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