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):
  11     _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
  12     _TESTS = [{
  13         'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
  14         'md5': '65e20c48e6abff62ed0c3965fff13a39',
  15         'info_dict': {
  16             'id': '229795',
  17             'display_id': 'kasia-music-video',
  18             'ext': 'mp4',
  19             'description': 'hot teen Kasia grinding',
  20             'uploader': 'unknown',
  21             'title': 'Kasia music video',
  22             'age_limit': 18,
  23             'duration': 230,
  24             'categories': ['Teen'],
  25             'tags': ['dancing'],
  26         },
  27     }, {
  28         'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
  29         'only_matching': True,
  30     }]
  31
  32     @staticmethod
  33     def _extract_urls(webpage):
  34         return re.findall(
  35             r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?tube8\.com/embed/(?:[^/]+/)+\d+)',
  36             webpage)
  37
  38     def _real_extract(self, url):
  39         webpage, info = self._extract_info(url)
  40
  41         if not info['title']:
  42             info['title'] = self._html_search_regex(
  43                 r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
  44
  45         description = self._html_search_regex(
  46             r'(?s)Description:</dt>\s*<dd>(.+?)</dd>', webpage, 'description', fatal=False)
  47         uploader = self._html_search_regex(
  48             r'<span class="username">\s*(.+?)\s*<',
  49             webpage, 'uploader', fatal=False)
  50
  51         like_count = int_or_none(self._search_regex(
  52             r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
  53         dislike_count = int_or_none(self._search_regex(
  54             r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
  55         view_count = str_to_int(self._search_regex(
  56             r'Views:\s*</dt>\s*<dd>([\d,\.]+)',
  57             webpage, 'view count', fatal=False))
  58         comment_count = str_to_int(self._search_regex(
  59             r'<span id="allCommentsCount">(\d+)</span>',
  60             webpage, 'comment count', fatal=False))
  61
  62         category = self._search_regex(
  63             r'Category:\s*</dt>\s*<dd>\s*<a[^>]+href=[^>]+>([^<]+)',
  64             webpage, 'category', fatal=False)
  65         categories = [category] if category else None
  66
  67         tags_str = self._search_regex(
  68             r'(?s)Tags:\s*</dt>\s*<dd>(.+?)</(?!a)',
  69             webpage, 'tags', fatal=False)
  70         tags = [t for t in re.findall(
  71             r'<a[^>]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None
  72
  73         info.update({
  74             'description': description,
  75             'uploader': uploader,
  76             'view_count': view_count,
  77             'like_count': like_count,
  78             'dislike_count': dislike_count,
  79             'comment_count': comment_count,
  80             'categories': categories,
  81             'tags': tags,
  82         })
  83
  84         return info