youtube_dl/extractor/onionstudios.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import determine_ext
   8
   9
  10 class OnionStudiosIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?onionstudios\.com/(?:videos/[^/]+-|embed\?.*\bid=)(?P<id>\d+)(?!-)'
  12
  13     _TESTS = [{
  14         'url': 'http://www.onionstudios.com/videos/hannibal-charges-forward-stops-for-a-cocktail-2937',
  15         'md5': 'd4851405d31adfadf71cd7a487b765bb',
  16         'info_dict': {
  17             'id': '2937',
  18             'ext': 'mp4',
  19             'title': 'Hannibal charges forward, stops for a cocktail',
  20             'description': 'md5:545299bda6abf87e5ec666548c6a9448',
  21             'thumbnail': 're:^https?://.*\.jpg$',
  22             'uploader': 'The A.V. Club',
  23             'uploader_id': 'TheAVClub',
  24         },
  25     }, {
  26         'url': 'http://www.onionstudios.com/embed?id=2855&autoplay=true',
  27         'only_matching': True,
  28     }]
  29
  30     @staticmethod
  31     def _extract_url(webpage):
  32         mobj = re.search(
  33             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?onionstudios\.com/embed.+?)\1', webpage)
  34         if mobj:
  35             return mobj.group('url')
  36
  37     def _real_extract(self, url):
  38         video_id = self._match_id(url)
  39
  40         webpage = self._download_webpage(
  41             'http://www.onionstudios.com/embed?id=%s' % video_id, video_id)
  42
  43         formats = []
  44         for src in re.findall(r'<source[^>]+src="([^"]+)"', webpage):
  45             if determine_ext(src) != 'm3u8':  # m3u8 always results in 403
  46                 formats.append({
  47                     'url': src,
  48                 })
  49         self._sort_formats(formats)
  50
  51         title = self._search_regex(
  52             r'share_title\s*=\s*(["\'])(?P<title>[^\1]+?)\1',
  53             webpage, 'title', group='title')
  54         description = self._search_regex(
  55             r'share_description\s*=\s*(["\'])(?P<description>[^\1]+?)\1',
  56             webpage, 'description', default=None, group='description')
  57         thumbnail = self._search_regex(
  58             r'poster\s*=\s*(["\'])(?P<thumbnail>[^\1]+?)\1',
  59             webpage, 'thumbnail', default=False, group='thumbnail')
  60
  61         uploader_id = self._search_regex(
  62             r'twitter_handle\s*=\s*(["\'])(?P<uploader_id>[^\1]+?)\1',
  63             webpage, 'uploader id', fatal=False, group='uploader_id')
  64         uploader = self._search_regex(
  65             r'window\.channelName\s*=\s*(["\'])Embedded:(?P<uploader>[^\1]+?)\1',
  66             webpage, 'uploader', default=False, group='uploader')
  67
  68         return {
  69             'id': video_id,
  70             'title': title,
  71             'description': description,
  72             'thumbnail': thumbnail,
  73             'uploader': uploader,
  74             'uploader_id': uploader_id,
  75             'formats': formats,
  76         }