webscout 8.2.7__py3-none-any.whl → 8.2.8__py3-none-any.whl

webscout/Extra/YTToolkit/ytapi/query.py

@@ -0,0 +1,40 @@
+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"))

webscout/Extra/YTToolkit/ytapi/stream.py

@@ -0,0 +1,63 @@
+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)

webscout/Extra/YTToolkit/ytapi/utils.py

@@ -0,0 +1,62 @@
+from urllib.request import Request, urlopen
+from collections import OrderedDict
+from urllib.error import HTTPError
+from .errors import TooManyRequests, InvalidURL, RequestError
+from webscout.litagent import LitAgent
+
+
+__all__ = ['dup_filter', 'request']
+
+
+_USER_AGENT_GENERATOR = LitAgent()
+
+
+def request(url: str, retry_attempts: int = 3) -> str:
+    """
+    Send a request with a random user agent and built-in retry mechanism.
+    
+    Args:
+        url (str): The URL to request
+        retry_attempts (int, optional): Number of retry attempts. Defaults to 3.
+    
+    Raises:
+        InvalidURL: If the URL cannot be found
+        TooManyRequests: If rate-limited
+        RequestError: For other request-related errors
+    
+    Returns:
+        str: Decoded response content
+    """
+    for attempt in range(retry_attempts):
+        try:
+            headers = {
+                "User-Agent": _USER_AGENT_GENERATOR.random()
+            }
+            
+            req = Request(url, headers=headers)
+            response = urlopen(req)
+            return response.read().decode('utf-8')
+        
+        except HTTPError as e:
+            if e.code == 404:
+                raise InvalidURL(f'Cannot find anything with the requested URL: {url}')
+            if e.code == 429:
+                raise TooManyRequests(f'Rate-limited on attempt {attempt + 1}')
+            
+            if attempt == retry_attempts - 1:
+                raise RequestError(f'HTTP Error {e.code}: {e.reason}') from e
+        
+        except Exception as e:
+            if attempt == retry_attempts - 1:
+                raise RequestError(f'Request failed: {e!r}') from None
+
+
+def dup_filter(iterable: list, limit: int = None) -> list:
+    if not iterable:
+        return []
+    lim = limit if limit else len(iterable)
+    converted = list(OrderedDict.fromkeys(iterable))
+    if len(converted) - lim > 0:
+        return converted[:-len(converted) + lim]
+    else:
+        return converted

