youtube_dl/extractor/pornhd.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import int_or_none
   8
   9
  10 class PornHdIE(InfoExtractor):
  11     _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)'
  12     _TEST = {
  13         'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
  14         'md5': '956b8ca569f7f4d8ec563e2c41598441',
  15         'info_dict': {
  16             'id': '1962',
  17             'ext': 'mp4',
  18             'title': 'Sierra loves doing laundry',
  19             'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
  20             'age_limit': 18,
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         mobj = re.match(self._VALID_URL, url)
  26         video_id = mobj.group('id')
  27
  28         webpage = self._download_webpage(url, video_id)
  29
  30         title = self._html_search_regex(
  31             r'<title>(.+) porn HD.+?</title>', webpage, 'title')
  32         description = self._html_search_regex(
  33             r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
  34         view_count = int_or_none(self._html_search_regex(
  35             r'(\d+) views\s*</span>', webpage, 'view count', fatal=False))
  36
  37         videos = re.findall(
  38             r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage)
  39
  40         mobj = re.search(r'flashVars = (?P<flashvars>{.+?});', webpage)
  41         if mobj:
  42             flashvars = json.loads(mobj.group('flashvars'))
  43             for key, quality in [('hashlink', 'low'), ('hd', 'high')]:
  44                 redirect_url = flashvars.get(key)
  45                 if redirect_url:
  46                     videos.append(('flv', quality, redirect_url))
  47             thumbnail = flashvars['urlWallpaper']
  48         else:
  49             thumbnail = self._og_search_thumbnail(webpage)
  50
  51         formats = []
  52         for format_, quality, redirect_url in videos:
  53             format_id = '%s-%s' % (format_.lower(), quality.lower())
  54             video_url = self._download_webpage(
  55                 redirect_url, video_id, 'Downloading %s video link' % format_id, fatal=False)
  56             if not video_url:
  57                 continue
  58             formats.append({
  59                 'url': video_url,
  60                 'ext': format_.lower(),
  61                 'format_id': format_id,
  62                 'quality': 1 if quality.lower() == 'high' else 0,
  63             })
  64         self._sort_formats(formats)
  65
  66         return {
  67             'id': video_id,
  68             'title': title,
  69             'description': description,
  70             'thumbnail': thumbnail,
  71             'view_count': view_count,
  72             'formats': formats,
  73             'age_limit': 18,
  74         }