_ Git - youtube-dl/blob - 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     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32
  33         webpage = self._download_webpage(
  34             'http://www.onionstudios.com/embed?id=%s' % video_id, video_id)
  35
  36         formats = []
  37         for src in re.findall(r'<source[^>]+src="([^"]+)"', webpage):
  38             if determine_ext(src) != 'm3u8':  # m3u8 always results in 403
  39                 formats.append({
  40                     'url': src,
  41                 })
  42         self._sort_formats(formats)
  43
  44         title = self._search_regex(
  45             r'share_title\s*=\s*"([^"]+)"', webpage, 'title')
  46         description = self._search_regex(
  47             r'share_description\s*=\s*"([^"]+)"', webpage,
  48             'description', default=None)
  49         thumbnail = self._search_regex(
  50             r'poster="([^"]+)"', webpage, 'thumbnail', default=False)
  51
  52         uploader_id = self._search_regex(
  53             r'twitter_handle\s*=\s*"([^"]+)"',
  54             webpage, 'uploader id', fatal=False)
  55         uploader = self._search_regex(
  56             r'window\.channelName\s*=\s*"Embedded:([^"]+)"',
  57             webpage, 'uploader', default=False)
  58
  59         return {
  60             'id': video_id,
  61             'title': title,
  62             'description': description,
  63             'thumbnail': thumbnail,
  64             'uploader': uploader,
  65             'uploader_id': uploader_id,
  66             'formats': formats,
  67         }