yt_dlp/extractor/twentyfourvideo.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     parse_iso8601,
   4     int_or_none,
   5     xpath_attr,
   6     xpath_element,
   7 )
   8
   9
  10 class TwentyFourVideoIE(InfoExtractor):
  11     IE_NAME = '24video'
  12     _VALID_URL = r'''(?x)
  13                     https?://
  14                         (?P<host>
  15                             (?:(?:www|porno?)\.)?24video\.
  16                             (?:net|me|xxx|sexy?|tube|adult|site|vip)
  17                         )/
  18                         (?:
  19                             video/(?:(?:view|xml)/)?|
  20                             player/new24_play\.swf\?id=
  21                         )
  22                         (?P<id>\d+)
  23                     '''
  24
  25     _TESTS = [{
  26         'url': 'http://www.24video.net/video/view/1044982',
  27         'md5': 'e09fc0901d9eaeedac872f154931deeb',
  28         'info_dict': {
  29             'id': '1044982',
  30             'ext': 'mp4',
  31             'title': 'Эротика каменного века',
  32             'description': 'Как смотрели порно в каменном веке.',
  33             'thumbnail': r're:^https?://.*\.jpg$',
  34             'uploader': 'SUPERTELO',
  35             'duration': 31,
  36             'timestamp': 1275937857,
  37             'upload_date': '20100607',
  38             'age_limit': 18,
  39             'like_count': int,
  40             'dislike_count': int,
  41         },
  42     }, {
  43         'url': 'http://www.24video.net/player/new24_play.swf?id=1044982',
  44         'only_matching': True,
  45     }, {
  46         'url': 'http://www.24video.me/video/view/1044982',
  47         'only_matching': True,
  48     }, {
  49         'url': 'http://www.24video.tube/video/view/2363750',
  50         'only_matching': True,
  51     }, {
  52         'url': 'https://www.24video.site/video/view/2640421',
  53         'only_matching': True,
  54     }, {
  55         'url': 'https://porno.24video.net/video/2640421-vsya-takaya-gibkaya-i-v-masle',
  56         'only_matching': True,
  57     }, {
  58         'url': 'https://www.24video.vip/video/view/1044982',
  59         'only_matching': True,
  60     }, {
  61         'url': 'https://porn.24video.net/video/2640421-vsya-takay',
  62         'only_matching': True,
  63     }]
  64
  65     def _real_extract(self, url):
  66         mobj = self._match_valid_url(url)
  67         video_id = mobj.group('id')
  68         host = mobj.group('host')
  69
  70         webpage = self._download_webpage(
  71             'http://%s/video/view/%s' % (host, video_id), video_id)
  72
  73         title = self._og_search_title(webpage)
  74         description = self._html_search_regex(
  75             r'<(p|span)[^>]+itemprop="description"[^>]*>(?P<description>[^<]+)</\1>',
  76             webpage, 'description', fatal=False, group='description')
  77         thumbnail = self._og_search_thumbnail(webpage)
  78         duration = int_or_none(self._og_search_property(
  79             'duration', webpage, 'duration', fatal=False))
  80         timestamp = parse_iso8601(self._search_regex(
  81             r'<time[^>]+\bdatetime="([^"]+)"[^>]+itemprop="uploadDate"',
  82             webpage, 'upload date', fatal=False))
  83
  84         uploader = self._html_search_regex(
  85             r'class="video-uploaded"[^>]*>\s*<a href="/jsecUser/movies/[^"]+"[^>]*>([^<]+)</a>',
  86             webpage, 'uploader', fatal=False)
  87
  88         view_count = int_or_none(self._html_search_regex(
  89             r'<span class="video-views">(\d+) просмотр',
  90             webpage, 'view count', fatal=False))
  91         comment_count = int_or_none(self._html_search_regex(
  92             r'<a[^>]+href="#tab-comments"[^>]*>(\d+) комментари',
  93             webpage, 'comment count', default=None))
  94
  95         # Sets some cookies
  96         self._download_xml(
  97             r'http://%s/video/xml/%s?mode=init' % (host, video_id),
  98             video_id, 'Downloading init XML')
  99
 100         video_xml = self._download_xml(
 101             'http://%s/video/xml/%s?mode=play' % (host, video_id),
 102             video_id, 'Downloading video XML')
 103
 104         video = xpath_element(video_xml, './/video', 'video', fatal=True)
 105
 106         formats = [{
 107             'url': xpath_attr(video, '', 'url', 'video URL', fatal=True),
 108         }]
 109
 110         like_count = int_or_none(video.get('ratingPlus'))
 111         dislike_count = int_or_none(video.get('ratingMinus'))
 112         age_limit = 18 if video.get('adult') == 'true' else 0
 113
 114         return {
 115             'id': video_id,
 116             'title': title,
 117             'description': description,
 118             'thumbnail': thumbnail,
 119             'uploader': uploader,
 120             'duration': duration,
 121             'timestamp': timestamp,
 122             'view_count': view_count,
 123             'comment_count': comment_count,
 124             'like_count': like_count,
 125             'dislike_count': dislike_count,
 126             'age_limit': age_limit,
 127             'formats': formats,
 128         }