yt_dlp/extractor/jable.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     InAdvancePagedList,
   6     int_or_none,
   7     orderedSet,
   8     unified_strdate,
   9 )
  10
  11
  12 class JableIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?jable.tv/videos/(?P<id>[\w-]+)'
  14     _TESTS = [{
  15         'url': 'https://jable.tv/videos/pppd-812/',
  16         'md5': 'f1537283a9bc073c31ff86ca35d9b2a6',
  17         'info_dict': {
  18             'id': 'pppd-812',
  19             'ext': 'mp4',
  20             'title': 'PPPD-812 只要表現好巨乳女教師吉根柚莉愛就獎勵學生們在白虎穴內射出精液',
  21             'description': 'md5:5b6d4199a854f62c5e56e26ccad19967',
  22             'thumbnail': r're:^https?://.*\.jpg$',
  23             'age_limit': 18,
  24             'like_count': int,
  25             'view_count': int,
  26         },
  27     }, {
  28         'url': 'https://jable.tv/videos/apak-220/',
  29         'md5': '71f9239d69ced58ab74a816908847cc1',
  30         'info_dict': {
  31             'id': 'apak-220',
  32             'ext': 'mp4',
  33             'title': 'md5:5c3861b7cf80112a6e2b70bccf170824',
  34             'description': '',
  35             'thumbnail': r're:^https?://.*\.jpg$',
  36             'age_limit': 18,
  37             'like_count': int,
  38             'view_count': int,
  39             'upload_date': '20220319',
  40         },
  41     }]
  42
  43     def _real_extract(self, url):
  44         video_id = self._match_id(url)
  45         webpage = self._download_webpage(url, video_id)
  46         formats = self._extract_m3u8_formats(
  47             self._search_regex(r'var\s+hlsUrl\s*=\s*\'([^\']+)', webpage, 'hls_url'), video_id, 'mp4', m3u8_id='hls')
  48         self._sort_formats(formats)
  49
  50         return {
  51             'id': video_id,
  52             'title': self._og_search_title(webpage),
  53             'description': self._og_search_description(webpage, default=''),
  54             'thumbnail': self._og_search_thumbnail(webpage, default=None),
  55             'formats': formats,
  56             'age_limit': 18,
  57             'upload_date': unified_strdate(self._search_regex(
  58                 r'class="inactive-color">\D+\s+(\d{4}-\d+-\d+)', webpage, 'upload_date', default=None)),
  59             'view_count': int_or_none(self._search_regex(
  60                 r'#icon-eye"></use></svg>\n*<span class="mr-3">([\d ]+)',
  61                 webpage, 'view_count', default='').replace(' ', '')),
  62             'like_count': int_or_none(self._search_regex(
  63                 r'#icon-heart"></use></svg><span class="count">(\d+)', webpage, 'link_count', default=None)),
  64         }
  65
  66
  67 class JablePlaylistIE(InfoExtractor):
  68     _VALID_URL = r'https?://(?:www\.)?jable.tv/(?:categories|models|tags)/(?P<id>[\w-]+)'
  69     _TESTS = [{
  70         'url': 'https://jable.tv/models/kaede-karen/',
  71         'info_dict': {
  72             'id': 'kaede-karen',
  73             'title': '楓カレン',
  74         },
  75         'playlist_count': 34,
  76     }, {
  77         'url': 'https://jable.tv/categories/roleplay/',
  78         'only_matching': True,
  79     }, {
  80         'url': 'https://jable.tv/tags/girl/',
  81         'only_matching': True,
  82     }]
  83
  84     def _real_extract(self, url):
  85         playlist_id = self._match_id(url)
  86         webpage = self._download_webpage(url, playlist_id)
  87
  88         def page_func(page_num):
  89             return [
  90                 self.url_result(player_url, JableIE)
  91                 for player_url in orderedSet(re.findall(
  92                     r'href="(https://jable.tv/videos/[\w-]+/?)"',
  93                     self._download_webpage(url, playlist_id, query={
  94                         'mode': 'async',
  95                         'from': page_num + 1,
  96                         'function': 'get_block',
  97                         'block_id': 'list_videos_common_videos_list',
  98                     }, note=f'Downloading page {page_num + 1}')))]
  99
 100         return self.playlist_result(
 101             InAdvancePagedList(page_func, int_or_none(self._search_regex(
 102                 r'from:(\d+)">[^<]+\s*&raquo;', webpage, 'last page number', default=1)), 24),
 103             playlist_id, self._search_regex(
 104                 r'<h2 class="h3-md mb-1">([^<]+)', webpage, 'playlist title', default=None))