Raphaël G. Git Repositories - youtubedl/blob - 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         story_filename = self._search_regex(
  49             r'\.storyFileName\("([^"]+)"\)', webpage, 'story filename')
  50         speaker_id = self._search_regex(
  51             r'\.speakerId\("([^"]+)"\)', webpage, 'speaker ID')
  52         story_id = self._search_regex(
  53             r'\.storyId\((\d+)\)', webpage, 'story ID')
  54         speaker_type = self._search_regex(
  55             r'\.speakerType\("([^"]+)"\)', webpage, 'speaker type')
  56         great_life = self._search_regex(
  57             r'isGreatLifeStory\s*=\s*(true|false)', webpage, 'great life story')
  58         is_great_life_series = great_life == 'true'
  59         duration = int_or_none(self._search_regex(
  60             r'\.duration\((\d+)\)', webpage, 'duration', fatal=False))
  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         }