yt_dlp/extractor/alphaporno.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     parse_duration,
   5     parse_filesize,
   6     parse_iso8601,
   7 )
   8
   9
  10 class AlphaPornoIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?alphaporno\.com/videos/(?P<id>[^/]+)'
  12     _TEST = {
  13         'url': 'http://www.alphaporno.com/videos/sensual-striptease-porn-with-samantha-alexandra/',
  14         'md5': 'feb6d3bba8848cd54467a87ad34bd38e',
  15         'info_dict': {
  16             'id': '258807',
  17             'display_id': 'sensual-striptease-porn-with-samantha-alexandra',
  18             'ext': 'mp4',
  19             'title': 'Sensual striptease porn with Samantha Alexandra',
  20             'thumbnail': r're:https?://.*\.jpg$',
  21             'timestamp': 1418694611,
  22             'upload_date': '20141216',
  23             'duration': 387,
  24             'filesize_approx': 54120000,
  25             'tbr': 1145,
  26             'categories': list,
  27             'age_limit': 18,
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         display_id = self._match_id(url)
  33
  34         webpage = self._download_webpage(url, display_id)
  35
  36         video_id = self._search_regex(
  37             r"video_id\s*:\s*'([^']+)'", webpage, 'video id', default=None)
  38
  39         video_url = self._search_regex(
  40             r"video_url\s*:\s*'([^']+)'", webpage, 'video url')
  41         ext = self._html_search_meta(
  42             'encodingFormat', webpage, 'ext', default='.mp4')[1:]
  43
  44         title = self._search_regex(
  45             [r'<meta content="([^"]+)" itemprop="description">',
  46              r'class="title" itemprop="name">([^<]+)<'],
  47             webpage, 'title')
  48         thumbnail = self._html_search_meta('thumbnail', webpage, 'thumbnail')
  49         timestamp = parse_iso8601(self._html_search_meta(
  50             'uploadDate', webpage, 'upload date'))
  51         duration = parse_duration(self._html_search_meta(
  52             'duration', webpage, 'duration'))
  53         filesize_approx = parse_filesize(self._html_search_meta(
  54             'contentSize', webpage, 'file size'))
  55         bitrate = int_or_none(self._html_search_meta(
  56             'bitrate', webpage, 'bitrate'))
  57         categories = self._html_search_meta(
  58             'keywords', webpage, 'categories', default='').split(',')
  59
  60         age_limit = self._rta_search(webpage)
  61
  62         return {
  63             'id': video_id,
  64             'display_id': display_id,
  65             'url': video_url,
  66             'ext': ext,
  67             'title': title,
  68             'thumbnail': thumbnail,
  69             'timestamp': timestamp,
  70             'duration': duration,
  71             'filesize_approx': filesize_approx,
  72             'tbr': bitrate,
  73             'categories': categories,
  74             'age_limit': age_limit,
  75         }