Raphaël G. Git Repositories - youtubedl/blob - 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._og_search_title(webpage)
  31         TITLE_SUFFIX = ' porn HD Video | PornHD.com '
  32         if title.endswith(TITLE_SUFFIX):
  33             title = title[:-len(TITLE_SUFFIX)]
  34
  35         description = self._html_search_regex(
  36             r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
  37         view_count = int_or_none(self._html_search_regex(
  38             r'(\d+) views       </span>', webpage, 'view count', fatal=False))
  39
  40         formats = [
  41             {
  42                 'url': format_url,
  43                 'ext': format.lower(),
  44                 'format_id': '%s-%s' % (format.lower(), quality.lower()),
  45                 'quality': 1 if quality.lower() == 'high' else 0,
  46             } for format, quality, format_url in re.findall(
  47                 r'var __video([\da-zA-Z]+?)(Low|High)StreamUrl = \'(http://.+?)\?noProxy=1\'', webpage)
  48         ]
  49
  50         mobj = re.search(r'flashVars = (?P<flashvars>{.+?});', webpage)
  51         if mobj:
  52             flashvars = json.loads(mobj.group('flashvars'))
  53             formats.extend([
  54                 {
  55                     'url': flashvars['hashlink'].replace('?noProxy=1', ''),
  56                     'ext': 'flv',
  57                     'format_id': 'flv-low',
  58                     'quality': 0,
  59                 },
  60                 {
  61                     'url': flashvars['hd'].replace('?noProxy=1', ''),
  62                     'ext': 'flv',
  63                     'format_id': 'flv-high',
  64                     'quality': 1,
  65                 }
  66             ])
  67             thumbnail = flashvars['urlWallpaper']
  68         else:
  69             thumbnail = self._og_search_thumbnail(webpage)
  70
  71         self._sort_formats(formats)
  72
  73         return {
  74             'id': video_id,
  75             'title': title,
  76             'description': description,
  77             'thumbnail': thumbnail,
  78             'view_count': view_count,
  79             'formats': formats,
  80             'age_limit': 18,
  81         }