yt_dlp/extractor/redtube.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     determine_ext,
   5     int_or_none,
   6     merge_dicts,
   7     str_to_int,
   8     unified_strdate,
   9     url_or_none,
  10     urljoin,
  11 )
  12
  13
  14 class RedTubeIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:(?:\w+\.)?redtube\.com(?:\.br)?/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)'
  16     _EMBED_REGEX = [r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)']
  17     _TESTS = [{
  18         'url': 'https://www.redtube.com/38864951',
  19         'md5': '4fba70cbca3aefd25767ab4b523c9878',
  20         'info_dict': {
  21             'id': '38864951',
  22             'ext': 'mp4',
  23             'title': 'Public Sex on the Balcony in Freezing Paris! Amateur Couple LeoLulu',
  24             'description': 'Watch video Public Sex on the Balcony in Freezing Paris! Amateur Couple LeoLulu on Redtube, home of free Blowjob porn videos and Blonde sex movies online. Video length: (10:46) - Uploaded by leolulu - Verified User - Starring Pornstar: Leolulu',
  25             'upload_date': '20210111',
  26             'timestamp': 1610343109,
  27             'duration': 646,
  28             'view_count': int,
  29             'age_limit': 18,
  30             'thumbnail': r're:https://\wi-ph\.rdtcdn\.com/videos/.+/.+\.jpg',
  31         },
  32     }, {
  33         'url': 'http://embed.redtube.com/?bgcolor=000000&id=1443286',
  34         'only_matching': True,
  35     }, {
  36         'url': 'http://it.redtube.com/66418',
  37         'only_matching': True,
  38     }, {
  39         'url': 'https://www.redtube.com.br/103224331',
  40         'only_matching': True,
  41     }]
  42
  43     def _real_extract(self, url):
  44         video_id = self._match_id(url)
  45         webpage = self._download_webpage(
  46             f'https://www.redtube.com/{video_id}', video_id)
  47
  48         ERRORS = (
  49             (('video-deleted-info', '>This video has been removed'), 'has been removed'),
  50             (('private_video_text', '>This video is private', '>Send a friend request to its owner to be able to view it'), 'is private'),
  51         )
  52
  53         for patterns, message in ERRORS:
  54             if any(p in webpage for p in patterns):
  55                 raise ExtractorError(
  56                     f'Video {video_id} {message}', expected=True)
  57
  58         info = self._search_json_ld(webpage, video_id, default={})
  59
  60         if not info.get('title'):
  61             info['title'] = self._html_search_regex(
  62                 (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle|video_title)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
  63                  r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1'),
  64                 webpage, 'title', group='title',
  65                 default=None) or self._og_search_title(webpage)
  66
  67         formats = []
  68         sources = self._parse_json(
  69             self._search_regex(
  70                 r'sources\s*:\s*({.+?})', webpage, 'source', default='{}'),
  71             video_id, fatal=False)
  72         if sources and isinstance(sources, dict):
  73             for format_id, format_url in sources.items():
  74                 if format_url:
  75                     formats.append({
  76                         'url': format_url,
  77                         'format_id': format_id,
  78                         'height': int_or_none(format_id),
  79                     })
  80         medias = self._parse_json(
  81             self._search_regex(
  82                 r'mediaDefinition["\']?\s*:\s*(\[.+?}\s*\])', webpage,
  83                 'media definitions', default='{}'),
  84             video_id, fatal=False)
  85         for media in medias if isinstance(medias, list) else []:
  86             format_url = urljoin('https://www.redtube.com', media.get('videoUrl'))
  87             if not format_url:
  88                 continue
  89             format_id = media.get('format')
  90             quality = media.get('quality')
  91             if format_id == 'hls' or (format_id == 'mp4' and not quality):
  92                 more_media = self._download_json(format_url, video_id, fatal=False)
  93             else:
  94                 more_media = [media]
  95             for media in more_media if isinstance(more_media, list) else []:
  96                 format_url = url_or_none(media.get('videoUrl'))
  97                 if not format_url:
  98                     continue
  99                 format_id = media.get('format')
 100                 if format_id == 'hls' or determine_ext(format_url) == 'm3u8':
 101                     formats.extend(self._extract_m3u8_formats(
 102                         format_url, video_id, 'mp4',
 103                         entry_protocol='m3u8_native', m3u8_id=format_id or 'hls',
 104                         fatal=False))
 105                     continue
 106                 format_id = media.get('quality')
 107                 formats.append({
 108                     'url': format_url,
 109                     'ext': 'mp4',
 110                     'format_id': format_id,
 111                     'height': int_or_none(format_id),
 112                 })
 113         if not formats:
 114             video_url = self._html_search_regex(
 115                 r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
 116             formats.append({'url': video_url, 'ext': 'mp4'})
 117
 118         thumbnail = self._og_search_thumbnail(webpage)
 119         upload_date = unified_strdate(self._search_regex(
 120             r'<span[^>]+>(?:ADDED|Published on) ([^<]+)<',
 121             webpage, 'upload date', default=None))
 122         duration = int_or_none(self._og_search_property(
 123             'video:duration', webpage, default=None) or self._search_regex(
 124                 r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None))
 125         view_count = str_to_int(self._search_regex(
 126             (r'<div[^>]*>Views</div>\s*<div[^>]*>\s*([\d,.]+)',
 127              r'<span[^>]*>VIEWS</span>\s*</td>\s*<td>\s*([\d,.]+)',
 128              r'<span[^>]+\bclass=["\']video_view_count[^>]*>\s*([\d,.]+)'),
 129             webpage, 'view count', default=None))
 130
 131         # No self-labeling, but they describe themselves as
 132         # "Home of Videos Porno"
 133         age_limit = 18
 134
 135         return merge_dicts(info, {
 136             'id': video_id,
 137             'ext': 'mp4',
 138             'thumbnail': thumbnail,
 139             'upload_date': upload_date,
 140             'duration': duration,
 141             'view_count': view_count,
 142             'age_limit': age_limit,
 143             'formats': formats,
 144         })