youtube_dl/extractor/minds.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_str
   6 from ..utils import (
   7     clean_html,
   8     int_or_none,
   9     str_or_none,
  10     strip_or_none,
  11 )
  12
  13
  14 class MindsBaseIE(InfoExtractor):
  15     _VALID_URL_BASE = r'https?://(?:www\.)?minds\.com/'
  16
  17     def _call_api(self, path, video_id, resource, query=None):
  18         api_url = 'https://www.minds.com/api/' + path
  19         token = self._get_cookies(api_url).get('XSRF-TOKEN')
  20         return self._download_json(
  21             api_url, video_id, 'Downloading %s JSON metadata' % resource, headers={
  22                 'Referer': 'https://www.minds.com/',
  23                 'X-XSRF-TOKEN': token.value if token else '',
  24             }, query=query)
  25
  26
  27 class MindsIE(MindsBaseIE):
  28     IE_NAME = 'minds'
  29     _VALID_URL = MindsBaseIE._VALID_URL_BASE + r'(?:media|newsfeed|archive/view)/(?P<id>[0-9]+)'
  30     _TESTS = [{
  31         'url': 'https://www.minds.com/media/100000000000086822',
  32         'md5': '215a658184a419764852239d4970b045',
  33         'info_dict': {
  34             'id': '100000000000086822',
  35             'ext': 'mp4',
  36             'title': 'Minds intro sequence',
  37             'thumbnail': r're:https?://.+\.png',
  38             'uploader_id': 'ottman',
  39             'upload_date': '20130524',
  40             'timestamp': 1369404826,
  41             'uploader': 'Bill Ottman',
  42             'view_count': int,
  43             'like_count': int,
  44             'dislike_count': int,
  45             'tags': ['animation'],
  46             'comment_count': int,
  47             'license': 'attribution-cc',
  48         },
  49     }, {
  50         # entity.type == 'activity' and empty title
  51         'url': 'https://www.minds.com/newsfeed/798025111988506624',
  52         'md5': 'b2733a74af78d7fd3f541c4cbbaa5950',
  53         'info_dict': {
  54             'id': '798022190320226304',
  55             'ext': 'mp4',
  56             'title': '798022190320226304',
  57             'uploader': 'ColinFlaherty',
  58             'upload_date': '20180111',
  59             'timestamp': 1515639316,
  60             'uploader_id': 'ColinFlaherty',
  61         },
  62     }, {
  63         'url': 'https://www.minds.com/archive/view/715172106794442752',
  64         'only_matching': True,
  65     }, {
  66         # youtube perma_url
  67         'url': 'https://www.minds.com/newsfeed/1197131838022602752',
  68         'only_matching': True,
  69     }]
  70
  71     def _real_extract(self, url):
  72         entity_id = self._match_id(url)
  73         entity = self._call_api(
  74             'v1/entities/entity/' + entity_id, entity_id, 'entity')['entity']
  75         if entity.get('type') == 'activity':
  76             if entity.get('custom_type') == 'video':
  77                 video_id = entity['entity_guid']
  78             else:
  79                 return self.url_result(entity['perma_url'])
  80         else:
  81             assert(entity['subtype'] == 'video')
  82             video_id = entity_id
  83         # 1080p and webm formats available only on the sources array
  84         video = self._call_api(
  85             'v2/media/video/' + video_id, video_id, 'video')
  86
  87         formats = []
  88         for source in (video.get('sources') or []):
  89             src = source.get('src')
  90             if not src:
  91                 continue
  92             formats.append({
  93                 'format_id': source.get('label'),
  94                 'height': int_or_none(source.get('size')),
  95                 'url': src,
  96             })
  97         self._sort_formats(formats)
  98
  99         entity = video.get('entity') or entity
 100         owner = entity.get('ownerObj') or {}
