_ Git - youtube-dl/blob - youtube_dl/extractor/youporn.py

   1 from __future__ import unicode_literals
   2
   3
   4 import json
   5 import re
   6 import sys
   7 import datetime
   8
   9 from .common import InfoExtractor
  10 from ..compat import (
  11     compat_urllib_parse_urlparse,
  12     compat_urllib_request,
  13 )
  14 from ..utils import (
  15     ExtractorError,
  16     unescapeHTML,
  17     unified_strdate,
  18 )
  19 from ..aes import (
  20     aes_decrypt_text
  21 )
  22
  23
  24 class YouPornIE(InfoExtractor):
  25     _VALID_URL = r'^(?P<proto>https?://)(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'
  26     _TEST = {
  27         'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
  28         'info_dict': {
  29             'id': '505835',
  30             'ext': 'mp4',
  31             'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
  32             'description': 'Watch Sex Ed: Is It Safe To Masturbate Daily? at YouPorn.com - YouPorn is the biggest free porn tube site on the net!',
  33             'uploader': 'Ask Dan And Jennifer',
  34             'thumbnail': 'http://cdn5.image.youporn.phncdn.com/201012/17/505835/640x480/8/sex-ed-is-it-safe-to-masturbate-daily-8.jpg',
  35             'date': '20101221',
  36             'age_limit': 18,
  37         }
  38     }
  39
  40     def _real_extract(self, url):
  41         mobj = re.match(self._VALID_URL, url)
  42         video_id = mobj.group('videoid')
  43         url = mobj.group('proto') + 'www.' + mobj.group('url')
  44
  45         req = compat_urllib_request.Request(url)
  46         req.add_header('Cookie', 'age_verified=1')
  47         webpage = self._download_webpage(req, video_id)
  48         age_limit = self._rta_search(webpage)
  49
  50         self.report_extraction(video_id)
  51         video_title = self._html_search_regex(r'page_params.video_title = \'(.+?)\';', webpage, 'video URL', fatal=False)
  52         video_description = self._html_search_meta('description', webpage, 'video DESC', fatal=False)
  53         video_thumbnail = self._html_search_regex(r'page_params.imageurl\t=\t"(.+?)";', webpage, 'video THUMB', fatal=False)
  54         video_uploader = self._html_search_regex(r"<div class=\'videoInfoBy\'>By:</div>\n<a href=\"[^>]+\">(.+?)</a>", webpage, 'video UPLOADER', fatal=False)
  55         video_date = self._html_search_regex(r"<div class='videoInfoTime'>\n<i class='icon-clock'></i> (.+?)\n</div>", webpage, 'video DATE', fatal=False)
  56         video_date = datetime.datetime.strptime(video_date, '%B %d, %Y').strftime('%Y%m%d')
  57
  58         # Get all of the links from the page
  59         DOWNLOAD_LIST_RE = r'(?s)sources: {\n(?P<download_list>.*?)}'
  60         download_list_html = self._search_regex(DOWNLOAD_LIST_RE, webpage, 'download list').strip()
  61         LINK_RE = r': \'(.+?)\','
  62         links = re.findall(LINK_RE, download_list_html)
  63
  64         # Get all encrypted links
  65         encrypted_links = re.findall(r'page_params.encryptedQuality[0-9]{3,4}URL\s=\s\'([a-zA-Z0-9+/]+={0,2})\';', webpage)
  66         for encrypted_link in encrypted_links:
  67             link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
  68             # it's unclear if encryted links still differ from normal ones, so only include in links array if it's unique
  69             if link not in links:
  70                 links.append(link)
  71
  72         formats = []
  73         for link in links:
  74             # A link looks like this:
  75             # http://cdn2b.public.youporn.phncdn.com/201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4?rs=200&ri=2500&s=1445599900&e=1445773500&h=5345d19ce9944ec52eb167abf24af248
  76             # A path looks like this:
  77             # 201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
  78             video_url = unescapeHTML(link)
  79             path = compat_urllib_parse_urlparse(video_url).path
  80             format_parts = path.split('/')[4].split('_')[:2]
  81
  82             dn = compat_urllib_parse_urlparse(video_url).netloc.partition('.')[0]
  83
  84             resolution = format_parts[0]
  85             height = int(resolution[:-len('p')])
  86             bitrate = int(format_parts[1][:-len('k')])
  87             format = '-'.join(format_parts) + '-' + dn
  88
  89             formats.append({
  90                 'url': video_url,
  91                 'format': format,
  92                 'format_id': format,
  93                 'height': height,
  94                 'tbr': bitrate,
  95                 'resolution': resolution,
  96             })
  97
  98         self._sort_formats(formats)
  99
 100         if not formats:
 101             raise ExtractorError('ERROR: no known formats available for video')
 102
 103         return {
 104             'id': video_id,
 105             'title': video_title,
 106             'description': video_description,
 107             'thumbnail': video_thumbnail,
 108             'uploader': video_uploader,
 109             'date': video_date,
 110             'age_limit': age_limit,
 111             'formats': formats,
 112         }