception:
+            return False
+
+    @staticmethod
+    def get_trending(limit: int = 20) -> List[str]:
+        """
+        Get trending YouTube Shorts.
+
+        Args:
+            limit: Maximum number of Shorts to return
+
+        Returns:
+            List of video IDs for trending Shorts
+        """
+        try:
+            html = request("https://www.youtube.com/shorts")
+            # Find video IDs in shorts context
+            pattern = r'"videoId":"([a-zA-Z0-9_-]{11})"'
+            video_ids = re.findall(pattern, html)
+            return dup_filter(video_ids, limit)
+        except Exception:
+            return []
+
+    @staticmethod
+    def search(query: str, limit: int = 20) -> List[str]:
+        """
+        Search for YouTube Shorts.
+
+        Args:
+            query: Search query
+            limit: Maximum number of results
+
+        Returns:
+            List of video IDs for matching Shorts
+        """
+        if not query:
+            return []
+
+        from urllib.parse import quote
+        # sp=EgIYAQ%253D%253D is the filter for Shorts
+        url = f"https://www.youtube.com/results?search_query={quote(query)}&sp=EgIYAQ%253D%253D"
+
+        try:
+            html = request(url)
+            video_ids = Patterns.video_id.findall(html)
+            return dup_filter(video_ids, limit)
+        except Exception:
+            return []
+
+
+if __name__ == "__main__":
+    print("Testing Shorts.is_short:")
+    # Test with a known Short ID (you'd replace with an actual Short ID)
+    print(f"  is_short test: {Shorts.is_short('abc123')}")
+
+    print("\nTrending Shorts:")
+    trending = Shorts.get_trending(5)
+    for vid in trending:
+        print(f"  - {vid}")
+
+    print("\nSearch Shorts:")
+    results = Shorts.search("funny cats", 5)
+    for vid in results:
+        print(f"  - {vid}")