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     parse_duration,
   9     qualities,
  10 )
  11
  12
  13 class VuClipIE(InfoExtractor):
  14     _VALID_URL = r'http://(?:m\.)?vuclip\.com/w\?.*?cid=(?P<id>[0-9]+)'
  15
  16     _TEST = {
  17         'url': 'http://m.vuclip.com/w?cid=843902317&fid=63532&z=1007&nvar&frm=index.html&bu=4757321434',
  18         'md5': '92ac9d1ccefec4f0bb474661ab144fcf',
  19         'info_dict': {
  20             'id': '843902317',
  21             'ext': '3gp',
  22             'title': 'Movie Trailer: Noah',
  23             'duration': 139,
  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         links_code = self._search_regex(
  41             r'(?s)<div class="social align_c".*?>(.*?)<hr\s*/?>', webpage,
  42             'links')
  43         title = self._html_search_regex(
  44             r'<title>(.*?)-\s*Vuclip</title>', webpage, 'title').strip()
  45
  46         quality_order = qualities(['Reg', 'Hi'])
  47         formats = []
  48         for url, q in re.findall(
  49                 r'<a href="(?P<url>[^"]+)".*?>(?P<q>[^<]+)</a>', links_code):
  50             format_id = compat_urllib_parse_urlparse(url).scheme + '-' + q
  51             formats.append({
  52                 'format_id': format_id,
  53                 'url': url,
  54                 'quality': quality_order(q),
  55             })
  56         self._sort_formats(formats)
  57
  58         duration = parse_duration(self._search_regex(
  59             r'\(([0-9:]+)\)</span></h1>', webpage, 'duration', fatal=False))
  60
  61         return {
  62             'id': video_id,
  63             'formats': formats,
  64             'title': title,
  65             'duration': duration,
  66         }