webscout 8.2.2__py3-none-any.whl → 2026.1.19__py3-none-any.whl

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}")

webscout/Extra/YTToolkit/ytapi/stream.py

@@ -1,63 +1,68 @@
-import re
-from typing import Dict, Any
-
-from .pool import collect
-from .https import video_data
-from .patterns import _VideoPatterns as Patterns
-
-
-class Video:
-
-    _HEAD = 'https://www.youtube.com/watch?v='
-
-    def __init__(self, video_id: str):
-        pattern = re.compile('.be/(.*?)$|=(.*?)$|^(\w{11})$')  # noqa
-        self._matched_id = (
-                pattern.search(video_id).group(1)
-                or pattern.search(video_id).group(2)
-                or pattern.search(video_id).group(3)
-        )
-        if self._matched_id:
-            self._url = self._HEAD + self._matched_id
-            self._video_data = video_data(self._matched_id)
-        else:
-            raise ValueError('invalid video id or url')
-
-    def __repr__(self):
-        return f'<Video {self._url}>'
-
-    @property
-    def metadata(self) -> Dict[str, Any]:
-        patterns = [
-            Patterns.title,
-            Patterns.views,
-            Patterns.likes,
-            Patterns.duration,
-            Patterns.author_id,
-            Patterns.upload_date,
-            Patterns.thumbnail,
-            Patterns.tags,
-            Patterns.description,
-            Patterns.is_streamed,
-            Patterns.is_premiered
-        ]
-        ext = collect(lambda x: x.findall(self._video_data) or None, patterns)
-        data = [i[0] if i else i for i in ext]
-        return {
-            'title': data[0],
-            'id': self._matched_id,
-            'views': data[1][:-6] if data[1] else None,
-            'likes': data[2],
-            'streamed': data[9] is not None,
-            'premiered': data[10],
-            'duration': int(data[3]) / 1000 if data[3] else None,
-            'author': data[4],
-            'upload_date': data[5],
-            'url': self._url,
-            'thumbnail': data[6],
-            'tags': data[7].split(',') if data[7] else None,
-            'description': data[8].replace('\\n', '\n') if data[8] else None
-        }
-
-if __name__ == '__main__':
-    print(Video('https://www.youtube.com/watch?v=9bZkp7q19f0').metadata)
+import re
+from typing import Any, Dict, Optional
+
+from .https import video_data
+from .patterns import _VideoPatterns as Patterns
+from .pool import collect
+
+
+class Video:
+
+    _HEAD = 'https://www.youtube.com/watch?v='
+
+    def __init__(self, video_id: str):
+        pattern = re.compile(r'.be/(.*?)$|=(.*?)$|^(\w{11})$')  # noqa
+        match = pattern.search(video_id)
+        if match:
+            self._matched_id = (
+                    match.group(1)
+                    or match.group(2)
+                    or match.group(3)
+            )
+        else:
+            self._matched_id = None
+
+        if self._matched_id:
+            self._url = self._HEAD + self._matched_id
+            self._video_data = video_data(self._matched_id)
+        else:
+            raise ValueError('invalid video id or url')
+
+    def __repr__(self):
+        return f'<Video {self._url}>'
+
+    @property
+    def metadata(self) -> Dict[str, Any]:
+        patterns = [
+            Patterns.title,
+            Patterns.views,
+            Patterns.likes,
+            Patterns.duration,
+            Patterns.author_id,
+            Patterns.upload_date,
+            Patterns.thumbnail,
+            Patterns.tags,
+            Patterns.description,
+            Patterns.is_streamed,
+            Patterns.is_premiered
+        ]
+        ext = collect(lambda x: x.findall(self._video_data) or None, patterns)
+        data = [i[0] if i else i for i in ext]
+        return {
+            'title': data[0],
+            'id': self._matched_id,
+            'views': data[1][:-6] if data[1] else None,
+            'likes': data[2],
+            'streamed': data[9] is not None,
+            'premiered': data[10],
+            'duration': int(data[3]) / 1000 if data[3] else None,
+            'author': data[4],
+            'upload_date': data[5],
+            'url': self._url,
+            'thumbnail': data[6],
+            'tags': data[7].split(',') if data[7] else None,
+            'description': data[8].replace('\\n', '\n') if data[8] else None
+        }
+
+if __name__ == '__main__':
+    print(Video('https://www.youtube.com/watch?v=9bZkp7q19f0').metadata)

webscout/Extra/YTToolkit/ytapi/suggestions.py

@@ -0,0 +1,97 @@
+"""YouTube search suggestions and autocomplete."""
+import json
+from typing import List, Optional
+from urllib.parse import quote
+from urllib.request import Request, urlopen
+
+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 Suggestions:
+    """Class for YouTube search suggestions and autocomplete."""
+
+    AUTOCOMPLETE_URL = "https://suggestqueries.google.com/complete/search"
+
+    @staticmethod
+    def autocomplete(query: str, language: str = "en") -> List[str]:
+        """
+        Get YouTube autocomplete suggestions for a search query.
+
+        Args:
+            query: Search query to get suggestions for
+            language: Language code (e.g., 'en', 'es', 'fr')
+
+        Returns:
+            List of autocomplete suggestions
+        """
+        if not query:
+            return []
+
+        url = f"{Suggestions.AUTOCOMPLETE_URL}?client=youtube&ds=yt&q={quote(query)}&hl={language}"
+
+        headers = {
+            "User-Agent": _USER_AGENT,
+            "Accept": "application/json"
+        }
+
+        try:
+            req = Request(url, headers=headers)
+            response = urlopen(req, timeout=10)
+            data = response.read().decode('utf-8')
+
+            # Response is JSONP, extract JSON part
+            # Format: window.google.ac.h(["query",[["suggestion1"],["suggestion2"],...]])
+            start = data.find('(')
+            end = data.rfind(')')
+            if start != -1 and end != -1:
+                json_str = data[start + 1:end]
+                parsed = json.loads(json_str)
+                if len(parsed) > 1 and isinstance(parsed[1], list):
+                    return [item[0] for item in parsed[1] if isinstance(item, list) and item]
+            return []
+        except Exception:
+            return []
+
+    @staticmethod
+    def trending_searches(language: str = "en", country: str = "US") -> List[str]:
+        """
+        Get trending YouTube searches.
+
+        Args:
+            language: Language code
+            country: Country code
+
+        Returns:
+            List of trending search terms
+        """
+        # Get suggestions for empty-ish queries that return trending
+        trending = []
+        for seed in ["", "how to", "what is", "best"]:
+            suggestions = Suggestions.autocomplete(seed, language)
+            trending.extend(suggestions[:3])
+
+        # Remove duplicates while preserving order
+        seen = set()
+        unique = []
+        for item in trending:
+            if item not in seen:
+                seen.add(item)
+                unique.append(item)
+
+        return unique[:20]
+
+
+if __name__ == "__main__":
+    print("Testing autocomplete:")
+    suggestions = Suggestions.autocomplete("python tutorial")
+    for s in suggestions[:5]:
+        print(f"  - {s}")
+
+    print("\nTrending searches:")
+    trending = Suggestions.trending_searches()
+    for t in trending[:5]:
+        print(f"  - {t}")