yt_dlp/extractor/redtube.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     determine_ext,
   8     ExtractorError,
   9     int_or_none,
  10     merge_dicts,
  11     str_to_int,
  12     unified_strdate,
  13     url_or_none,
  14 )
  15
  16
  17 class RedTubeIE(InfoExtractor):
  18     _VALID_URL = r'https?://(?:(?:\w+\.)?redtube\.com/|embed\.redtube\.com/\?.*?\bid=)(?P<id>[0-9]+)'
  19     _TESTS = [{
  20         'url': 'https://www.redtube.com/38864951',
  21         'md5': '4fba70cbca3aefd25767ab4b523c9878',
  22         'info_dict': {
  23             'id': '38864951',
  24             'ext': 'mp4',
  25             'title': 'Public Sex on the Balcony in Freezing Paris! Amateur Couple LeoLulu',
  26             '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',
  27             'upload_date': '20210111',
  28             'timestamp': 1610343109,
  29             'duration': 646,
  30             'view_count': int,
  31             'age_limit': 18,
  32             'thumbnail': r're:https://\wi-ph\.rdtcdn\.com/videos/.+/.+\.jpg',
  33         },
  34     }, {
  35         'url': 'http://embed.redtube.com/?bgcolor=000000&id=1443286',
  36         'only_matching': True,
  37     }, {
  38         'url': 'http://it.redtube.com/66418',
  39         'only_matching': True,
  40     }]
  41
  42     @staticmethod
  43     def _extract_urls(webpage):
  44         return re.findall(
  45             r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//embed\.redtube\.com/\?.*?\bid=\d+)',
  46             webpage)
  47
  48     def _real_extract(self, url):
  49         video_id = self._match_id(url)
  50         webpage = self._download_webpage(
  51             'http://www.redtube.com/%s' % video_id, video_id)
  52
  53         ERRORS = (
  54             (('video-deleted-info', '>This video has been removed'), 'has been removed'),
  55             (('private_video_text', '>This video is private', '>Send a friend request to its owner to be able to view it'), 'is private'),
  56         )
  57
  58         for patterns, message in ERRORS:
  59             if any(p in webpage for p in patterns):
  60                 raise ExtractorError(
  61                     'Video %s %s' % (video_id, message), expected=True)
  62
  63         info = self._search_json_ld(webpage, video_id, default={})
  64
  65         if not info.get('title'):
  66             info['title'] = self._html_search_regex(
  67                 (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle|video_title)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
  68                  r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',),
  69                 webpage, 'title', group='title',
  70                 default=None) or self._og_search_title(webpage)
  71
  72         formats = []
  73         sources = self._parse_json(
  74             self._search_regex(
  75                 r'sources\s*:\s*({.+?})', webpage, 'source', default='{}'),
  76             video_id, fatal=False)
  77         if sources and isinstance(sources, dict):
  78             for format_id, format_url in sources.items():
  79                 if format_url:
  80                     formats.append({
  81                         'url': format_url,
  82                         'format_id': format_id,
  83                         'height': int_or_none(format_id),
  84                     })
  85         medias = self._parse_json(
  86             self._search_regex(
  87                 r'mediaDefinition["\']?\s*:\s*(\[.+?}\s*\])', webpage,
  88                 'media definitions', default='{}'),
  89             video_id, fatal=False)
  90         for media in medias if isinstance(medias, list) else []:
  91             format_url = url_or_none(media.get('videoUrl'))
  92             if not format_url:
  93                 continue
  94             format_id = media.get('format')
  95             quality = media.get('quality')
  96             if format_id == 'hls' or (format_id == 'mp4' and not quality):
  97                 more_media = self._download_json(format_url, video_id, fatal=False)
  98             else:
  99                 more_media = [media]
 100             for media in more_media if isinstance(more_media, list) else []:
 101                 format_url = url_or_none(media.get('videoUrl'))
 102                 if not format_url:
 103                     continue
 104                 format_id = media.get('format')
 105                 if format_id == 'hls' or determine_ext(format_url) == 'm3u8':
 106                     formats.extend(self._extract_m3u8_formats(
 107                         format_url, video_id, 'mp4',
 108                         entry_protocol='m3u8_native', m3u8_id=format_id or 'hls',
 109                         fatal=False))
 110                     continue
 111                 format_id = media.get('quality')
 112                 formats.append({
 113                     'url': format_url,
 114                     'ext': 'mp4',
 115                     'format_id': format_id,
 116                     'height': int_or_none(format_id),
 117                 })
 118         if not formats:
 119             video_url = self._html_search_regex(
 120                 r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
 121             formats.append({'url': video_url, 'ext': 'mp4'})
 122         self._sort_formats(formats)
 123
 124         thumbnail = self._og_search_thumbnail(webpage)
 125         upload_date = unified_strdate(self._search_regex(
 126             r'<span[^>]+>(?:ADDED|Published on) ([^<]+)<',
 127             webpage, 'upload date', default=None))
 128         duration = int_or_none(self._og_search_property(
 129             'video:duration', webpage, default=None) or self._search_regex(
 130                 r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None))
 131         view_count = str_to_int(self._search_regex(
 132             (r'<div[^>]*>Views</div>\s*<div[^>]*>\s*([\d,.]+)',
 133              r'<span[^>]*>VIEWS</span>\s*</td>\s*<td>\s*([\d,.]+)',
 134              r'<span[^>]+\bclass=["\']video_view_count[^>]*>\s*([\d,.]+)'),
 135             webpage, 'view count', default=None))
 136
 137         # No self-labeling, but they describe themselves as
 138         # "Home of Videos Porno"
 139         age_limit = 18
 140
 141         return merge_dicts(info, {
 142             'id': video_id,
 143             'ext': 'mp4',
 144             'thumbnail': thumbnail,
 145             'upload_date': upload_date,
 146             'duration': duration,
 147             'view_count': view_count,
 148             'age_limit': age_limit,
 149             'formats': formats,
 150         })