Raphaël G. Git Repositories - youtubedl/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 )
  10 from ..utils import (
  11     sanitized_Request,
  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<id>[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('id')
  53
  54         req = sanitized_Request('http://www.' + mobj.group('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|Profile\.aspx)\?.*?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         videos = re.findall(
  85             r'playerData\.cdnPath([0-9]{3,})\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage)
  86         heights = [int(video[0]) for video in videos]
  87         video_urls = list(map(compat_urllib_parse_unquote, [video[1] for video in videos]))
  88         if webpage.find(r'flashvars\.encrypted = "true"') != -1:
  89             password = self._search_regex(
  90                 r'flashvars\.video_title = "([^"]+)',
  91                 webpage, 'password').replace('+', ' ')
  92             video_urls = list(map(
  93                 lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'),
  94                 video_urls))
  95
  96         formats = []
  97         for height, video_url in zip(heights, video_urls):
  98             path = compat_urllib_parse_urlparse(video_url).path
  99             m = re.search(r'/(?P<height>\d+)[pP]_(?P<tbr>\d+)[kK]', path)
 100             if m:
 101                 tbr = int(m.group('tbr'))
 102                 height = int(m.group('height'))
 103             else:
 104                 tbr = None
 105             formats.append({
 106                 'url': video_url,
 107                 'format_id': '%dp' % height,
 108                 'height': height,
 109                 'tbr': tbr,
 110             })
 111         self._sort_formats(formats)
 112
 113         age_limit = self._rta_search(webpage)
 114
 115         return {
 116             'id': video_id,
 117             'title': title,
 118             'description': description,
 119             'thumbnail': thumbnail,
 120             'uploader': uploader,
 121             'uploader_id': uploader_id,
 122             'upload_date': upload_date,
 123             'view_count': view_count,
 124             'comment_count': comment_count,
 125             'formats': formats,
 126             'age_limit': age_limit,
 127         }