yt_dlp/extractor/curiositystream.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     urlencode_postdata,
   7     compat_str,
   8     ExtractorError,
   9 )
  10
  11
  12 class CuriosityStreamBaseIE(InfoExtractor):
  13     _NETRC_MACHINE = 'curiositystream'
  14     _auth_token = None
  15
  16     def _handle_errors(self, result):
  17         error = result.get('error', {}).get('message')
  18         if error:
  19             if isinstance(error, dict):
  20                 error = ', '.join(error.values())
  21             raise ExtractorError(
  22                 '%s said: %s' % (self.IE_NAME, error), expected=True)
  23
  24     def _call_api(self, path, video_id, query=None):
  25         headers = {}
  26         if not self._auth_token:
  27             auth_cookie = self._get_cookies('https://curiositystream.com').get('auth_token')
  28             if auth_cookie:
  29                 self.write_debug('Obtained auth_token cookie')
  30                 self._auth_token = auth_cookie.value
  31         if self._auth_token:
  32             headers['X-Auth-Token'] = self._auth_token
  33         result = self._download_json(
  34             self._API_BASE_URL + path, video_id, headers=headers, query=query)
  35         self._handle_errors(result)
  36         return result['data']
  37
  38     def _perform_login(self, username, password):
  39         result = self._download_json(
  40             'https://api.curiositystream.com/v1/login', None,
  41             note='Logging in', data=urlencode_postdata({
  42                 'email': username,
  43                 'password': password,
  44             }))
  45         self._handle_errors(result)
  46         CuriosityStreamBaseIE._auth_token = result['message']['auth_token']
  47
  48
  49 class CuriosityStreamIE(CuriosityStreamBaseIE):
  50     IE_NAME = 'curiositystream'
  51     _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/video/(?P<id>\d+)'
  52     _TESTS = [{
  53         'url': 'https://app.curiositystream.com/video/2',
  54         'info_dict': {
  55             'id': '2',
  56             'ext': 'mp4',
  57             'title': 'How Did You Develop The Internet?',
  58             'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.',
  59             'channel': 'Curiosity Stream',
  60             'categories': ['Technology', 'Interview'],
  61             'average_rating': 96.79,
  62             'series_id': '2',
  63         },
  64         'params': {
  65             # m3u8 download
  66             'skip_download': True,
  67         },
  68     }]
  69
  70     _API_BASE_URL = 'https://api.curiositystream.com/v1/media/'
  71
  72     def _real_extract(self, url):
  73         video_id = self._match_id(url)
  74
  75         formats = []
  76         for encoding_format in ('m3u8', 'mpd'):
  77             media = self._call_api(video_id, video_id, query={
  78                 'encodingsNew': 'true',
  79                 'encodingsFormat': encoding_format,
  80             })
  81             for encoding in media.get('encodings', []):
  82                 playlist_url = encoding.get('master_playlist_url')
  83                 if encoding_format == 'm3u8':
  84                     # use `m3u8` entry_protocol until EXT-X-MAP is properly supported by `m3u8_native` entry_protocol
  85                     formats.extend(self._extract_m3u8_formats(
  86                         playlist_url, video_id, 'mp4',
  87                         m3u8_id='hls', fatal=False))
  88                 elif encoding_format == 'mpd':
  89                     formats.extend(self._extract_mpd_formats(
  90                         playlist_url, video_id, mpd_id='dash', fatal=False))
  91                 encoding_url = encoding.get('url')
  92                 file_url = encoding.get('file_url')
  93                 if not encoding_url and not file_url:
  94                     continue
  95                 f = {
  96                     'width': int_or_none(encoding.get('width')),
  97                     'height': int_or_none(encoding.get('height')),
  98                     'vbr': int_or_none(encoding.get('video_bitrate')),
  99                     'abr': int_or_none(encoding.get('audio_bitrate')),
 100                     'filesize': int_or_none(encoding.get('size_in_bytes')),
 101                     'vcodec': encoding.get('video_codec'),
 102                     'acodec': encoding.get('audio_codec'),
 103                     'container': encoding.get('container_type'),
 104                 }
