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