_ Git - youtube-dl/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         import io
  33         webpage = io.open('922692425_http_-_m.vuclip.com_wcid=922692425_fid=70295_z=1010_nvar_frm=index.html.dump', encoding='utf-8').read()
  34         ad_m = re.search(
  35             r'''value="No.*?" onClick="location.href='([^"']+)'"''', webpage)
  36         if ad_m:
  37             urlr = compat_urllib_parse_urlparse(url)
  38             adfree_url = urlr.scheme + '://' + urlr.netloc + ad_m.group(1)
  39             webpage = self._download_webpage(
  40                 adfree_url, video_id, note='Download post-ad page')
  41
  42         error_msg = self._html_search_regex(
  43             r'<p class="message">(.*?)</p>', webpage, 'error message',
  44             default=None)
  45         if error_msg:
  46             raise ExtractorError(
  47                 '%s said: %s' % (self.IE_NAME, error_msg), expected=True)
  48
  49         # These clowns alternate between two page types
  50         links_code = self._search_regex(
  51             r'''(?xs)
  52                 (?:
  53                     <img\s+src="/im/play.gif".*?>|
  54                     <!--\ player\ end\ -->\s*</div><!--\ thumb\ end-->
  55                 )
  56                 (.*?)
  57                 (?:
  58                     <a\s+href="fblike'|<div\s+class="social">
  59                 )
  60             ''', webpage, 'links')
  61         title = self._html_search_regex(
  62             r'<title>(.*?)-\s*Vuclip</title>', webpage, 'title').strip()
  63
  64         quality_order = qualities(['Reg', 'Hi'])
  65         formats = []
  66         for url, q in re.findall(
  67                 r'<a\s+href="(?P<url>[^"]+)".*?>(?:<button[^>]*>)?(?P<q>[^<]+)(?:</button>)?</a>', links_code):
  68             format_id = compat_urllib_parse_urlparse(url).scheme + '-' + q
  69             formats.append({
  70                 'format_id': format_id,
  71                 'url': url,
  72                 'quality': quality_order(q),
  73             })
  74         self._sort_formats(formats)
  75
  76         duration = parse_duration(self._search_regex(
  77             r'\(([0-9:]+)\)</span>', webpage, 'duration', fatal=False))
  78
  79         return {
  80             'id': video_id,
  81             'formats': formats,
  82             'title': title,
  83             'duration': duration,
  84         }