Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/pornflip.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import (
   6     compat_parse_qs,
   7     compat_str,
   8 )
   9 from ..utils import (
  10     int_or_none,
  11     try_get,
  12     unified_timestamp,
  13 )
  14
  15
  16 class PornFlipIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?pornflip\.com/(?:v|embed)/(?P<id>[0-9A-Za-z-]{11})'
  18     _TESTS = [{
  19         'url': 'https://www.pornflip.com/v/wz7DfNhMmep',
  20         'md5': '98c46639849145ae1fd77af532a9278c',
  21         'info_dict': {
  22             'id': 'wz7DfNhMmep',
  23             'ext': 'mp4',
  24             'title': '2 Amateurs swallow make his dream cumshots true',
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26             'duration': 112,
  27             'timestamp': 1481655502,
  28             'upload_date': '20161213',
  29             'uploader_id': '106786',
  30             'uploader': 'figifoto',
  31             'view_count': int,
  32             'age_limit': 18,
  33         }
  34     }, {
  35         'url': 'https://www.pornflip.com/embed/wz7DfNhMmep',
  36         'only_matching': True,
  37     }, {
  38         'url': 'https://www.pornflip.com/v/EkRD6-vS2-s',
  39         'only_matching': True,
  40     }, {
  41         'url': 'https://www.pornflip.com/embed/EkRD6-vS2-s',
  42         'only_matching': True,
  43     }]
  44
  45     def _real_extract(self, url):
  46         video_id = self._match_id(url)
  47
  48         webpage = self._download_webpage(
  49             'https://www.pornflip.com/v/%s' % video_id, video_id)
  50
  51         flashvars = compat_parse_qs(self._search_regex(
  52             r'<embed[^>]+flashvars=(["\'])(?P<flashvars>(?:(?!\1).)+)\1',
  53             webpage, 'flashvars', group='flashvars'))
  54
  55         title = flashvars['video_vars[title]'][0]
  56
  57         def flashvar(kind):
  58             return try_get(
  59                 flashvars, lambda x: x['video_vars[%s]' % kind][0], compat_str)
  60
  61         formats = []
  62         for key, value in flashvars.items():
  63             if not (value and isinstance(value, list)):
  64                 continue
  65             format_url = value[0]
  66             if key == 'video_vars[hds_manifest]':
  67                 formats.extend(self._extract_mpd_formats(
  68                     format_url, video_id, mpd_id='dash', fatal=False))
  69                 continue
  70             height = self._search_regex(
  71                 r'video_vars\[video_urls\]\[(\d+)', key, 'height', default=None)
  72             if not height:
  73                 continue
  74             formats.append({
  75                 'url': format_url,
  76                 'format_id': 'http-%s' % height,
  77                 'height': int_or_none(height),
  78             })
  79         self._sort_formats(formats)
  80
  81         uploader = self._html_search_regex(
  82             (r'<span[^>]+class="name"[^>]*>\s*<a[^>]+>\s*<strong>(?P<uploader>[^<]+)',
  83              r'<meta[^>]+content=(["\'])[^>]*\buploaded by (?P<uploader>.+?)\1'),
  84             webpage, 'uploader', fatal=False, group='uploader')
  85
  86         return {
  87             'id': video_id,
  88             'formats': formats,
  89             'title': title,
  90             'thumbnail': flashvar('big_thumb'),
  91             'duration': int_or_none(flashvar('duration')),
  92             'timestamp': unified_timestamp(self._html_search_meta(
  93                 'uploadDate', webpage, 'timestamp')),
  94             'uploader_id': flashvar('author_id'),
  95             'uploader': uploader,
  96             'view_count': int_or_none(flashvar('views')),
  97             'age_limit': 18,
  98         }