yt_dlp/extractor/xxxymovies.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     parse_duration,
   5 )
   6
   7
   8 class XXXYMoviesIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:www\.)?xxxymovies\.com/videos/(?P<id>\d+)/(?P<display_id>[^/]+)'
  10     _TEST = {
  11         'url': 'http://xxxymovies.com/videos/138669/ecstatic-orgasm-sofcore/',
  12         'md5': '810b1bdbbffff89dd13bdb369fe7be4b',
  13         'info_dict': {
  14             'id': '138669',
  15             'display_id': 'ecstatic-orgasm-sofcore',
  16             'ext': 'mp4',
  17             'title': 'Ecstatic Orgasm Sofcore',
  18             'duration': 931,
  19             'categories': list,
  20             'view_count': int,
  21             'like_count': int,
  22             'dislike_count': int,
  23             'age_limit': 18,
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         mobj = self._match_valid_url(url)
  29         video_id = mobj.group('id')
  30         display_id = mobj.group('display_id')
  31
  32         webpage = self._download_webpage(url, display_id)
  33
  34         video_url = self._search_regex(
  35             r"video_url\s*:\s*'([^']+)'", webpage, 'video URL')
  36
  37         title = self._html_search_regex(
  38             [r'<div[^>]+\bclass="block_header"[^>]*>\s*<h1>([^<]+)<',
  39              r'<title>(.*?)\s*-\s*(?:XXXYMovies\.com|XXX\s+Movies)</title>'],
  40             webpage, 'title')
  41
  42         thumbnail = self._search_regex(
  43             r"preview_url\s*:\s*'([^']+)'",
  44             webpage, 'thumbnail', fatal=False)
  45
  46         categories = self._html_search_meta(
  47             'keywords', webpage, 'categories', default='').split(',')
  48
  49         duration = parse_duration(self._search_regex(
  50             r'<span>Duration:</span>\s*(\d+:\d+)',
  51             webpage, 'duration', fatal=False))
  52
  53         view_count = int_or_none(self._html_search_regex(
  54             r'<div class="video_views">\s*(\d+)',
  55             webpage, 'view count', fatal=False))
  56         like_count = int_or_none(self._search_regex(
  57             r'>\s*Likes? <b>\((\d+)\)',
  58             webpage, 'like count', fatal=False))
  59         dislike_count = int_or_none(self._search_regex(
  60             r'>\s*Dislike <b>\((\d+)\)</b>',
  61             webpage, 'dislike count', fatal=False))
  62
  63         age_limit = self._rta_search(webpage)
  64
  65         return {
  66             'id': video_id,
  67             'display_id': display_id,
  68             'url': video_url,
  69             'title': title,
  70             'thumbnail': thumbnail,
  71             'categories': categories,
  72             'duration': duration,
  73             'view_count': view_count,
  74             'like_count': like_count,
  75             'dislike_count': dislike_count,
  76             'age_limit': age_limit,
  77         }