yt_dlp/extractor/minds.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     clean_html,
   5     format_field,
   6     int_or_none,
   7     str_or_none,
   8     strip_or_none,
   9 )
  10
  11
  12 class MindsBaseIE(InfoExtractor):
  13     _VALID_URL_BASE = r'https?://(?:www\.)?minds\.com/'
  14
  15     def _call_api(self, path, video_id, resource, query=None):
  16         api_url = 'https://www.minds.com/api/' + path
  17         token = self._get_cookies(api_url).get('XSRF-TOKEN')
  18         return self._download_json(
  19             api_url, video_id, 'Downloading %s JSON metadata' % resource, headers={
  20                 'Referer': 'https://www.minds.com/',
  21                 'X-XSRF-TOKEN': token.value if token else '',
  22             }, query=query)
  23
  24
  25 class MindsIE(MindsBaseIE):
  26     IE_NAME = 'minds'
  27     _VALID_URL = MindsBaseIE._VALID_URL_BASE + r'(?:media|newsfeed|archive/view)/(?P<id>[0-9]+)'
  28     _TESTS = [{
  29         'url': 'https://www.minds.com/media/100000000000086822',
  30         'md5': '215a658184a419764852239d4970b045',
  31         'info_dict': {
  32             'id': '100000000000086822',
  33             'ext': 'mp4',
  34             'title': 'Minds intro sequence',
  35             'thumbnail': r're:https?://.+\.png',
  36             'uploader_id': 'ottman',
  37             'upload_date': '20130524',
  38             'timestamp': 1369404826,
  39             'uploader': 'Bill Ottman',
  40             'view_count': int,
  41             'like_count': int,
  42             'dislike_count': int,
  43             'tags': ['animation'],
  44             'comment_count': int,
  45             'license': 'attribution-cc',
  46         },
  47     }, {
  48         # entity.type == 'activity' and empty title
  49         'url': 'https://www.minds.com/newsfeed/798025111988506624',
  50         'md5': 'b2733a74af78d7fd3f541c4cbbaa5950',
  51         'info_dict': {
  52             'id': '798022190320226304',
  53             'ext': 'mp4',
  54             'title': '798022190320226304',
  55             'uploader': 'ColinFlaherty',
  56             'upload_date': '20180111',
  57             'timestamp': 1515639316,
  58             'uploader_id': 'ColinFlaherty',
  59         },
  60     }, {
  61         'url': 'https://www.minds.com/archive/view/715172106794442752',
  62         'only_matching': True,
  63     }, {
  64         # youtube perma_url
  65         'url': 'https://www.minds.com/newsfeed/1197131838022602752',
  66         'only_matching': True,
  67     }]
  68
  69     def _real_extract(self, url):
  70         entity_id = self._match_id(url)
  71         entity = self._call_api(
  72             'v1/entities/entity/' + entity_id, entity_id, 'entity')['entity']
  73         if entity.get('type') == 'activity':
  74             if entity.get('custom_type') == 'video':
  75                 video_id = entity['entity_guid']
  76             else:
  77                 return self.url_result(entity['perma_url'])
  78         else:
  79             assert entity['subtype'] == 'video'
  80             video_id = entity_id
  81         # 1080p and webm formats available only on the sources array
  82         video = self._call_api(
  83             'v2/media/video/' + video_id, video_id, 'video')
  84
  85         formats = []
  86         for source in (video.get('sources') or []):
  87             src = source.get('src')
  88             if not src:
  89                 continue
  90             formats.append({
  91                 'format_id': source.get('label'),
  92                 'height': int_or_none(source.get('size')),
  93                 'url': src,
  94             })
  95         self._sort_formats(formats)
  96
  97         entity = video.get('entity') or entity
  98         owner = entity.get('ownerObj') or {}
