youtube_dl/extractor/porncom.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_urlparse
   7 from ..utils import (
   8     int_or_none,
   9     js_to_json,
  10     parse_filesize,
  11     str_to_int,
  12 )
  13
  14
  15 class PornComIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:[a-zA-Z]+\.)?porn\.com/videos/(?:(?P<display_id>[^/]+)-)?(?P<id>\d+)'
  17     _TESTS = [{
  18         'url': 'http://www.porn.com/videos/teen-grabs-a-dildo-and-fucks-her-pussy-live-on-1hottie-i-rec-2603339',
  19         'md5': '3f30ce76267533cd12ba999263156de7',
  20         'info_dict': {
  21             'id': '2603339',
  22             'display_id': 'teen-grabs-a-dildo-and-fucks-her-pussy-live-on-1hottie-i-rec',
  23             'ext': 'mp4',
  24             'title': 'Teen grabs a dildo and fucks her pussy live on 1hottie, I rec',
  25             'thumbnail': r're:^https?://.*\.jpg$',
  26             'duration': 551,
  27             'view_count': int,
  28             'age_limit': 18,
  29             'categories': list,
  30             'tags': list,
  31         },
  32     }, {
  33         'url': 'http://se.porn.com/videos/marsha-may-rides-seth-on-top-of-his-thick-cock-2658067',
  34         'only_matching': True,
  35     }]
  36
  37     def _real_extract(self, url):
  38         mobj = re.match(self._VALID_URL, url)
  39         video_id = mobj.group('id')
  40         display_id = mobj.group('display_id') or video_id
  41
  42         webpage = self._download_webpage(url, display_id)
  43
  44         config = self._parse_json(
  45             self._search_regex(
  46                 (r'=\s*({.+?})\s*;\s*v1ar\b',
  47                  r'=\s*({.+?})\s*,\s*[\da-zA-Z_]+\s*='),
  48                 webpage, 'config', default='{}'),
  49             display_id, transform_source=js_to_json, fatal=False)
  50
  51         if config:
  52             title = config['title']
  53             formats = [{
  54                 'url': stream['url'],
  55                 'format_id': stream.get('id'),
  56                 'height': int_or_none(self._search_regex(
  57                     r'^(\d+)[pP]', stream.get('id') or '', 'height', default=None))
  58             } for stream in config['streams'] if stream.get('url')]
  59             thumbnail = (compat_urlparse.urljoin(
  60                 config['thumbCDN'], config['poster'])
  61                 if config.get('thumbCDN') and config.get('poster') else None)
  62             duration = int_or_none(config.get('length'))
  63         else:
  64             title = self._search_regex(
  65                 (r'<title>([^<]+)</title>', r'<h1[^>]*>([^<]+)</h1>'),
  66                 webpage, 'title')
  67             formats = [{
  68                 'url': compat_urlparse.urljoin(url, format_url),
  69                 'format_id': '%sp' % height,
  70                 'height': int(height),
  71                 'filesize_approx': parse_filesize(filesize),
  72             } for format_url, height, filesize in re.findall(
  73                 r'<a[^>]+href="(/download/[^"]+)">[^<]*?(\d+)p<span[^>]*>(\d+\s*[a-zA-Z]+)<',
  74                 webpage)]
  75             thumbnail = None
  76             duration = None
  77
  78         self._sort_formats(formats)
  79
  80         view_count = str_to_int(self._search_regex(
  81             (r'Views:\s*</span>\s*<span>\s*([\d,.]+)',
  82              r'class=["\']views["\'][^>]*><p>([\d,.]+)'), webpage,
  83             'view count', fatal=False))
  84
  85         def extract_list(kind):
  86             s = self._search_regex(
  87                 (r'(?s)%s:\s*</span>\s*<span>(.+?)</span>' % kind.capitalize(),
  88                  r'(?s)<p[^>]*>%s:(.+?)</p>' % kind.capitalize()),
  89                 webpage, kind, fatal=False)
  90             return re.findall(r'<a[^>]+>([^<]+)</a>', s or '')
  91
  92         return {
  93             'id': video_id,
  94             'display_id': display_id,
  95             'title': title,
  96             'thumbnail': thumbnail,
  97             'duration': duration,
  98             'view_count': view_count,
  99             'formats': formats,
 100             'age_limit': 18,
 101             'categories': extract_list('categories'),
 102             'tags': extract_list('tags'),
 103         }