Raphaël G. Git Repositories - youtubedl/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 (
   8     determine_ext,
   9     int_or_none,
  10 )
  11
  12
  13 class OnionStudiosIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?onionstudios\.com/(?:videos/[^/]+-|embed\?.*\bid=)(?P<id>\d+)(?!-)'
  15
  16     _TESTS = [{
  17         'url': 'http://www.onionstudios.com/videos/hannibal-charges-forward-stops-for-a-cocktail-2937',
  18         'md5': 'd4851405d31adfadf71cd7a487b765bb',
  19         'info_dict': {
  20             'id': '2937',
  21             'ext': 'mp4',
  22             'title': 'Hannibal charges forward, stops for a cocktail',
  23             'description': 'md5:e786add7f280b7f0fe237b64cc73df76',
  24             'thumbnail': 're:^https?://.*\.jpg$',
  25             'uploader': 'The A.V. Club',
  26             'uploader_id': 'TheAVClub',
  27         },
  28     }, {
  29         'url': 'http://www.onionstudios.com/embed?id=2855&autoplay=true',
  30         'only_matching': True,
  31     }]
  32
  33     @staticmethod
  34     def _extract_url(webpage):
  35         mobj = re.search(
  36             r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?onionstudios\.com/embed.+?)\1', webpage)
  37         if mobj:
  38             return mobj.group('url')
  39
  40     def _real_extract(self, url):
  41         video_id = self._match_id(url)
  42
  43         webpage = self._download_webpage(
  44             'http://www.onionstudios.com/embed?id=%s' % video_id, video_id)
  45
  46         formats = []
  47         for src in re.findall(r'<source[^>]+src="([^"]+)"', webpage):
  48             ext = determine_ext(src)
  49             if ext == 'm3u8':
  50                 formats.extend(self._extract_m3u8_formats(
  51                     src, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
  52             else:
  53                 height = int_or_none(self._search_regex(
  54                     r'/(\d+)\.%s' % ext, src, 'height', default=None))
  55                 formats.append({
  56                     'format_id': ext + ('-%sp' % height if height else ''),
  57                     'url': src,
  58                     'height': height,
  59                     'ext': ext,
  60                     'preference': 1,
  61                 })
  62         self._sort_formats(formats)
  63
  64         title = self._search_regex(
  65             r'share_title\s*=\s*(["\'])(?P<title>[^\1]+?)\1',
  66             webpage, 'title', group='title')
  67         description = self._search_regex(
  68             r'share_description\s*=\s*(["\'])(?P<description>[^\'"]+?)\1',
  69             webpage, 'description', default=None, group='description')
  70         thumbnail = self._search_regex(
  71             r'poster\s*=\s*(["\'])(?P<thumbnail>[^\1]+?)\1',
  72             webpage, 'thumbnail', default=False, group='thumbnail')
  73
  74         uploader_id = self._search_regex(
  75             r'twitter_handle\s*=\s*(["\'])(?P<uploader_id>[^\1]+?)\1',
  76             webpage, 'uploader id', fatal=False, group='uploader_id')
  77         uploader = self._search_regex(
  78             r'window\.channelName\s*=\s*(["\'])Embedded:(?P<uploader>[^\1]+?)\1',
  79             webpage, 'uploader', default=False, group='uploader')
  80
  81         return {
  82             'id': video_id,
  83             'title': title,
  84             'description': description,
  85             'thumbnail': thumbnail,
  86             'uploader': uploader,
  87             'uploader_id': uploader_id,
  88             'formats': formats,
  89         }