yt_dlp/extractor/boosty.py

   1 from .common import InfoExtractor
   2 from .youtube import YoutubeIE
   3 from ..utils import (
   4     ExtractorError,
   5     int_or_none,
   6     qualities,
   7     str_or_none,
   8     url_or_none,
   9 )
  10 from ..utils.traversal import traverse_obj
  11
  12
  13 class BoostyIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?boosty\.to/(?P<user>[^/#?]+)/posts/(?P<post_id>[^/#?]+)'
  15     _TESTS = [{
  16         # single ok_video
  17         'url': 'https://boosty.to/kuplinov/posts/e55d050c-e3bb-4873-a7db-ac7a49b40c38',
  18         'info_dict': {
  19             'id': 'd7473824-352e-48e2-ae53-d4aa39459968',
  20             'title': 'phasma_3',
  21             'channel': 'Kuplinov',
  22             'channel_id': '7958701',
  23             'timestamp': 1655031975,
  24             'upload_date': '20220612',
  25             'release_timestamp': 1655049000,
  26             'release_date': '20220612',
  27             'modified_timestamp': 1668680993,
  28             'modified_date': '20221117',
  29             'tags': ['куплинов', 'phasmophobia'],
  30             'like_count': int,
  31             'ext': 'mp4',
  32             'duration': 105,
  33             'view_count': int,
  34             'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
  35         },
  36     }, {
  37         # multiple ok_video
  38         'url': 'https://boosty.to/maddyson/posts/0c652798-3b35-471f-8b48-a76a0b28736f',
  39         'info_dict': {
  40             'id': '0c652798-3b35-471f-8b48-a76a0b28736f',
  41             'title': 'то что не пропустил юта6',
  42             'channel': 'Илья Давыдов',
  43             'channel_id': '6808257',
  44             'timestamp': 1694017040,
  45             'upload_date': '20230906',
  46             'release_timestamp': 1694017040,
  47             'release_date': '20230906',
  48             'modified_timestamp': 1694071178,
  49             'modified_date': '20230907',
  50             'like_count': int,
  51         },
  52         'playlist_count': 3,
  53         'playlist': [{
  54             'info_dict': {
  55                 'id': 'cc325a9f-a563-41c6-bf47-516c1b506c9a',
  56                 'title': 'то что не пропустил юта6',
  57                 'channel': 'Илья Давыдов',
  58                 'channel_id': '6808257',
  59                 'timestamp': 1694017040,
  60                 'upload_date': '20230906',
  61                 'release_timestamp': 1694017040,
  62                 'release_date': '20230906',
  63                 'modified_timestamp': 1694071178,
  64                 'modified_date': '20230907',
  65                 'like_count': int,
  66                 'ext': 'mp4',
  67                 'duration': 31204,
  68                 'view_count': int,
  69                 'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
  70             },
  71         }, {
  72             'info_dict': {
  73                 'id': 'd07b0a72-9493-4512-b54e-55ce468fd4b7',
  74                 'title': 'то что не пропустил юта6',
  75                 'channel': 'Илья Давыдов',
  76                 'channel_id': '6808257',
  77                 'timestamp': 1694017040,
  78                 'upload_date': '20230906',
  79                 'release_timestamp': 1694017040,
  80                 'release_date': '20230906',
  81                 'modified_timestamp': 1694071178,
  82                 'modified_date': '20230907',
  83                 'like_count': int,
  84                 'ext': 'mp4',
  85                 'duration': 25704,
  86                 'view_count': int,
  87                 'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
  88             },
  89         }, {
  90             'info_dict': {
  91                 'id': '4a3bba32-78c8-422a-9432-2791aff60b42',
  92                 'title': 'то что не пропустил юта6',
  93                 'channel': 'Илья Давыдов',
  94                 'channel_id': '6808257',
  95                 'timestamp': 1694017040,
  96                 'upload_date': '20230906',
  97                 'release_timestamp': 1694017040,
  98                 'release_date': '20230906',
  99                 'modified_timestamp': 1694071178,
 100                 'modified_date': '20230907',
 101                 'like_count': int,
 102                 'ext': 'mp4',
 103                 'duration': 31867,
 104                 'view_count': int,
 105                 'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
 106             },
 107         }],
 108     }, {
 109         # single external video (youtube)
 110         'url': 'https://boosty.to/denischuzhoy/posts/6094a487-bcec-4cf8-a453-43313b463c38',
 111         'info_dict': {
 112             'id': 'EXelTnve5lY',
 113             'title': 'Послание Президента Федеральному Собранию | Класс народа',