 105                 for f_url in (encoding_url, file_url):
 106                     if not f_url:
 107                         continue
 108                     fmt = f.copy()
 109                     rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', f_url)
 110                     if rtmp:
 111                         fmt.update({
 112                             'url': rtmp.group('url'),
 113                             'play_path': rtmp.group('playpath'),
 114                             'app': rtmp.group('app'),
 115                             'ext': 'flv',
 116                             'format_id': 'rtmp',
 117                         })
 118                     else:
 119                         fmt.update({
 120                             'url': f_url,
 121                             'format_id': 'http',
 122                         })
 123                     formats.append(fmt)
 124         self._sort_formats(formats)
 125
 126         title = media['title']
 127
 128         subtitles = {}
 129         for closed_caption in media.get('closed_captions', []):
 130             sub_url = closed_caption.get('file')
 131             if not sub_url:
 132                 continue
 133             lang = closed_caption.get('code') or closed_caption.get('language') or 'en'
 134             subtitles.setdefault(lang, []).append({
 135                 'url': sub_url,
 136             })
 137
 138         return {
 139             'id': video_id,
 140             'formats': formats,
 141             'title': title,
 142             'description': media.get('description'),
 143             'thumbnail': media.get('image_large') or media.get('image_medium') or media.get('image_small'),
 144             'duration': int_or_none(media.get('duration')),
 145             'tags': media.get('tags'),
 146             'subtitles': subtitles,
 147             'channel': media.get('producer'),
 148             'categories': [media.get('primary_category'), media.get('type')],
 149             'average_rating': media.get('rating_percentage'),
 150             'series_id': str(media.get('collection_id') or '') or None,
 151         }
 152
 153
 154 class CuriosityStreamCollectionBaseIE(CuriosityStreamBaseIE):
 155
 156     def _real_extract(self, url):
 157         collection_id = self._match_id(url)
 158         collection = self._call_api(collection_id, collection_id)
 159         entries = []
 160         for media in collection.get('media', []):
 161             media_id = compat_str(media.get('id'))
 162             media_type, ie = ('series', CuriosityStreamSeriesIE) if media.get('is_collection') else ('video', CuriosityStreamIE)
 163             entries.append(self.url_result(
 164                 'https://curiositystream.com/%s/%s' % (media_type, media_id),
 165                 ie=ie.ie_key(), video_id=media_id))
 166         return self.playlist_result(
 167             entries, collection_id,
 168             collection.get('title'), collection.get('description'))
 169
 170
 171 class CuriosityStreamCollectionsIE(CuriosityStreamCollectionBaseIE):
 172     IE_NAME = 'curiositystream:collections'
 173     _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/collections/(?P<id>\d+)'
 174     _API_BASE_URL = 'https://api.curiositystream.com/v2/collections/'
 175     _TESTS = [{
 176         'url': 'https://curiositystream.com/collections/86',
 177         'info_dict': {
 178             'id': '86',
 179             'title': 'Staff Picks',
 180             'description': 'Wondering where to start? Here are a few of our favorite series and films... from our couch to yours.',
 181         },
 182         'playlist_mincount': 7,
 183     }, {
 184         'url': 'https://curiositystream.com/collections/36',
 185         'only_matching': True,
 186     }]
 187
 188
 189 class CuriosityStreamSeriesIE(CuriosityStreamCollectionBaseIE):
 190     IE_NAME = 'curiositystream:series'
 191     _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/(?:series|collection)/(?P<id>\d+)'
 192     _API_BASE_URL = 'https://api.curiositystream.com/v2/series/'
 193     _TESTS = [{
 194         'url': 'https://curiositystream.com/series/2',
 195         'info_dict': {
 196             'id': '2',
 197             'title': 'Curious Minds: The Internet',
 198             'description': 'How is the internet shaping our lives in the 21st Century?',
 199         },
 200         'playlist_mincount': 16,
 201     }, {
 202         'url': 'https://curiositystream.com/collection/2',
 203         'only_matching': True,
 204     }]