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,
   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     _TEST = {
  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': '20070508',
  31             'age_limit': 18,
  32         }
  33     }
  34
  35     def _real_extract(self, url):
  36         mobj = re.match(self._VALID_URL, url)
  37         video_id = mobj.group('videoid')
  38         url = 'http://www.' + mobj.group('url')
  39
  40         req = compat_urllib_request.Request(url)
  41         req.add_header('Cookie', 'age_verified=1')
  42         webpage = self._download_webpage(req, video_id)
  43
  44         title = self._html_search_regex(
  45             r'<h1>([^<]+)', webpage, 'title')
  46         description = self._html_search_regex(
  47             r'<div\s+id="descriptionContent">([^<]+)<',
  48             webpage, 'description', fatal=False)
  49         thumbnail = self._html_search_regex(
  50             r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']',
  51             webpage, 'thumbnail', fatal=False)
  52
  53         uploader = self._html_search_regex(
  54             r'by:\s*<a [^>]*>(.+?)</a>',
  55             webpage, 'uploader', fatal=False)
  56         uploader_id = self._html_search_regex(
  57             r'by:\s*<a href="/Profile\.aspx\?.*?UserId=(\d+).*?"',
  58             webpage, 'uploader id', fatal=False)
  59         upload_date = unified_strdate(self._html_search_regex(
  60             r'</a> on (.+?) at \d+:\d+',
  61             webpage, 'upload date', fatal=False))
  62
  63         view_count = str_to_int(self._html_search_regex(
  64             r'<div id="viewsCounter"><span>([\d,\.]+)</span> views</div>',
  65             webpage, 'view count', fatal=False))
  66         comment_count = str_to_int(self._html_search_regex(
  67             r'Comments<span[^>]+>\s*\(([\d,\.]+)\)</span>',
  68             webpage, 'comment count', fatal=False))
  69
  70         video_urls = list(map(
  71             compat_urllib_parse.unquote,
  72             re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*["\']([^"\']+)["\']', webpage)))
  73         if webpage.find('flashvars\.encrypted = "true"') != -1:
  74             password = self._html_search_regex(
  75                 r'flashvars\.video_title = "([^"]+)',
  76                 webpage, 'password').replace('+', ' ')
  77             video_urls = list(map(
  78                 lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'),
  79                 video_urls))
  80
  81         formats = []
  82         for video_url in video_urls:
  83             path = compat_urllib_parse_urlparse(video_url).path
  84             format = path.split('/')[4].split('_')[:2]
  85             resolution, bitrate_str = format
  86             format = "-".join(format)
  87             height = int(resolution.rstrip('Pp'))
  88             tbr = int(bitrate_str.rstrip('Kk'))
  89             formats.append({
  90                 'url': video_url,
  91                 'resolution': resolution,
  92                 'format': format,
  93                 'tbr': tbr,
  94                 'height': height,
  95                 'format_id': format,
  96             })
  97         self._sort_formats(formats)
  98
  99         age_limit = self._rta_search(webpage)
 100
 101         return {
 102             'id': video_id,
 103             'title': title,
 104             'description': description,
 105             'thumbnail': thumbnail,
 106             'uploader': uploader,
 107             'uploader_id': uploader_id,
 108             'upload_date': upload_date,
 109             'view_count': view_count,
 110             'comment_count': comment_count,
 111             'formats': formats,
 112             'age_limit': age_limit,
 113         }