 114             'upload_date': '20210425',
 115             'channel': 'Денис Чужой',
 116             'tags': 'count:10',
 117             'like_count': int,
 118             'ext': 'mp4',
 119             'duration': 816,
 120             'view_count': int,
 121             'thumbnail': r're:^https://i\.ytimg\.com/',
 122             'age_limit': 0,
 123             'availability': 'public',
 124             'categories': list,
 125             'channel_follower_count': int,
 126             'channel_id': 'UCCzVNbWZfYpBfyofCCUD_0w',
 127             'channel_is_verified': bool,
 128             'channel_url': r're:^https://www\.youtube\.com/',
 129             'comment_count': int,
 130             'description': str,
 131             'heatmap': 'count:100',
 132             'live_status': str,
 133             'playable_in_embed': bool,
 134             'uploader': str,
 135             'uploader_id': str,
 136             'uploader_url': r're:^https://www\.youtube\.com/',
 137         },
 138     }]
 139
 140     _MP4_TYPES = ('tiny', 'lowest', 'low', 'medium', 'high', 'full_hd', 'quad_hd', 'ultra_hd')
 141
 142     def _extract_formats(self, player_urls, video_id):
 143         formats = []
 144         quality = qualities(self._MP4_TYPES)
 145         for player_url in traverse_obj(player_urls, lambda _, v: url_or_none(v['url'])):
 146             url = player_url['url']
 147             format_type = player_url.get('type')
 148             if format_type in ('hls', 'hls_live', 'live_ondemand_hls', 'live_playback_hls'):
 149                 formats.extend(self._extract_m3u8_formats(url, video_id, m3u8_id='hls', fatal=False))
 150             elif format_type in ('dash', 'dash_live', 'live_playback_dash'):
 151                 formats.extend(self._extract_mpd_formats(url, video_id, mpd_id='dash', fatal=False))
 152             elif format_type in self._MP4_TYPES:
 153                 formats.append({
 154                     'url': url,
 155                     'ext': 'mp4',
 156                     'format_id': format_type,
 157                     'quality': quality(format_type),
 158                 })
 159             else:
 160                 self.report_warning(f'Unknown format type: {format_type!r}')
 161         return formats
 162
 163     def _real_extract(self, url):
 164         user, post_id = self._match_valid_url(url).group('user', 'post_id')
 165         post = self._download_json(
 166             f'https://api.boosty.to/v1/blog/{user}/post/{post_id}', post_id,
 167             note='Downloading post data', errnote='Unable to download post data')
 168
 169         post_title = post.get('title')
 170         if not post_title:
 171             self.report_warning('Unable to extract post title. Falling back to parsing html page')
 172             webpage = self._download_webpage(url, video_id=post_id)
 173             post_title = self._og_search_title(webpage, default=None) or self._html_extract_title(webpage)
 174
 175         common_metadata = {
 176             'title': post_title,
 177             **traverse_obj(post, {
 178                 'channel': ('user', 'name', {str}),
 179                 'channel_id': ('user', 'id', {str_or_none}),
 180                 'timestamp': ('createdAt', {int_or_none}),
 181                 'release_timestamp': ('publishTime', {int_or_none}),
 182                 'modified_timestamp': ('updatedAt', {int_or_none}),
 183                 'tags': ('tags', ..., 'title', {str}),
 184                 'like_count': ('count', 'likes', {int_or_none}),
 185             }),
 186         }
 187         entries = []
 188         for item in traverse_obj(post, ('data', ..., {dict})):
 189             item_type = item.get('type')
 190             if item_type == 'video' and url_or_none(item.get('url')):
 191                 entries.append(self.url_result(item['url'], YoutubeIE))
 192             elif item_type == 'ok_video':
 193                 video_id = item.get('id') or post_id
 194                 entries.append({
 195                     'id': video_id,
 196                     'formats': self._extract_formats(item.get('playerUrls'), video_id),
 197                     **common_metadata,
 198                     **traverse_obj(item, {
 199                         'title': ('title', {str}),
 200                         'duration': ('duration', {int_or_none}),
 201                         'view_count': ('viewsCounter', {int_or_none}),
 202                         'thumbnail': (('previewUrl', 'defaultPreview'), {url_or_none}),
 203                     }, get_all=False)})
 204
 205         if not entries:
 206             raise ExtractorError('No videos found', expected=True)
 207         if len(entries) == 1:
 208             return entries[0]
 209         return self.playlist_result(entries, post_id, post_title, **common_metadata)