webscout/Extra/YTToolkit/ytapi/video.py

@@ -0,0 +1,232 @@
+import re
+import json
+from typing import Dict, Any
+from .https import video_data
+
+
+class Video:
+
+    _HEAD = 'https://www.youtube.com/watch?v='
+
+    def __init__(self, video_id: str):
+        """
+        Represents a YouTube video
+
+        Parameters
+        ----------
+        video_id : str
+            The id or url of the video
+        """
+        pattern = re.compile('.be/(.*?)$|=(.*?)$|^(\w{11})$')  # noqa
+        match = pattern.search(video_id)
+
+        if not match:
+            raise ValueError('Invalid YouTube video ID or URL')
+
+        self._matched_id = (
+                match.group(1)
+                or match.group(2)
+                or match.group(3)
+        )
+
+        if self._matched_id:
+            self._url = self._HEAD + self._matched_id
+            self._video_data = video_data(self._matched_id)
+            # Extract basic info for fallback
+            title_match = re.search('<title>(.*?) - YouTube</title>', self._video_data)
+            self.title = title_match.group(1) if title_match else None
+            self.id = self._matched_id
+        else:
+            raise ValueError('Invalid YouTube video ID or URL')
+
+    def __repr__(self):
+        return f'<Video {self._url}>'
+
+    @property
+    def metadata(self) -> Dict[str, Any]:
+        """
+        Fetches video metadata in a dict format
+
+        Returns
+        -------
+        Dict
+            Video metadata in a dict format containing keys: title, id, views, duration, author_id,
+            upload_date, url, thumbnails, tags, description, likes, genre, etc.
+        """
+        # Multiple patterns to try for video details extraction for robustness
+        details_patterns = [
+            re.compile('videoDetails\":(.*?)\"isLiveContent\":.*?}'),
+            re.compile('videoDetails\":(.*?),\"playerConfig'),
+            re.compile('videoDetails\":(.*?),\"playabilityStatus')
+        ]
+
+        # Other metadata patterns
+        upload_date_pattern = re.compile("<meta itemprop=\"uploadDate\" content=\"(.*?)\">")
+        genre_pattern = re.compile("<meta itemprop=\"genre\" content=\"(.*?)\">")
+        like_count_patterns = [
+            re.compile("iconType\":\"LIKE\"},\"defaultText\":(.*?)}"),
+            re.compile('\"likeCount\":\"(\\d+)\"')
+        ]
+        channel_name_pattern = re.compile('"ownerChannelName":"(.*?)"')
+
+        # Try each pattern for video details
+        raw_details_match = None
+        for pattern in details_patterns:
+            match = pattern.search(self._video_data)
+            if match:
+                raw_details_match = match
+                break
+
+        if not raw_details_match:
+            # Fallback metadata for search results or incomplete video data
+            return {
+                'title': getattr(self, 'title', None),
+                'id': getattr(self, 'id', None),
+                'views': getattr(self, 'views', None),
+                'streamed': False,
+                'duration': None,
+                'author_id': None,
+                'author_name': None,
+                'upload_date': None,
+                'url': f"https://www.youtube.com/watch?v={getattr(self, 'id', '')}" if hasattr(self, 'id') else None,
+                'thumbnails': None,
+                'tags': None,
+                'description': None,
+                'likes': None,
+                'genre': None,
+                'is_age_restricted': 'age-restricted' in self._video_data.lower(),
+                'is_unlisted': 'unlisted' in self._video_data.lower()
+            }
+
+        raw_details = raw_details_match.group(0)
+
+        # Extract upload date
+        upload_date_match = upload_date_pattern.search(self._video_data)
+        upload_date = upload_date_match.group(1) if upload_date_match else None
+
+        # Extract channel name
+        channel_name_match = channel_name_pattern.search(self._video_data)
+        channel_name = channel_name_match.group(1) if channel_name_match else None
+
+        # Parse video details
+        try:
+            # Clean up the JSON string for parsing
+            clean_json = raw_details.replace('videoDetails\":', '')
+            # Handle potential JSON parsing issues
+            if clean_json.endswith(','):
+                clean_json = clean_json[:-1]
+            metadata = json.loads(clean_json)
+
+            data = {
+                'title': metadata.get('title'),
+                'id': metadata.get('videoId', self._matched_id),
+                'views': metadata.get('viewCount'),
+                'streamed': metadata.get('isLiveContent', False),
+                'duration': metadata.get('lengthSeconds'),
+                'author_id': metadata.get('channelId'),
+                'author_name': channel_name or metadata.get('author'),
+                'upload_date': upload_date,
+                'url': f"https://www.youtube.com/watch?v={metadata.get('videoId', self._matched_id)}",
+                'thumbnails': metadata.get('thumbnail', {}).get('thumbnails'),
+                'tags': metadata.get('keywords'),
+                'description': metadata.get('shortDescription'),
+                'is_age_restricted': metadata.get('isAgeRestricted', False) or 'age-restricted' in self._video_data.lower(),
+                'is_unlisted': 'unlisted' in self._video_data.lower(),
+                'is_family_safe': metadata.get('isFamilySafe', True),
+                'is_private': metadata.get('isPrivate', False),
+                'is_live_content': metadata.get('isLiveContent', False),
+                'is_crawlable': metadata.get('isCrawlable', True),
+                'allow_ratings': metadata.get('allowRatings', True)
+            }
+        except (json.JSONDecodeError, KeyError, TypeError) as e:
+            # Fallback to basic metadata if JSON parsing fails
+            return {
+                'title': getattr(self, 'title', None),
+                'id': self._matched_id,
+                'url': self._url,
+                'error': f"Failed to parse video details: {str(e)}"
+            }
+
+        # Try to extract likes count
+        likes = None
+        for pattern in like_count_patterns:
+            try:
+                likes_match = pattern.search(self._video_data)
+                if likes_match:
+                    likes_text = likes_match.group(1)
+                    # Handle different formats of like count
+                    if '{' in likes_text:
+                        likes = json.loads(likes_text + '}}}')['accessibility']['accessibilityData']['label'].split(' ')[0].replace(',', '')
+                    else:
+                        likes = likes_text
+                    break
+            except (AttributeError, KeyError, json.decoder.JSONDecodeError):
+                continue
+
+        data['likes'] = likes
+
+        # Try to extract genre
+        try:
+            genre_match = genre_pattern.search(self._video_data)
+            data['genre'] = genre_match.group(1) if genre_match else None
+        except AttributeError:
+            data['genre'] = None
+
+        return data
+
+
+
+    @property
+    def embed_html(self) -> str:
+        """
+        Get the embed HTML code for this video
+
+        Returns:
+            HTML iframe code for embedding the video
+        """
+        return f'<iframe width="560" height="315" src="https://www.youtube.com/embed/{self._matched_id}" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>'
+
+    @property
+    def embed_url(self) -> str:
+        """
+        Get the embed URL for this video
+
+        Returns:
+            URL for embedding the video
+        """
+        return f'https://www.youtube.com/embed/{self._matched_id}'
+
+    @property
+    def thumbnail_url(self) -> str:
+        """
+        Get the thumbnail URL for this video
+
+        Returns:
+            URL of the video thumbnail (high quality)
+        """
+        return f'https://i.ytimg.com/vi/{self._matched_id}/hqdefault.jpg'
+
+    @property
+    def thumbnail_urls(self) -> Dict[str, str]:
+        """
+        Get all thumbnail URLs for this video in different qualities
+
+        Returns:
+            Dictionary of thumbnail URLs with quality labels
+        """
+        return {
+            'default': f'https://i.ytimg.com/vi/{self._matched_id}/default.jpg',
+            'medium': f'https://i.ytimg.com/vi/{self._matched_id}/mqdefault.jpg',
+            'high': f'https://i.ytimg.com/vi/{self._matched_id}/hqdefault.jpg',
+            'standard': f'https://i.ytimg.com/vi/{self._matched_id}/sddefault.jpg',
+            'maxres': f'https://i.ytimg.com/vi/{self._matched_id}/maxresdefault.jpg'
+        }
+
+if __name__ == '__main__':
+    video = Video('https://www.youtube.com/watch?v=9bZkp7q19f0')
+    print(video.metadata)
+
+    # Example of getting comments
+    print("\nFirst 3 comments:")
+    for i, comment in enumerate(video.stream_comments(3), 1):
+        print(f"{i}. {comment['author']}: {comment['text'][:50]}...")

webscout/Extra/__init__.py

@@ -0,0 +1,7 @@
+from .gguf import *
+from .weather import *
+from .weather_ascii import *
+from .autocoder import *
+from .YTToolkit import *
+from .GitToolkit import *
+from .tempmail import *

webscout/Extra/autocoder/__init__.py

@@ -0,0 +1,9 @@
+"""
+AutoCoder Module - Part of Webscout
+Provides automated code generation and manipulation capabilities.
+"""
+
+from .autocoder import *
+from .autocoder_utiles import *
+
+# __all__ = []  # Add your public module names here