youtube_dl/extractor/spankwire.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_urllib_parse_unquote,
   8     compat_urllib_parse_urlparse,
   9     compat_urllib_request,
  10 )
  11 from ..utils import (
  12     str_to_int,
  13     unified_strdate,
  14 )
  15 from ..aes import aes_decrypt_text
  16
  17
  18 class SpankwireIE(InfoExtractor):
  19     _VALID_URL = r'https?://(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
  20     _TESTS = [{
  21                 'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
  22                 'md5': '8bbfde12b101204b39e4b9fe7eb67095',
  23                     'info_dict': {
  24                                     'id': '103545',
  25                                     'ext': 'mp4',
  26                                     'title': 'Buckcherry`s X Rated Music Video Crazy Bitch',
  27                                     'description': 'Crazy Bitch X rated music video.',
  28                                     'uploader': 'oreusz',
  29                                     'uploader_id': '124697',
  30                                     'upload_date': '20070507',
  31                                     'age_limit': 18,
  32                     }
  33               },
  34               {
  35                 'url': 'http://www.spankwire.com/Titcums-Compiloation-I/video1921551/',
  36                 'md5': '09b3c20833308b736ae8902db2f8d7e6',
  37                     'info_dict': {
  38                                     'id': '1921551',
  39                                     'ext': 'mp4',
  40                                     'title': 'Titcums Compiloation I',
  41                                     'description': 'cum on tits',
  42                                     'uploader': 'dannyh78999',
  43                                     'uploader_id': '3056053',
  44                                     'upload_date': '20150822',
  45                                     'age_limit': 18,
  46                     }
  47               }]
  48
  49     def _real_extract(self, url):
  50         mobj = re.match(self._VALID_URL, url)
  51         video_id = mobj.group('videoid')
  52         url = 'http://www.' + mobj.group('url')
  53
  54         req = compat_urllib_request.Request(url)
  55         req.add_header('Cookie', 'age_verified=1')
  56         webpage = self._download_webpage(req, video_id)
  57
  58         title = self._html_search_regex(
  59             r'<h1>([^<]+)', webpage, 'title')
  60         description = self._html_search_regex(
  61             r'(?s)<div\s+id="descriptionContent">(.+?)</div>',
  62             webpage, 'description', fatal=False)
  63         thumbnail = self._html_search_regex(
  64             r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']',
  65             webpage, 'thumbnail', fatal=False)
  66
  67         uploader = self._html_search_regex(
  68             r'by:\s*<a [^>]*>(.+?)</a>',
  69             webpage, 'uploader', fatal=False)
  70         uploader_id = self._html_search_regex(
  71             r'by:\s*<a href="/user/viewProfile\?.*?UserId=(\d+).*?"',
  72             webpage, 'uploader id', fatal=False)
  73         upload_date = unified_strdate(self._html_search_regex(
  74             r'</a> on (.+?) at \d+:\d+',
  75             webpage, 'upload date', fatal=False))
  76
  77         view_count = str_to_int(self._html_search_regex(
  78             r'<div id="viewsCounter"><span>([\d,\.]+)</span> views</div>',
  79             webpage, 'view count', fatal=False))
  80         comment_count = str_to_int(self._html_search_regex(
  81             r'<span\s+id="spCommentCount"[^>]*>([\d,\.]+)</span>',
  82             webpage, 'comment count', fatal=False))
  83
  84         video_urls = list(map(
  85             compat_urllib_parse_unquote,
  86             re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage)))
  87         if webpage.find('flashvars\.encrypted = "true"') != -1:
  88             password = self._search_regex(
  89                 r'flashvars\.video_title = "([^"]+)',
  90                 webpage, 'password').replace('+', ' ')
  91             video_urls = list(map(
  92                 lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'),
  93                 video_urls))
  94
  95         formats = []
  96         for video_url in video_urls:
  97             path = compat_urllib_parse_urlparse(video_url).path
  98             format = path.split('/')[4].split('_')[:2]
  99             if format[0] == 'mp4':
 100                 format_id, quality = format
 101                 format = "-".join(format)
 102                 if quality == 'normal':
 103                     height = 180
 104                 elif quality == 'high':
 105                     height = 240
 106                 elif quality == 'ultra':
 107                     height = 480
 108                 elif quality == '720p':
 109                     height = 720
 110                 formats.append({
 111                     'url': video_url,
 112                     'format': format,
 113                     'height': height,
 114                     'format_id': format,
 115                 })
 116             else:
 117                 resolution, bitrate_str = format
 118                 format = "-".join(format)
 119                 height = int(resolution.rstrip('Pp'))
 120                 tbr = int(bitrate_str.rstrip('Kk'))
 121                 formats.append({
 122                     'url': video_url,
 123                     'resolution': resolution,
 124                     'format': format,
 125                     'tbr': tbr,
 126                     'height': height,
 127                     'format_id': format,
 128                 })
 129         self._sort_formats(formats)
 130
 131         age_limit = self._rta_search(webpage)
 132
 133         return {
 134             'id': video_id,
 135             'title': title,
 136             'description': description,
 137             'thumbnail': thumbnail,
 138             'uploader': uploader,
 139             'uploader_id': uploader_id,
 140             'upload_date': upload_date,
 141             'view_count': view_count,
 142             'comment_count': comment_count,
 143             'formats': formats,
 144             'age_limit': age_limit,
 145         }