yt_dlp/extractor/webofstories.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     orderedSet,
   7 )
   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         'url': 'http://www.webofstories.com/play/hans.bethe/71',
  17         'md5': '373e4dd915f60cfe3116322642ddf364',
  18         'info_dict': {
  19             'id': '4536',
  20             'ext': 'mp4',
  21             'title': 'The temperature of the sun',
  22             'thumbnail': r're:^https?://.*\.jpg$',
  23             'description': 'Hans Bethe talks about calculating the temperature of the sun',
  24             'duration': 238,
  25         },
  26     }, {
  27         'url': 'http://www.webofstories.com/play/55908',
  28         'md5': '2985a698e1fe3211022422c4b5ed962c',
  29         'info_dict': {
  30             'id': '55908',
  31             'ext': 'mp4',
  32             'title': 'The story of Gemmata obscuriglobus',
  33             'thumbnail': r're:^https?://.*\.jpg$',
  34             'description': 'Planctomycete talks about The story of Gemmata obscuriglobus',
  35             'duration': 169,
  36         },
  37         'skip': 'notfound',
  38     }, {
  39         # malformed og:title meta
  40         'url': 'http://www.webofstories.com/play/54215?o=MS',
  41         'info_dict': {
  42             'id': '54215',
  43             'ext': 'mp4',
  44             'title': '"A Leg to Stand On"',
  45             'thumbnail': r're:^https?://.*\.jpg$',
  46             'description': 'Oliver Sacks talks about the death and resurrection of a limb',
  47             'duration': 97,
  48         },
  49         'params': {
  50             'skip_download': True,
  51         },
  52     }]
  53
  54     def _real_extract(self, url):
  55         video_id = self._match_id(url)
  56
  57         webpage = self._download_webpage(url, video_id)
  58         # Sometimes og:title meta is malformed
  59         title = self._og_search_title(webpage, default=None) or self._html_search_regex(
  60             r'(?s)<strong>Title:\s*</strong>(.+?)<', webpage, 'title')
  61         description = self._html_search_meta('description', webpage)
  62         thumbnail = self._og_search_thumbnail(webpage)
  63
  64         embed_params = [s.strip(" \r\n\t'") for s in self._search_regex(
  65             r'(?s)\$\("#embedCode"\).html\(getEmbedCode\((.*?)\)',
  66             webpage, 'embed params').split(',')]
  67
  68         (
  69             _, speaker_id, story_id, story_duration,
  70             speaker_type, great_life, _thumbnail, _has_subtitles,
  71             story_filename, _story_order) = embed_params
  72
  73         is_great_life_series = great_life == 'true'
  74         duration = int_or_none(story_duration)
  75
  76         # URL building, see: http://www.webofstories.com/scripts/player.js
  77         ms_prefix = ''
  78         if speaker_type.lower() == 'ms':
  79             ms_prefix = 'mini_sites/'
  80
  81         if is_great_life_series:
  82             mp4_url = f'{self._VIDEO_DOMAIN}lives/{speaker_id}/{story_filename}.mp4'
  83             rtmp_ext = 'flv'
  84             streamer = self._GREAT_LIFE_STREAMER
  85             play_path = f'stories/{speaker_id}/{story_filename}'
  86         else:
  87             mp4_url = f'{self._VIDEO_DOMAIN}{ms_prefix}{speaker_id}/{story_filename}.mp4'
  88             rtmp_ext = 'mp4'
  89             streamer = self._USER_STREAMER
  90             play_path = f'mp4:{ms_prefix}{speaker_id}/{story_filename}.mp4'
  91
  92         formats = [{
  93             'format_id': 'mp4_sd',
  94             'url': mp4_url,
  95         }, {
  96             'format_id': 'rtmp_sd',
  97             'page_url': url,
  98             'url': streamer,
  99             'ext': rtmp_ext,
 100             'play_path': play_path,
 101         }]
 102
 103         return {
 104             'id': story_id,
 105             'title': title,
 106             'formats': formats,
 107             'thumbnail': thumbnail,
 108             'description': description,
 109             'duration': duration,
 110         }
 111
 112
 113 class WebOfStoriesPlaylistIE(InfoExtractor):
 114     _VALID_URL = r'https?://(?:www\.)?webofstories\.com/playAll/(?P<id>[^/]+)'
 115     _TEST = {
 116         'url': 'http://www.webofstories.com/playAll/donald.knuth',
 117         'info_dict': {
 118             'id': 'donald.knuth',
 119             'title': 'Donald Knuth (Scientist)',
 120         },
 121         'playlist_mincount': 97,
 122     }
 123
 124     def _real_extract(self, url):
 125         playlist_id = self._match_id(url)
 126
 127         webpage = self._download_webpage(url, playlist_id)
 128
 129         entries = [
 130             self.url_result(
 131                 f'http://www.webofstories.com/play/{video_id}',
 132                 'WebOfStories', video_id=video_id)
 133             for video_id in orderedSet(re.findall(r'\bid=["\']td_(\d+)', webpage))
 134         ]
 135
 136         title = self._search_regex(
 137             r'<div id="speakerName">\s*<span>([^<]+)</span>',
 138             webpage, 'speaker', default=None)
 139         if title:
 140             field = self._search_regex(
 141                 r'<span id="primaryField">([^<]+)</span>',
 142                 webpage, 'field', default=None)
 143             if field:
 144                 title += f' ({field})'
 145
 146         if not title:
 147             title = self._search_regex(
 148                 r'<title>Play\s+all\s+stories\s*-\s*([^<]+)\s*-\s*Web\s+of\s+Stories</title>',
 149                 webpage, 'title')
 150
 151         return self.playlist_result(entries, playlist_id, title)