yt_dlp/extractor/curiositystream.py

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