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 ..utils import (
   8     int_or_none,
   9     url_or_none,
  10 )
  11
  12
  13 class BreakIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?break\.com/video/(?P<display_id>[^/]+?)(?:-(?P<id>\d+))?(?:[/?#&]|$)'
  15     _TESTS = [{
  16         'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
  17         'info_dict': {
  18             'id': '2468056',
  19             'ext': 'mp4',
  20             'title': 'When Girls Act Like D-Bags',
  21             'age_limit': 13,
  22         },
  23     }, {
  24         # youtube embed
  25         'url': 'http://www.break.com/video/someone-forgot-boat-brakes-work',
  26         'info_dict': {
  27             'id': 'RrrDLdeL2HQ',
  28             'ext': 'mp4',
  29             'title': 'Whale Watching Boat Crashing Into San Diego Dock',
  30             'description': 'md5:afc1b2772f0a8468be51dd80eb021069',
  31             'upload_date': '20160331',
  32             'uploader': 'Steve Holden',
  33             'uploader_id': 'sdholden07',
  34         },
  35         'params': {
  36             'skip_download': True,
  37         }
  38     }, {
  39         'url': 'http://www.break.com/video/ugc/baby-flex-2773063',
  40         'only_matching': True,
  41     }]
  42
  43     def _real_extract(self, url):
  44         display_id, video_id = re.match(self._VALID_URL, url).groups()
  45
  46         webpage = self._download_webpage(url, display_id)
  47
  48         youtube_url = YoutubeIE._extract_url(webpage)
  49         if youtube_url:
  50             return self.url_result(youtube_url, ie=YoutubeIE.ie_key())
  51
  52         content = self._parse_json(
  53             self._search_regex(
  54                 r'(?s)content["\']\s*:\s*(\[.+?\])\s*[,\n]', webpage,
  55                 'content'),
  56             display_id)
  57
  58         formats = []
  59         for video in content:
  60             video_url = url_or_none(video.get('url'))
  61             if not video_url:
  62                 continue
  63             bitrate = int_or_none(self._search_regex(
  64                 r'(\d+)_kbps', video_url, 'tbr', default=None))
  65             formats.append({
  66                 'url': video_url,
  67                 'format_id': 'http-%d' % bitrate if bitrate else 'http',
  68                 'tbr': bitrate,
  69             })
  70         self._sort_formats(formats)
  71
  72         title = self._search_regex(
  73             (r'title["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
  74              r'<h1[^>]*>(?P<value>[^<]+)'), webpage, 'title', group='value')
  75
  76         def get(key, name):
  77             return int_or_none(self._search_regex(
  78                 r'%s["\']\s*:\s*["\'](\d+)' % key, webpage, name,
  79                 default=None))
  80
  81         age_limit = get('ratings', 'age limit')
  82         video_id = video_id or get('pid', 'video id') or display_id
  83
  84         return {
  85             'id': video_id,
  86             'display_id': display_id,
  87             'title': title,
  88             'thumbnail': self._og_search_thumbnail(webpage),
  89             'age_limit': age_limit,
  90             'formats': formats,
  91         }