yt_dlp/extractor/tube8.py

   1 import re
   2
   3 from ..utils import (
   4     int_or_none,
   5     str_to_int,
   6 )
   7 from .keezmovies import KeezMoviesIE
   8
   9
  10 class Tube8IE(KeezMoviesIE):  # XXX: Do not subclass from concrete IE
  11     _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
  12     _EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?tube8\.com/embed/(?:[^/]+/)+\d+)']
  13     _TESTS = [{
  14         'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
  15         'md5': '65e20c48e6abff62ed0c3965fff13a39',
  16         'info_dict': {
  17             'id': '229795',
  18             'display_id': 'kasia-music-video',
  19             'ext': 'mp4',
  20             'description': 'hot teen Kasia grinding',
  21             'uploader': 'unknown',
  22             'title': 'Kasia music video',
  23             'age_limit': 18,
  24             'duration': 230,
  25             'categories': ['Teen'],
  26             'tags': ['dancing'],
  27         },
  28     }, {
  29         'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
  30         'only_matching': True,
  31     }]
  32
  33     def _real_extract(self, url):
  34         webpage, info = self._extract_info(url)
  35
  36         if not info['title']:
  37             info['title'] = self._html_search_regex(
  38                 r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
  39
  40         description = self._html_search_regex(
  41             r'(?s)Description:</dt>\s*<dd>(.+?)</dd>', webpage, 'description', fatal=False)
  42         uploader = self._html_search_regex(
  43             r'<span class="username">\s*(.+?)\s*<',
  44             webpage, 'uploader', fatal=False)
  45
  46         like_count = int_or_none(self._search_regex(
  47             r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
  48         dislike_count = int_or_none(self._search_regex(
  49             r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
  50         view_count = str_to_int(self._search_regex(
  51             r'Views:\s*</dt>\s*<dd>([\d,\.]+)',
  52             webpage, 'view count', fatal=False))
  53         comment_count = str_to_int(self._search_regex(
  54             r'<span id="allCommentsCount">(\d+)</span>',
  55             webpage, 'comment count', fatal=False))
  56
  57         category = self._search_regex(
  58             r'Category:\s*</dt>\s*<dd>\s*<a[^>]+href=[^>]+>([^<]+)',
  59             webpage, 'category', fatal=False)
  60         categories = [category] if category else None
  61
  62         tags_str = self._search_regex(
  63             r'(?s)Tags:\s*</dt>\s*<dd>(.+?)</(?!a)',
  64             webpage, 'tags', fatal=False)
  65         tags = [t for t in re.findall(
  66             r'<a[^>]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None
  67
  68         info.update({
  69             'description': description,
  70             'uploader': uploader,
  71             'view_count': view_count,
  72             'like_count': like_count,
  73             'dislike_count': dislike_count,
  74             'comment_count': comment_count,
  75             'categories': categories,
  76             'tags': tags,
  77         })
  78
  79         return info