Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/breakcom.py

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