yt_dlp/extractor/altcensored.py

   1 import re
   2
   3 from .archiveorg import ArchiveOrgIE
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     InAdvancePagedList,
   7     clean_html,
   8     int_or_none,
   9     orderedSet,
  10     str_to_int,
  11     urljoin,
  12 )
  13
  14
  15 class AltCensoredIE(InfoExtractor):
  16     IE_NAME = 'altcensored'
  17     _VALID_URL = r'https?://(?:www\.)?altcensored\.com/(?:watch\?v=|embed/)(?P<id>[^/?#]+)'
  18     _TESTS = [{
  19         'url': 'https://www.altcensored.com/watch?v=k0srjLSkga8',
  20         'info_dict': {
  21             'id': 'youtube-k0srjLSkga8',
  22             'ext': 'webm',
  23             'title': "QUELLES SONT LES CONSÉQUENCES DE L'HYPERSEXUALISATION DE LA SOCIÉTÉ ?",
  24             'display_id': 'k0srjLSkga8.webm',
  25             'release_date': '20180403',
  26             'creators': ['Virginie Vota'],
  27             'release_year': 2018,
  28             'upload_date': '20230318',
  29             'uploader': 'admin@altcensored.com',
  30             'description': 'md5:0b38a8fc04103579d5c1db10a247dc30',
  31             'timestamp': 1679161343,
  32             'track': 'k0srjLSkga8',
  33             'duration': 926.09,
  34             'thumbnail': 'https://archive.org/download/youtube-k0srjLSkga8/youtube-k0srjLSkga8.thumbs/k0srjLSkga8_000925.jpg',
  35             'view_count': int,
  36             'categories': ['News & Politics'],
  37         },
  38     }]
  39
  40     def _real_extract(self, url):
  41         video_id = self._match_id(url)
  42         webpage = self._download_webpage(url, video_id)
  43         category = clean_html(self._html_search_regex(
  44             r'<a href="/category/\d+">([^<]+)</a>', webpage, 'category', default=None))
  45
  46         return {
  47             '_type': 'url_transparent',
  48             'url': f'https://archive.org/details/youtube-{video_id}',
  49             'ie_key': ArchiveOrgIE.ie_key(),
  50             'view_count': str_to_int(self._html_search_regex(
  51                 r'YouTube Views:(?:\s|&nbsp;)*([\d,]+)', webpage, 'view count', default=None)),
  52             'categories': [category] if category else None,
  53         }
  54
  55
  56 class AltCensoredChannelIE(InfoExtractor):
  57     IE_NAME = 'altcensored:channel'
  58     _VALID_URL = r'https?://(?:www\.)?altcensored\.com/channel/(?!page|table)(?P<id>[^/?#]+)'
  59     _PAGE_SIZE = 24
  60     _TESTS = [{
  61         'url': 'https://www.altcensored.com/channel/UCFPTO55xxHqFqkzRZHu4kcw',
  62         'info_dict': {
  63             'title': 'Virginie Vota',
  64             'id': 'UCFPTO55xxHqFqkzRZHu4kcw',
  65         },
  66         'playlist_count': 85,
  67     }, {
  68         'url': 'https://altcensored.com/channel/UC9CcJ96HKMWn0LZlcxlpFTw',
  69         'info_dict': {
  70             'title': 'yukikaze775',
  71             'id': 'UC9CcJ96HKMWn0LZlcxlpFTw',
  72         },
  73         'playlist_count': 4,
  74     }, {
  75         'url': 'https://altcensored.com/channel/UCfYbb7nga6-icsFWWgS-kWw',
  76         'info_dict': {
  77             'title': 'Mister Metokur',
  78             'id': 'UCfYbb7nga6-icsFWWgS-kWw',
  79         },
  80         'playlist_count': 121,
  81     }]
  82
  83     def _real_extract(self, url):
  84         channel_id = self._match_id(url)
  85         webpage = self._download_webpage(
  86             url, channel_id, 'Download channel webpage', 'Unable to get channel webpage')
  87         title = self._html_search_meta('altcen_title', webpage, 'title', fatal=False)
  88         page_count = int_or_none(self._html_search_regex(
  89             r'<a[^>]+href="/channel/[\w-]+/page/(\d+)">(?:\1)</a>',
  90             webpage, 'page count', default='1'))
  91
  92         def page_func(page_num):
  93             page_num += 1
  94             webpage = self._download_webpage(
  95                 f'https://altcensored.com/channel/{channel_id}/page/{page_num}',
  96                 channel_id, note=f'Downloading page {page_num}')
  97
  98             items = re.findall(r'<a[^>]+href="(/watch\?v=[^"]+)', webpage)
  99             return [self.url_result(urljoin('https://www.altcensored.com', path), AltCensoredIE)
 100                     for path in orderedSet(items)]
 101
 102         return self.playlist_result(
 103             InAdvancePagedList(page_func, page_count, self._PAGE_SIZE),
 104             playlist_id=channel_id, playlist_title=title)