yt_dlp/extractor/pornovoisines.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     float_or_none,
   4     int_or_none,
   5     unified_strdate,
   6 )
   7
   8
   9 class PornoVoisinesIE(InfoExtractor):
  10     _WORKING = False
  11     _VALID_URL = r'https?://(?:www\.)?pornovoisines\.com/videos/show/(?P<id>\d+)/(?P<display_id>[^/.]+)'
  12
  13     _TEST = {
  14         'url': 'http://www.pornovoisines.com/videos/show/919/recherche-appartement.html',
  15         'md5': '6f8aca6a058592ab49fe701c8ba8317b',
  16         'info_dict': {
  17             'id': '919',
  18             'display_id': 'recherche-appartement',
  19             'ext': 'mp4',
  20             'title': 'Recherche appartement',
  21             'description': 'md5:fe10cb92ae2dd3ed94bb4080d11ff493',
  22             'thumbnail': r're:^https?://.*\.jpg$',
  23             'upload_date': '20140925',
  24             'duration': 120,
  25             'view_count': int,
  26             'average_rating': float,
  27             'categories': ['Débutante', 'Débutantes', 'Scénario', 'Sodomie'],
  28             'age_limit': 18,
  29             'subtitles': {
  30                 'fr': [{
  31                     'ext': 'vtt',
  32                 }]
  33             },
  34         }
  35     }
  36
  37     def _real_extract(self, url):
  38         mobj = self._match_valid_url(url)
  39         video_id = mobj.group('id')
  40         display_id = mobj.group('display_id')
  41
  42         settings_url = self._download_json(
  43             'http://www.pornovoisines.com/api/video/%s/getsettingsurl/' % video_id,
  44             video_id, note='Getting settings URL')['video_settings_url']
  45         settings = self._download_json(settings_url, video_id)['data']
  46
  47         formats = []
  48         for kind, data in settings['variants'].items():
  49             if kind == 'HLS':
  50                 formats.extend(self._extract_m3u8_formats(
  51                     data, video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls'))
  52             elif kind == 'MP4':
  53                 for item in data:
  54                     formats.append({
  55                         'url': item['url'],
  56                         'height': item.get('height'),
  57                         'bitrate': item.get('bitrate'),
  58                     })
  59
  60         webpage = self._download_webpage(url, video_id)
  61
  62         title = self._og_search_title(webpage)
  63         description = self._og_search_description(webpage)
  64
  65         # The webpage has a bug - there's no space between "thumb" and src=
  66         thumbnail = self._html_search_regex(
  67             r'<img[^>]+class=([\'"])thumb\1[^>]*src=([\'"])(?P<url>[^"]+)\2',
  68             webpage, 'thumbnail', fatal=False, group='url')
  69
  70         upload_date = unified_strdate(self._search_regex(
  71             r'Le\s*<b>([\d/]+)', webpage, 'upload date', fatal=False))
  72         duration = settings.get('main', {}).get('duration')
  73         view_count = int_or_none(self._search_regex(
  74             r'(\d+) vues', webpage, 'view count', fatal=False))
  75         average_rating = self._search_regex(
  76             r'Note\s*:\s*(\d+(?:,\d+)?)', webpage, 'average rating', fatal=False)
  77         if average_rating:
  78             average_rating = float_or_none(average_rating.replace(',', '.'))
  79
  80         categories = self._html_search_regex(
  81             r'(?s)Catégories\s*:\s*<b>(.+?)</b>', webpage, 'categories', fatal=False)
  82         if categories:
  83             categories = [category.strip() for category in categories.split(',')]
  84
  85         subtitles = {'fr': [{
  86             'url': subtitle,
  87         } for subtitle in settings.get('main', {}).get('vtt_tracks', {}).values()]}
  88
  89         return {
  90             'id': video_id,
  91             'display_id': display_id,
  92             'formats': formats,
  93             'title': title,
  94             'description': description,
  95             'thumbnail': thumbnail,
  96             'upload_date': upload_date,
  97             'duration': duration,
  98             'view_count': view_count,
  99             'average_rating': average_rating,
 100             'categories': categories,
 101             'age_limit': 18,
 102             'subtitles': subtitles,
 103         }