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 ..utils import (
   7     compat_urllib_parse_urlparse,
   8     compat_urllib_request,
   9     compat_urllib_parse,
  10     unified_strdate,
  11     str_to_int,
  12 )
  13 from ..aes import aes_decrypt_text
  14
  15
  16 class SpankwireIE(InfoExtractor):
  17     _VALID_URL = r'https?://(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
  18     _TEST = {
  19         'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
  20         'md5': '8bbfde12b101204b39e4b9fe7eb67095',
  21         'info_dict': {
  22             'id': '103545',
  23             'ext': 'mp4',
  24             'title': 'Buckcherry`s X Rated Music Video Crazy Bitch',
  25             'description': 'Crazy Bitch X rated music video.',
  26             'uploader': 'oreusz',
  27             'uploader_id': '124697',
  28             'upload_date': '20070508',
  29             'age_limit': 18,
  30         }
  31     }
  32
  33     def _real_extract(self, url):
  34         mobj = re.match(self._VALID_URL, url)
  35         video_id = mobj.group('videoid')
  36         url = 'http://www.' + mobj.group('url')
  37
  38         req = compat_urllib_request.Request(url)
  39         req.add_header('Cookie', 'age_verified=1')
  40         webpage = self._download_webpage(req, video_id)
  41
  42         title = self._html_search_regex(
  43             r'<h1>([^<]+)', webpage, 'title')
  44         description = self._html_search_regex(
  45             r'<div\s+id="descriptionContent">([^<]+)<',
  46             webpage, 'description', fatal=False)
  47         thumbnail = self._html_search_regex(
  48             r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']',
  49             webpage, 'thumbnail', fatal=False)
  50
  51         uploader = self._html_search_regex(
  52             r'by:\s*<a [^>]*>(.+?)</a>',
  53             webpage, 'uploader', fatal=False)
  54         uploader_id = self._html_search_regex(
  55             r'by:\s*<a href="/Profile\.aspx\?.*?UserId=(\d+).*?"',
  56             webpage, 'uploader id', fatal=False)
  57         upload_date = unified_strdate(self._html_search_regex(
  58             r'</a> on (.+?) at \d+:\d+',
  59             webpage, 'upload date', fatal=False))
  60
  61         view_count = str_to_int(self._html_search_regex(
  62             r'<div id="viewsCounter"><span>([\d,\.]+)</span> views</div>',
  63             webpage, 'view count', fatal=False))
  64         comment_count = str_to_int(self._html_search_regex(
  65             r'Comments<span[^>]+>\s*\(([\d,\.]+)\)</span>',
  66             webpage, 'comment count', fatal=False))
  67
  68         video_urls = list(map(
  69             compat_urllib_parse.unquote,
  70             re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*["\']([^"\']+)["\']', webpage)))
  71         if webpage.find('flashvars\.encrypted = "true"') != -1:
  72             password = self._html_search_regex(
  73                 r'flashvars\.video_title = "([^"]+)',
  74                 webpage, 'password').replace('+', ' ')
  75             video_urls = list(map(
  76                 lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'),
  77                 video_urls))
  78
  79         formats = []
  80         for video_url in video_urls:
  81             path = compat_urllib_parse_urlparse(video_url).path
  82             format = path.split('/')[4].split('_')[:2]
  83             resolution, bitrate_str = format
  84             format = "-".join(format)
  85             height = int(resolution.rstrip('Pp'))
  86             tbr = int(bitrate_str.rstrip('Kk'))
  87             formats.append({
  88                 'url': video_url,
  89                 'resolution': resolution,
  90                 'format': format,
  91                 'tbr': tbr,
  92                 'height': height,
  93                 'format_id': format,
  94             })
  95         self._sort_formats(formats)
  96
  97         age_limit = self._rta_search(webpage)
  98
  99         return {
 100             'id': video_id,
 101             'title': title,
 102             'description': description,
 103             'thumbnail': thumbnail,
 104             'uploader': uploader,
 105             'uploader_id': uploader_id,
 106             'upload_date': upload_date,
 107             'view_count': view_count,
 108             'comment_count': comment_count,
 109             'formats': formats,
 110             'age_limit': age_limit,
 111         }