yt_dlp/extractor/breakcom.py

   1 from .common import InfoExtractor
   2 from .youtube import YoutubeIE
   3 from ..utils import (
   4     int_or_none,
   5     url_or_none,
   6 )
   7
   8
   9 class BreakIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?break\.com/video/(?P<display_id>[^/]+?)(?:-(?P<id>\d+))?(?:[/?#&]|$)'
  11     _TESTS = [{
  12         'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
  13         'info_dict': {
  14             'id': '2468056',
  15             'ext': 'mp4',
  16             'title': 'When Girls Act Like D-Bags',
  17             'age_limit': 13,
  18         },
  19     }, {
  20         # youtube embed
  21         'url': 'http://www.break.com/video/someone-forgot-boat-brakes-work',
  22         'info_dict': {
  23             'id': 'RrrDLdeL2HQ',
  24             'ext': 'mp4',
  25             'title': 'Whale Watching Boat Crashing Into San Diego Dock',
  26             'description': 'md5:afc1b2772f0a8468be51dd80eb021069',
  27             'upload_date': '20160331',
  28             'uploader': 'Steve Holden',
  29             'uploader_id': 'sdholden07',
  30         },
  31         'params': {
  32             'skip_download': True,
  33         }
  34     }, {
  35         'url': 'http://www.break.com/video/ugc/baby-flex-2773063',
  36         'only_matching': True,
  37     }]
  38
  39     def _real_extract(self, url):
  40         display_id, video_id = self._match_valid_url(url).groups()
  41
  42         webpage = self._download_webpage(url, display_id)
  43
  44         youtube_url = YoutubeIE._extract_url(webpage)
  45         if youtube_url:
  46             return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
  47
  48         content = self._parse_json(
  49             self._search_regex(
  50                 r'(?s)content["\']\s*:\s*(\[.+?\])\s*[,\n]', webpage,
  51                 'content'),
  52             display_id)
  53
  54         formats = []
  55         for video in content:
  56             video_url = url_or_none(video.get('url'))
  57             if not video_url:
  58                 continue
  59             bitrate = int_or_none(self._search_regex(
  60                 r'(\d+)_kbps', video_url, 'tbr', default=None))
  61             formats.append({
  62                 'url': video_url,
  63                 'format_id': 'http-%d' % bitrate if bitrate else 'http',
  64                 'tbr': bitrate,
  65             })
  66
  67         title = self._search_regex(
  68             (r'title["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
  69              r'<h1[^>]*>(?P<value>[^<]+)'), webpage, 'title', group='value')
  70
  71         def get(key, name):
  72             return int_or_none(self._search_regex(
  73                 r'%s["\']\s*:\s*["\'](\d+)' % key, webpage, name,
  74                 default=None))
  75
  76         age_limit = get('ratings', 'age limit')
  77         video_id = video_id or get('pid', 'video id') or display_id
  78
  79         return {
  80             'id': video_id,
  81             'display_id': display_id,
  82             'title': title,
  83             'thumbnail': self._og_search_thumbnail(webpage),
  84             'age_limit': age_limit,
  85             'formats': formats,
  86         }