_ Git - youtube-dl/blob - 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         # download URL pattern: */<height>P_<tbr>K_<video_id>.mp4
  22         'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
  23         'md5': '8bbfde12b101204b39e4b9fe7eb67095',
  24         'info_dict': {
  25             'id': '103545',
  26             'ext': 'mp4',
  27             'title': 'Buckcherry`s X Rated Music Video Crazy Bitch',
  28             'description': 'Crazy Bitch X rated music video.',
  29             'uploader': 'oreusz',
  30             'uploader_id': '124697',
  31             'upload_date': '20070507',
  32             'age_limit': 18,
  33         }
  34     }, {
  35         # download URL pattern: */mp4_<format_id>_<video_id>.mp4
  36         'url': 'http://www.spankwire.com/Titcums-Compiloation-I/video1921551/',
  37         'md5': '09b3c20833308b736ae8902db2f8d7e6',
  38         'info_dict': {
  39             'id': '1921551',
  40             'ext': 'mp4',
  41             'title': 'Titcums Compiloation I',
  42             'description': 'cum on tits',
  43             'uploader': 'dannyh78999',
  44             'uploader_id': '3056053',
  45             'upload_date': '20150822',
  46             'age_limit': 18,
  47         },
  48     }]
  49
  50     def _real_extract(self, url):
  51         mobj = re.match(self._VALID_URL, url)
  52         video_id = mobj.group('videoid')
  53         url = 'http://www.' + mobj.group('url')
  54
  55         req = compat_urllib_request.Request(url)
  56         req.add_header('Cookie', 'age_verified=1')
  57         webpage = self._download_webpage(req, video_id)
  58
  59         title = self._html_search_regex(
  60             r'<h1>([^<]+)', webpage, 'title')
  61         description = self._html_search_regex(
  62             r'(?s)<div\s+id="descriptionContent">(.+?)</div>',
  63             webpage, 'description', fatal=False)
  64         thumbnail = self._html_search_regex(
  65             r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']',
  66             webpage, 'thumbnail', fatal=False)
  67
  68         uploader = self._html_search_regex(
  69             r'by:\s*<a [^>]*>(.+?)</a>',
  70             webpage, 'uploader', fatal=False)
  71         uploader_id = self._html_search_regex(
  72             r'by:\s*<a href="/user/viewProfile\?.*?UserId=(\d+).*?"',
  73             webpage, 'uploader id', fatal=False)
  74         upload_date = unified_strdate(self._html_search_regex(
  75             r'</a> on (.+?) at \d+:\d+',
  76             webpage, 'upload date', fatal=False))
  77
  78         view_count = str_to_int(self._html_search_regex(
  79             r'<div id="viewsCounter"><span>([\d,\.]+)</span> views</div>',
  80             webpage, 'view count', fatal=False))
  81         comment_count = str_to_int(self._html_search_regex(
  82             r'<span\s+id="spCommentCount"[^>]*>([\d,\.]+)</span>',
  83             webpage, 'comment count', fatal=False))
  84
  85         videos = re.findall(
  86             r'playerData\.cdnPath([0-9]{3,})\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage)
  87         heights = [int(video[0]) for video in videos]
  88         video_urls = list(map(compat_urllib_parse_unquote, [video[1] for video in videos]))
  89         if webpage.find('flashvars\.encrypted = "true"') != -1:
  90             password = self._search_regex(
  91                 r'flashvars\.video_title = "([^"]+)',
  92                 webpage, 'password').replace('+', ' ')
  93             video_urls = list(map(
  94                 lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'),
  95                 video_urls))
  96
  97         formats = []
  98         for height, video_url in zip(heights, video_urls):
  99             path = compat_urllib_parse_urlparse(video_url).path
 100             _, quality = path.split('/')[4].split('_')[:2]
 101             f = {
 102                 'url': video_url,
 103                 'height': height,
 104             }
 105             tbr = self._search_regex(r'^(\d+)[Kk]$', quality, 'tbr', default=None)
 106             if tbr:
 107                 f.update({
 108                     'tbr': int(tbr),
 109                     'format_id': '%dp' % height,
 110                 })
 111             else:
 112                 f['format_id'] = quality
 113             formats.append(f)
 114         self._sort_formats(formats)
 115
 116         age_limit = self._rta_search(webpage)
 117
 118         return {
 119             'id': video_id,
 120             'title': title,
 121             'description': description,
 122             'thumbnail': thumbnail,
 123             'uploader': uploader,
 124             'uploader_id': uploader_id,
 125             'upload_date': upload_date,
 126             'view_count': view_count,
 127             'comment_count': comment_count,
 128             'formats': formats,
 129             'age_limit': age_limit,
 130         }