Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vuclip.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_urlparse,
   8 )
   9 from ..utils import (
  10     ExtractorError,
  11     parse_duration,
  12     qualities,
  13 )
  14
  15
  16 class VuClipIE(InfoExtractor):
  17     _VALID_URL = r'http://(?:m\.)?vuclip\.com/w\?.*?cid=(?P<id>[0-9]+)'
  18
  19     _TEST = {
  20         'url': 'http://m.vuclip.com/w?cid=922692425&fid=70295&z=1010&nvar&frm=index.html',
  21         'info_dict': {
  22             'id': '922692425',
  23             'ext': '3gp',
  24             'title': 'The Toy Soldiers - Hollywood Movie Trailer',
  25             'duration': 180,
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31         webpage = self._download_webpage(url, video_id)
  32
  33         ad_m = re.search(
  34             r'''value="No.*?" onClick="location.href='([^"']+)'"''', webpage)
  35         if ad_m:
  36             urlr = compat_urllib_parse_urlparse(url)
  37             adfree_url = urlr.scheme + '://' + urlr.netloc + ad_m.group(1)
  38             webpage = self._download_webpage(
  39                 adfree_url, video_id, note='Download post-ad page')
  40
  41         error_msg = self._html_search_regex(
  42             r'<p class="message">(.*?)</p>', webpage, 'error message',
  43             default=None)
  44         if error_msg:
  45             raise ExtractorError(
  46                 '%s said: %s' % (self.IE_NAME, error_msg), expected=True)
  47
  48         # These clowns alternate between two page types
  49         links_code = self._search_regex(
  50             r'''(?xs)
  51                 (?:
  52                     <img\s+src="/im/play.gif".*?>|
  53                     <!--\ player\ end\ -->\s*</div><!--\ thumb\ end-->
  54                 )
  55                 (.*?)
  56                 (?:
  57                     <a\s+href="fblike|<div\s+class="social">
  58                 )
  59             ''', webpage, 'links')
  60         title = self._html_search_regex(
  61             r'<title>(.*?)-\s*Vuclip</title>', webpage, 'title').strip()
  62
  63         quality_order = qualities(['Reg', 'Hi'])
  64         formats = []
  65         for url, q in re.findall(
  66                 r'<a\s+href="(?P<url>[^"]+)".*?>(?:<button[^>]*>)?(?P<q>[^<]+)(?:</button>)?</a>', links_code):
  67             format_id = compat_urllib_parse_urlparse(url).scheme + '-' + q
  68             formats.append({
  69                 'format_id': format_id,
  70                 'url': url,
  71                 'quality': quality_order(q),
  72             })
  73         self._sort_formats(formats)
  74
  75         duration = parse_duration(self._search_regex(
  76             r'\(([0-9:]+)\)</span>', webpage, 'duration', fatal=False))
  77
  78         return {
  79             'id': video_id,
  80             'formats': formats,
  81             'title': title,
  82             'duration': duration,
  83         }