Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/webofstories.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 int_or_none
   8
   9
  10 class WebOfStoriesIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?webofstories\.com/play/(?:[^/]+/)?(?P<id>[0-9]+)'
  12     _VIDEO_DOMAIN = 'http://eu-mobile.webofstories.com/'
  13     _GREAT_LIFE_STREAMER = 'rtmp://eu-cdn1.webofstories.com/cfx/st/'
  14     _USER_STREAMER = 'rtmp://eu-users.webofstories.com/cfx/st/'
  15     _TESTS = [
  16         {
  17             'url': 'http://www.webofstories.com/play/hans.bethe/71',
  18             'md5': '373e4dd915f60cfe3116322642ddf364',
  19             'info_dict': {
  20                 'id': '4536',
  21                 'ext': 'mp4',
  22                 'title': 'The temperature of the sun',
  23                 'thumbnail': 're:^https?://.*\.jpg$',
  24                 'description': 'Hans Bethe talks about calculating the temperature of the sun',
  25                 'duration': 238,
  26             }
  27         },
  28         {
  29             'url': 'http://www.webofstories.com/play/55908',
  30             'md5': '2985a698e1fe3211022422c4b5ed962c',
  31             'info_dict': {
  32                 'id': '55908',
  33                 'ext': 'mp4',
  34                 'title': 'The story of Gemmata obscuriglobus',
  35                 'thumbnail': 're:^https?://.*\.jpg$',
  36                 'description': 'Planctomycete talks about The story of Gemmata obscuriglobus',
  37                 'duration': 169,
  38             }
  39         },
  40     ]
  41
  42     def _real_extract(self, url):
  43         video_id = self._match_id(url)
  44
  45         webpage = self._download_webpage(url, video_id)
  46         title = self._og_search_title(webpage)
  47         description = self._html_search_meta('description', webpage)
  48         thumbnail = self._og_search_thumbnail(webpage)
  49
  50         embed_params = [s.strip(" \r\n\t'") for s in self._search_regex(
  51             r'(?s)\$\("#embedCode"\).html\(getEmbedCode\((.*?)\)',
  52             webpage, 'embed params').split(',')]
  53
  54         (
  55             _, speaker_id, story_id, story_duration,
  56             speaker_type, great_life, _thumbnail, _has_subtitles,
  57             story_filename, _story_order) = embed_params
  58
  59         is_great_life_series = great_life == 'true'
  60         duration = int_or_none(story_duration)
  61
  62         # URL building, see: http://www.webofstories.com/scripts/player.js
  63         ms_prefix = ''
  64         if speaker_type.lower() == 'ms':
  65             ms_prefix = 'mini_sites/'
  66
  67         if is_great_life_series:
  68             mp4_url = '{0:}lives/{1:}/{2:}.mp4'.format(
  69                 self._VIDEO_DOMAIN, speaker_id, story_filename)
  70             rtmp_ext = 'flv'
  71             streamer = self._GREAT_LIFE_STREAMER
  72             play_path = 'stories/{0:}/{1:}'.format(
  73                 speaker_id, story_filename)
  74         else:
  75             mp4_url = '{0:}{1:}{2:}/{3:}.mp4'.format(
  76                 self._VIDEO_DOMAIN, ms_prefix, speaker_id, story_filename)
  77             rtmp_ext = 'mp4'
  78             streamer = self._USER_STREAMER
  79             play_path = 'mp4:{0:}{1:}/{2}.mp4'.format(
  80                 ms_prefix, speaker_id, story_filename)
  81
  82         formats = [{
  83             'format_id': 'mp4_sd',
  84             'url': mp4_url,
  85         }, {
  86             'format_id': 'rtmp_sd',
  87             'page_url': url,
  88             'url': streamer,
  89             'ext': rtmp_ext,
  90             'play_path': play_path,
  91         }]
  92
  93         self._sort_formats(formats)
  94
  95         return {
  96             'id': story_id,
  97             'title': title,
  98             'formats': formats,
  99             'thumbnail': thumbnail,
 100             'description': description,
 101             'duration': duration,
 102         }
 103
 104
 105 class WebOfStoriesPlaylistIE(InfoExtractor):
 106     _VALID_URL = r'https?://(?:www\.)?webofstories\.com/playAll/(?P<id>[^/]+)'
 107     _TEST = {
 108         'url': 'http://www.webofstories.com/playAll/donald.knuth',
 109         'info_dict': {
 110             'id': 'donald.knuth',
 111             'title': 'Donald Knuth (Scientist)',
 112         },
 113         'playlist_mincount': 97,
 114     }
 115
 116     def _real_extract(self, url):
 117         playlist_id = self._match_id(url)
 118
 119         webpage = self._download_webpage(url, playlist_id)
 120
 121         entries = [
 122             self.url_result('http://www.webofstories.com/play/%s' % video_number, 'WebOfStories')
 123             for video_number in set(re.findall('href="/playAll/%s\?sId=(\d+)"' % playlist_id, webpage))
 124         ]
 125
 126         title = self._search_regex(
 127             r'<div id="speakerName">\s*<span>([^<]+)</span>',
 128             webpage, 'speaker', default=None)
 129         if title:
 130             field = self._search_regex(
 131                 r'<span id="primaryField">([^<]+)</span>',
 132                 webpage, 'field', default=None)
 133             if field:
 134                 title += ' (%s)' % field
 135
 136         if not title:
 137             title = self._search_regex(
 138                 r'<title>Play\s+all\s+stories\s*-\s*([^<]+)\s*-\s*Web\s+of\s+Stories</title>',
 139                 webpage, 'title')
 140
 141         return self.playlist_result(entries, playlist_id, title)