[Lecture2Go] Add new extractor
[youtube-dl] / youtube_dl / extractor / webofstories.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 from .common import InfoExtractor
5 from ..utils import int_or_none
6
7
8 class WebOfStoriesIE(InfoExtractor):
9     _VALID_URL = r'https?://(?:www\.)?webofstories\.com/play/(?:[^/]+/)?(?P<id>[0-9]+)'
10     _VIDEO_DOMAIN = 'http://eu-mobile.webofstories.com/'
11     _GREAT_LIFE_STREAMER = 'rtmp://eu-cdn1.webofstories.com/cfx/st/'
12     _USER_STREAMER = 'rtmp://eu-users.webofstories.com/cfx/st/'
13     _TESTS = [
14         {
15             'url': 'http://www.webofstories.com/play/hans.bethe/71',
16             'md5': '373e4dd915f60cfe3116322642ddf364',
17             'info_dict': {
18                 'id': '4536',
19                 'ext': 'mp4',
20                 'title': 'The temperature of the sun',
21                 'thumbnail': 're:^https?://.*\.jpg$',
22                 'description': 'Hans Bethe talks about calculating the temperature of the sun',
23                 'duration': 238,
24             }
25         },
26         {
27             'url': 'http://www.webofstories.com/play/55908',
28             'md5': '2985a698e1fe3211022422c4b5ed962c',
29             'info_dict': {
30                 'id': '55908',
31                 'ext': 'mp4',
32                 'title': 'The story of Gemmata obscuriglobus',
33                 'thumbnail': 're:^https?://.*\.jpg$',
34                 'description': 'Planctomycete talks about The story of Gemmata obscuriglobus',
35                 'duration': 169,
36             }
37         },
38     ]
39
40     def _real_extract(self, url):
41         video_id = self._match_id(url)
42
43         webpage = self._download_webpage(url, video_id)
44         title = self._og_search_title(webpage)
45         description = self._html_search_meta('description', webpage)
46         thumbnail = self._og_search_thumbnail(webpage)
47
48         embed_params = [s.strip(" \r\n\t'") for s in self._search_regex(
49             r'(?s)\$\("#embedCode"\).html\(getEmbedCode\((.*?)\)',
50             webpage, 'embed params').split(',')]
51
52         (
53             _, speaker_id, story_id, story_duration,
54             speaker_type, great_life, _thumbnail, _has_subtitles,
55             story_filename, _story_order) = embed_params
56
57         is_great_life_series = great_life == 'true'
58         duration = int_or_none(story_duration)
59
60         # URL building, see: http://www.webofstories.com/scripts/player.js
61         ms_prefix = ''
62         if speaker_type.lower() == 'ms':
63             ms_prefix = 'mini_sites/'
64
65         if is_great_life_series:
66             mp4_url = '{0:}lives/{1:}/{2:}.mp4'.format(
67                 self._VIDEO_DOMAIN, speaker_id, story_filename)
68             rtmp_ext = 'flv'
69             streamer = self._GREAT_LIFE_STREAMER
70             play_path = 'stories/{0:}/{1:}'.format(
71                 speaker_id, story_filename)
72         else:
73             mp4_url = '{0:}{1:}{2:}/{3:}.mp4'.format(
74                 self._VIDEO_DOMAIN, ms_prefix, speaker_id, story_filename)
75             rtmp_ext = 'mp4'
76             streamer = self._USER_STREAMER
77             play_path = 'mp4:{0:}{1:}/{2}.mp4'.format(
78                 ms_prefix, speaker_id, story_filename)
79
80         formats = [{
81             'format_id': 'mp4_sd',
82             'url': mp4_url,
83         }, {
84             'format_id': 'rtmp_sd',
85             'page_url': url,
86             'url': streamer,
87             'ext': rtmp_ext,
88             'play_path': play_path,
89         }]
90
91         self._sort_formats(formats)
92
93         return {
94             'id': story_id,
95             'title': title,
96             'formats': formats,
97             'thumbnail': thumbnail,
98             'description': description,
99             'duration': duration,
100         }