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