_ Git - youtube-dl/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 (
   8     int_or_none,
   9     js_to_json,
  10     qualities,
  11     determine_ext,
  12 )
  13
  14
  15 class PornHdIE(InfoExtractor):
  16     _VALID_URL = r'http://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
  17     _TEST = {
  18         'url': 'http://www.pornhd.com/videos/1962/sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
  19         'md5': '956b8ca569f7f4d8ec563e2c41598441',
  20         'info_dict': {
  21             'id': '1962',
  22             'display_id': 'sierra-day-gets-his-cum-all-over-herself-hd-porn-video',
  23             'ext': 'mp4',
  24             'title': 'Sierra loves doing laundry',
  25             'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
  26             'thumbnail': 're:^https?://.*\.jpg',
  27             'view_count': int,
  28             'age_limit': 18,
  29         }
  30     }
  31
  32     def _real_extract(self, url):
  33         mobj = re.match(self._VALID_URL, url)
  34         video_id = mobj.group('id')
  35         display_id = mobj.group('display_id')
  36
  37         webpage = self._download_webpage(url, display_id or video_id)
  38
  39         title = self._html_search_regex(
  40             r'<title>(.+) porn HD.+?</title>', webpage, 'title')
  41         description = self._html_search_regex(
  42             r'<div class="description">([^<]+)</div>', webpage, 'description', fatal=False)
  43         view_count = int_or_none(self._html_search_regex(
  44             r'(\d+) views\s*</span>', webpage, 'view count', fatal=False))
  45         thumbnail = self._search_regex(
  46             r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
  47
  48         quality = qualities(['sd', 'hd'])
  49         sources = json.loads(js_to_json(self._search_regex(
  50             r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}\);", webpage, 'sources')))
  51         formats = []
  52         for container, s in sources.items():
  53             for qname, video_url in s.items():
  54                 formats.append({
  55                     'url': video_url,
  56                     'container': container,
  57                     'format_id': '%s-%s' % (container, qname),
  58                     'quality': quality(qname),
  59                 })
  60         self._sort_formats(formats)
  61
  62         return {
  63             'id': video_id,
  64             'display_id': display_id,
  65             'title': title,
  66             'description': description,
  67             'thumbnail': thumbnail,
  68             'view_count': view_count,
  69             'formats': formats,
  70             'age_limit': 18,
  71         }