  99         uploader_id = owner.get('username')
 100
 101         tags = entity.get('tags')
 102         if tags and isinstance(tags, compat_str):
 103             tags = [tags]
 104
 105         thumbnail = None
 106         poster = video.get('poster') or entity.get('thumbnail_src')
 107         if poster:
 108             urlh = self._request_webpage(poster, video_id, fatal=False)
 109             if urlh:
 110                 thumbnail = urlh.geturl()
 111
 112         return {
 113             'id': video_id,
 114             'title': entity.get('title') or video_id,
 115             'formats': formats,
 116             'description': clean_html(entity.get('description')) or None,
 117             'license': str_or_none(entity.get('license')),
 118             'timestamp': int_or_none(entity.get('time_created')),
 119             'uploader': strip_or_none(owner.get('name')),
 120             'uploader_id': uploader_id,
 121             'uploader_url': format_field(uploader_id, None, 'https://www.minds.com/%s'),
 122             'view_count': int_or_none(entity.get('play:count')),
 123             'like_count': int_or_none(entity.get('thumbs:up:count')),
 124             'dislike_count': int_or_none(entity.get('thumbs:down:count')),
 125             'tags': tags,
 126             'comment_count': int_or_none(entity.get('comments:count')),
 127             'thumbnail': thumbnail,
 128         }
 129
 130
 131 class MindsFeedBaseIE(MindsBaseIE):
 132     _PAGE_SIZE = 150
 133
 134     def _entries(self, feed_id):
 135         query = {'limit': self._PAGE_SIZE, 'sync': 1}
 136         i = 1
 137         while True:
 138             data = self._call_api(
 139                 'v2/feeds/container/%s/videos' % feed_id,
 140                 feed_id, 'page %s' % i, query)
 141             entities = data.get('entities') or []
 142             for entity in entities:
 143                 guid = entity.get('guid')
 144                 if not guid:
 145                     continue
 146                 yield self.url_result(
 147                     'https://www.minds.com/newsfeed/' + guid,
 148                     MindsIE.ie_key(), guid)
 149             query['from_timestamp'] = data['load-next']
 150             if not (query['from_timestamp'] and len(entities) == self._PAGE_SIZE):
 151                 break
 152             i += 1
 153
 154     def _real_extract(self, url):
 155         feed_id = self._match_id(url)
 156         feed = self._call_api(
 157             'v1/%s/%s' % (self._FEED_PATH, feed_id),
 158             feed_id, self._FEED_TYPE)[self._FEED_TYPE]
 159
 160         return self.playlist_result(
 161             self._entries(feed['guid']), feed_id,
 162             strip_or_none(feed.get('name')),
 163             feed.get('briefdescription'))
 164
 165
 166 class MindsChannelIE(MindsFeedBaseIE):
 167     _FEED_TYPE = 'channel'
 168     IE_NAME = 'minds:' + _FEED_TYPE
 169     _VALID_URL = MindsBaseIE._VALID_URL_BASE + r'(?!(?:newsfeed|media|api|archive|groups)/)(?P<id>[^/?&#]+)'
 170     _FEED_PATH = 'channel'
 171     _TEST = {
 172         'url': 'https://www.minds.com/ottman',
 173         'info_dict': {
 174             'id': 'ottman',
 175             'title': 'Bill Ottman',
 176             'description': 'Co-creator & CEO @minds',
 177         },
 178         'playlist_mincount': 54,
 179     }
 180
 181
 182 class MindsGroupIE(MindsFeedBaseIE):
 183     _FEED_TYPE = 'group'
 184     IE_NAME = 'minds:' + _FEED_TYPE
 185     _VALID_URL = MindsBaseIE._VALID_URL_BASE + r'groups/profile/(?P<id>[0-9]+)'
 186     _FEED_PATH = 'groups/group'
 187     _TEST = {
 188         'url': 'https://www.minds.com/groups/profile/785582576369672204/feed/videos',
 189         'info_dict': {
 190             'id': '785582576369672204',
 191             'title': 'Cooking Videos',
 192         },
 193         'playlist_mincount': 1,
 194     }