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     float_or_none,
  11 )
  12
  13
  14 class OnionStudiosIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?onionstudios\.com/(?:videos/[^/]+-|embed\?.*\bid=)(?P<id>\d+)(?!-)'
  16
  17     _TESTS = [{
  18         'url': 'http://www.onionstudios.com/videos/hannibal-charges-forward-stops-for-a-cocktail-2937',
  19         'md5': 'e49f947c105b8a78a675a0ee1bddedfe',
  20         'info_dict': {
  21             'id': '2937',
  22             'ext': 'mp4',
  23             'title': 'Hannibal charges forward, stops for a cocktail',
  24             'thumbnail': 're:^https?://.*\.jpg$',
  25             'uploader': 'The A.V. Club',
  26             'uploader_id': 'the-av-club',
  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         video_data = self._download_json(
  44             'http://www.onionstudios.com/video/%s.json' % video_id, video_id)
  45
  46         title = video_data['title']
  47
  48         formats = []
  49         for source in video_data.get('sources', []):
  50             source_url = source.get('url')
  51             if not source_url:
  52                 continue
  53             content_type = source.get('content_type')
  54             ext = determine_ext(source_url)
  55             if content_type == 'application/x-mpegURL' or ext == 'm3u8':
  56                 formats.extend(self._extract_m3u8_formats(
  57                     source_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
  58             else:
  59                 tbr = int_or_none(source.get('bitrate'))
  60                 formats.append({
  61                     'format_id': ext + ('-%d' % tbr if tbr else ''),
  62                     'url': source_url,
  63                     'width': int_or_none(source.get('width')),
  64                     'tbr': tbr,
  65                     'ext': ext,
  66                 })
  67         self._sort_formats(formats)
  68
  69         return {
  70             'id': video_id,
  71             'title': title,
  72             'thumbnail': video_data.get('poster_url'),
  73             'uploader': video_data.get('channel_name'),
  74             'uploader_id': video_data.get('channel_slug'),
  75             'duration': float_or_none(video_data.get('duration', 1000)),
  76             'tags': video_data.get('tags'),
  77             'formats': formats,
  78         }