yt_dlp/extractor/eporner.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     ExtractorError,
   4     encode_base_n,
   5     get_elements_by_class,
   6     int_or_none,
   7     join_nonempty,
   8     merge_dicts,
   9     parse_duration,
  10     str_to_int,
  11     url_or_none,
  12 )
  13
  14
  15 class EpornerIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?eporner\.com/(?:(?:hd-porn|embed)/|video-)(?P<id>\w+)(?:/(?P<display_id>[\w-]+))?'
  17     _TESTS = [{
  18         'url': 'http://www.eporner.com/hd-porn/95008/Infamous-Tiffany-Teen-Strip-Tease-Video/',
  19         'md5': '39d486f046212d8e1b911c52ab4691f8',
  20         'info_dict': {
  21             'id': 'qlDUmNsj6VS',
  22             'display_id': 'Infamous-Tiffany-Teen-Strip-Tease-Video',
  23             'ext': 'mp4',
  24             'title': 'Infamous Tiffany Teen Strip Tease Video',
  25             'description': 'md5:764f39abf932daafa37485eb46efa152',
  26             'timestamp': 1232520922,
  27             'upload_date': '20090121',
  28             'duration': 1838,
  29             'view_count': int,
  30             'age_limit': 18,
  31         },
  32         'params': {
  33             'proxy': '127.0.0.1:8118'
  34         }
  35     }, {
  36         # New (May 2016) URL layout
  37         'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0/Star-Wars-XXX-Parody/',
  38         'only_matching': True,
  39     }, {
  40         'url': 'http://www.eporner.com/hd-porn/3YRUtzMcWn0',
  41         'only_matching': True,
  42     }, {
  43         'url': 'http://www.eporner.com/embed/3YRUtzMcWn0',
  44         'only_matching': True,
  45     }, {
  46         'url': 'https://www.eporner.com/video-FJsA19J3Y3H/one-of-the-greats/',
  47         'only_matching': True,
  48     }]
  49
  50     def _real_extract(self, url):
  51         mobj = self._match_valid_url(url)
  52         video_id = mobj.group('id')
  53         display_id = mobj.group('display_id') or video_id
  54
  55         webpage, urlh = self._download_webpage_handle(url, display_id)
  56
  57         video_id = self._match_id(urlh.url)
  58
  59         hash = self._search_regex(
  60             r'hash\s*[:=]\s*["\']([\da-f]{32})', webpage, 'hash')
  61
  62         title = self._og_search_title(webpage, default=None) or self._html_search_regex(
  63             r'<title>(.+?) - EPORNER', webpage, 'title')
  64
  65         # Reverse engineered from vjs.js
  66         def calc_hash(s):
  67             return ''.join((encode_base_n(int(s[lb:lb + 8], 16), 36) for lb in range(0, 32, 8)))
  68
  69         video = self._download_json(
  70             'http://www.eporner.com/xhr/video/%s' % video_id,
  71             display_id, note='Downloading video JSON',
  72             query={
  73                 'hash': calc_hash(hash),
  74                 'device': 'generic',
  75                 'domain': 'www.eporner.com',
  76                 'fallback': 'false',
  77             })
  78
  79         if video.get('available') is False:
  80             raise ExtractorError(
  81                 '%s said: %s' % (self.IE_NAME, video['message']), expected=True)
  82
  83         sources = video['sources']
  84
  85         formats = []
  86         has_av1 = bool(get_elements_by_class('download-av1', webpage))
  87         for kind, formats_dict in sources.items():
  88             if not isinstance(formats_dict, dict):
  89                 continue
  90             for format_id, format_dict in formats_dict.items():
  91                 if not isinstance(format_dict, dict):
  92                     continue
  93                 src = url_or_none(format_dict.get('src'))
  94                 if not src or not src.startswith('http'):
  95                     continue
  96                 if kind == 'hls':
  97                     formats.extend(self._extract_m3u8_formats(
  98                         src, display_id, 'mp4', entry_protocol='m3u8_native',
  99                         m3u8_id=kind, fatal=False))
 100                 else:
 101                     height = int_or_none(self._search_regex(
 102                         r'(\d+)[pP]', format_id, 'height', default=None))
 103                     fps = int_or_none(self._search_regex(
 104                         r'(\d+)fps', format_id, 'fps', default=None))
 105
 106                     formats.append({
 107                         'url': src,
 108                         'format_id': format_id,
 109                         'height': height,
 110                         'fps': fps,
 111                     })
 112                     if has_av1:
 113                         formats.append({
 114                             'url': src.replace('.mp4', '-av1.mp4'),
 115                             'format_id': join_nonempty('av1', format_id),
 116                             'height': height,
 117                             'fps': fps,
 118                             'vcodec': 'av1',
 119                         })
 120
 121         json_ld = self._search_json_ld(webpage, display_id, default={})
 122
 123         duration = parse_duration(self._html_search_meta(
 124             'duration', webpage, default=None))
 125         view_count = str_to_int(self._search_regex(
 126             r'id=["\']cinemaviews1["\'][^>]*>\s*([0-9,]+)',
 127             webpage, 'view count', default=None))
 128
 129         return merge_dicts(json_ld, {
 130             'id': video_id,
 131             'display_id': display_id,
 132             'title': title,
 133             'duration': duration,
 134             'view_count': view_count,
 135             'formats': formats,
 136             'age_limit': 18,
 137         })