yt_dlp/extractor/breakcom.py

   1 from __future__ import unicode_literals
   2
   3
   4 from .common import InfoExtractor
   5 from .youtube import YoutubeIE
   6 from ..utils import (
   7     int_or_none,
   8     url_or_none,
   9 )
  10
  11
  12 class BreakIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?break\.com/video/(?P<display_id>[^/]+?)(?:-(?P<id>\d+))?(?:[/?#&]|$)'
  14     _TESTS = [{
  15         'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
  16         'info_dict': {
  17             'id': '2468056',
  18             'ext': 'mp4',
  19             'title': 'When Girls Act Like D-Bags',
  20             'age_limit': 13,
  21         },
  22     }, {
  23         # youtube embed
  24         'url': 'http://www.break.com/video/someone-forgot-boat-brakes-work',
  25         'info_dict': {
  26             'id': 'RrrDLdeL2HQ',
  27             'ext': 'mp4',
  28             'title': 'Whale Watching Boat Crashing Into San Diego Dock',
  29             'description': 'md5:afc1b2772f0a8468be51dd80eb021069',
  30             'upload_date': '20160331',
  31             'uploader': 'Steve Holden',
  32             'uploader_id': 'sdholden07',
  33         },
  34         'params': {
  35             'skip_download': True,
  36         }
  37     }, {
  38         'url': 'http://www.break.com/video/ugc/baby-flex-2773063',
  39         'only_matching': True,
  40     }]
  41
  42     def _real_extract(self, url):
  43         display_id, video_id = self._match_valid_url(url).groups()
  44
  45         webpage = self._download_webpage(url, display_id)
  46
  47         youtube_url = YoutubeIE._extract_url(webpage)
  48         if youtube_url:
  49             return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
  50
  51         content = self._parse_json(
  52             self._search_regex(
  53                 r'(?s)content["\']\s*:\s*(\[.+?\])\s*[,\n]', webpage,
  54                 'content'),
  55             display_id)
  56
  57         formats = []
  58         for video in content:
  59             video_url = url_or_none(video.get('url'))
  60             if not video_url:
  61                 continue
  62             bitrate = int_or_none(self._search_regex(
  63                 r'(\d+)_kbps', video_url, 'tbr', default=None))
  64             formats.append({
  65                 'url': video_url,
  66                 'format_id': 'http-%d' % bitrate if bitrate else 'http',
  67                 'tbr': bitrate,
  68             })
  69         self._sort_formats(formats)
  70
  71         title = self._search_regex(
  72             (r'title["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
  73              r'<h1[^>]*>(?P<value>[^<]+)'), webpage, 'title', group='value')
  74
  75         def get(key, name):
  76             return int_or_none(self._search_regex(
  77                 r'%s["\']\s*:\s*["\'](\d+)' % key, webpage, name,
  78                 default=None))
  79
  80         age_limit = get('ratings', 'age limit')
  81         video_id = video_id or get('pid', 'video id') or display_id
  82
  83         return {
  84             'id': video_id,
  85             'display_id': display_id,
  86             'title': title,
  87             'thumbnail': self._og_search_thumbnail(webpage),
  88             'age_limit': age_limit,
  89             'formats': formats,
  90         }