webscout 6.4__py3-none-any.whl → 6.5__py3-none-any.whl

webscout/Extra/YTToolkit/ytapi/stream.py

@@ -0,0 +1,60 @@
+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
+        }

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 +1,102 @@
+import re
+import json
+from .https import video_data
+from typing import Dict, Any
+
+
+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
+        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):
+        """
+        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
+        """
+        details_pattern = re.compile('videoDetails\":(.*?)\"isLiveContent\":.*?}')
+        upload_date_pattern = re.compile("<meta itemprop=\"uploadDate\" content=\"(.*?)\">")
+        genre_pattern = re.compile("<meta itemprop=\"genre\" content=\"(.*?)\">")
+        like_count_pattern = re.compile("iconType\":\"LIKE\"},\"defaultText\":(.*?)}}")
+        
+        # Add robust error handling
+        raw_details_match = details_pattern.search(self._video_data)
+        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,
+                '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
+            }
+        
+        raw_details = raw_details_match.group(0)
+        
+        # Add None checking for 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
+        
+        metadata = json.loads(raw_details.replace('videoDetails\":', ''))
+        data = {
+            'title': metadata['title'],
+            'id': metadata['videoId'],
+            'views': metadata.get('viewCount'),
+            'streamed': metadata['isLiveContent'],
+            'duration': metadata['lengthSeconds'],
+            'author_id': metadata['channelId'],
+            'upload_date': upload_date,
+            'url': f"https://www.youtube.com/watch?v={metadata['videoId']}",
+            'thumbnails': metadata.get('thumbnail', {}).get('thumbnails'),
+            'tags': metadata.get('keywords'),
+            'description': metadata.get('shortDescription'),
+        }
+        try:
+            likes_count = like_count_pattern.search(self._video_data).group(1)
+            data['likes'] = json.loads(likes_count + '}}}')[
+                'accessibility'
+            ]['accessibilityData']['label'].split(' ')[0].replace(',', '')
+        except (AttributeError, KeyError, json.decoder.JSONDecodeError):
+            data['likes'] = None
+        try:
+            data['genre'] = genre_pattern.search(self._video_data).group(1)
+        except AttributeError:
+            data['genre'] = None
+        return data

webscout/Extra/__init__.py

@@ -2,4 +2,5 @@ from .gguf import *
 from .autollama import *
 from .weather import *
 from .weather_ascii import *
-from .autocoder import *
+from .autocoder import *
+from .YTToolkit import *