yt_dlp/extractor/hellporno.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     merge_dicts,
   5     remove_end,
   6     unified_timestamp,
   7 )
   8
   9
  10 class HellPornoIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?hellporno\.(?:com/videos|net/v)/(?P<id>[^/]+)'
  12     _TESTS = [{
  13         'url': 'http://hellporno.com/videos/dixie-is-posing-with-naked-ass-very-erotic/',
  14         'md5': 'f0a46ebc0bed0c72ae8fe4629f7de5f3',
  15         'info_dict': {
  16             'id': '149116',
  17             'display_id': 'dixie-is-posing-with-naked-ass-very-erotic',
  18             'ext': 'mp4',
  19             'title': 'Dixie is posing with naked ass very erotic',
  20             'description': 'md5:9a72922749354edb1c4b6e540ad3d215',
  21             'categories': list,
  22             'thumbnail': r're:https?://.*\.jpg$',
  23             'duration': 240,
  24             'timestamp': 1398762720,
  25             'upload_date': '20140429',
  26             'view_count': int,
  27             'age_limit': 18,
  28         },
  29     }, {
  30         'url': 'http://hellporno.net/v/186271/',
  31         'only_matching': True,
  32     }]
  33
  34     def _real_extract(self, url):
  35         display_id = self._match_id(url)
  36
  37         webpage = self._download_webpage(url, display_id)
  38
  39         title = remove_end(self._html_extract_title(webpage), ' - Hell Porno')
  40
  41         info = self._parse_html5_media_entries(url, webpage, display_id)[0]
  42
  43         video_id = self._search_regex(
  44             (r'chs_object\s*=\s*["\'](\d+)',
  45              r'params\[["\']video_id["\']\]\s*=\s*(\d+)'), webpage, 'video id',
  46             default=display_id)
  47         description = self._search_regex(
  48             r'class=["\']desc_video_view_v2[^>]+>([^<]+)', webpage,
  49             'description', fatal=False)
  50         categories = [
  51             c.strip()
  52             for c in self._html_search_meta(
  53                 'keywords', webpage, 'categories', default='').split(',')
  54             if c.strip()]
  55         duration = int_or_none(self._og_search_property(
  56             'video:duration', webpage, fatal=False))
  57         timestamp = unified_timestamp(self._og_search_property(
  58             'video:release_date', webpage, fatal=False))
  59         view_count = int_or_none(self._search_regex(
  60             r'>Views\s+(\d+)', webpage, 'view count', fatal=False))
  61
  62         return merge_dicts(info, {
  63             'id': video_id,
  64             'display_id': display_id,
  65             'title': title,
  66             'description': description,
  67             'categories': categories,
  68             'duration': duration,
  69             'timestamp': timestamp,
  70             'view_count': view_count,
  71             'age_limit': 18,
  72         })