 101         uploader_id = owner.get('username')
 102
 103         tags = entity.get('tags')
 104         if tags and isinstance(tags, compat_str):
 105             tags = [tags]
 106
 107         thumbnail = None
 108         poster = video.get('poster') or entity.get('thumbnail_src')
 109         if poster:
 110             urlh = self._request_webpage(poster, video_id, fatal=False)
 111             if urlh:
 112                 thumbnail = urlh.geturl()
 113
 114         return {
 115             'id': video_id,
 116             'title': entity.get('title') or video_id,
 117             'formats': formats,
 118             'description': clean_html(entity.get('description')) or None,
 119             'license': str_or_none(entity.get('license')),
 120             'timestamp': int_or_none(entity.get('time_created')),
 121             'uploader': strip_or_none(owner.get('name')),
 122             'uploader_id': uploader_id,
 123             'uploader_url': 'https://www.minds.com/' + uploader_id if uploader_id else None,
 124             'view_count': int_or_none(entity.get('play:count')),
 125             'like_count': int_or_none(entity.get('thumbs:up:count')),
 126             'dislike_count': int_or_none(entity.get('thumbs:down:count')),
 127             'tags': tags,
 128             'comment_count': int_or_none(entity.get('comments:count')),
 129             'thumbnail': thumbnail,
 130         }
 131
 132
 133 class MindsFeedBaseIE(MindsBaseIE):
 134     _PAGE_SIZE = 150
 135
 136     def _entries(self, feed_id):
 137         query = {'limit': self._PAGE_SIZE, 'sync': 1}
 138         i = 1
 139         while True:
 140             data = self._call_api(
 141                 'v2/feeds/container/%s/videos' % feed_id,
 142                 feed_id, 'page %s' % i, query)
 143             entities = data.get('entities') or []
 144             for entity in entities:
 145                 guid = entity.get('guid')
 146                 if not guid:
 147                     continue
 148                 yield self.url_result(
 149                     'https://www.minds.com/newsfeed/' + guid,
 150                     MindsIE.ie_key(), guid)
 151             query['from_timestamp'] = data['load-next']
 152             if not (query['from_timestamp'] and len(entities) == self._PAGE_SIZE):
 153                 break
 154             i += 1
 155
 156     def _real_extract(self, url):
 157         feed_id = self._match_id(url)
 158         feed = self._call_api(
 159             'v1/%s/%s' % (self._FEED_PATH, feed_id),
 160             feed_id, self._FEED_TYPE)[self._FEED_TYPE]
 161
 162         return self.playlist_result(
 163             self._entries(feed['guid']), feed_id,
 164             strip_or_none(feed.get('name')),
 165             feed.get('briefdescription'))
 166
 167
 168 class MindsChannelIE(MindsFeedBaseIE):
 169     _FEED_TYPE = 'channel'
 170     IE_NAME = 'minds:' + _FEED_TYPE
 171     _VALID_URL = MindsBaseIE._VALID_URL_BASE + r'(?!(?:newsfeed|media|api|archive|groups)/)(?P<id>[^/?&#]+)'
 172     _FEED_PATH = 'channel'
 173     _TEST = {
 174         'url': 'https://www.minds.com/ottman',
 175         'info_dict': {
 176             'id': 'ottman',
 177             'title': 'Bill Ottman',
 178             'description': 'Co-creator & CEO @minds',
 179         },
 180         'playlist_mincount': 54,
 181     }
 182
 183
 184 class MindsGroupIE(MindsFeedBaseIE):
 185     _FEED_TYPE = 'group'
 186     IE_NAME = 'minds:' + _FEED_TYPE
 187     _VALID_URL = MindsBaseIE._VALID_URL_BASE + r'groups/profile/(?P<id>[0-9]+)'
 188     _FEED_PATH = 'groups/group'
 189     _TEST = {
 190         'url': 'https://www.minds.com/groups/profile/785582576369672204/feed/videos',
 191         'info_dict': {
 192             'id': '785582576369672204',
 193             'title': 'Cooking Videos',
 194         },
 195         'playlist_mincount': 1,
 196     }