youtube_dl/extractor/musicvault.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class MusicVaultIE(InfoExtractor):
   9     _VALID_URL = r'https?://www\.musicvault\.com/(?P<uploader_id>[^/?#]*)/video/(?P<display_id>[^/?#]*)_(?P<id>[0-9]+)\.html'
  10     _TEST = {
  11         'url': 'http://www.musicvault.com/the-allman-brothers-band/video/straight-from-the-heart_1010863.html',
  12         'md5': '3adcbdb3dcc02d647539e53f284ba171',
  13         'info_dict': {
  14             'id': '1010863',
  15             'ext': 'mp4',
  16             'uploader_id': 'the-allman-brothers-band',
  17             'title': 'Straight from the Heart',
  18             'duration': 244,
  19             'uploader': 'The Allman Brothers Band',
  20             'thumbnail': 're:^https?://.*/thumbnail/.*',
  21             'upload_date': '20131219',
  22             'location': 'Capitol Theatre (Passaic, NJ)',
  23             'description': 'Listen to The Allman Brothers Band perform Straight from the Heart at Capitol Theatre (Passaic, NJ) on Dec 16, 1981',
  24             'timestamp': int,
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = re.match(self._VALID_URL, url)
  30         display_id = mobj.group('display_id')
  31         webpage = self._download_webpage(url, display_id)
  32
  33         thumbnail = self._search_regex(
  34             r'<meta itemprop="thumbnail" content="([^"]+)"',
  35             webpage, 'thumbnail', fatal=False)
  36
  37         data_div = self._search_regex(
  38             r'(?s)<div class="data">(.*?)</div>', webpage, 'data fields')
  39         uploader = self._html_search_regex(
  40             r'<h1.*?>(.*?)</h1>', data_div, 'uploader', fatal=False)
  41         title = self._html_search_regex(
  42             r'<h2.*?>(.*?)</h2>', data_div, 'title')
  43         location = self._html_search_regex(
  44             r'<h4.*?>(.*?)</h4>', data_div, 'location', fatal=False)
  45
  46         kaltura_id = self._search_regex(
  47             r'<div id="video-detail-player" data-kaltura-id="([^"]+)"',
  48             webpage, 'kaltura ID')
  49         wid = self._search_regex(r'/wid/_([0-9]+)/', webpage, 'wid')
  50
  51         return {
  52             'id': mobj.group('id'),
  53             '_type': 'url_transparent',
  54             'url': 'kaltura:%s:%s' % (wid, kaltura_id),
  55             'ie_key': 'Kaltura',
  56             'display_id': display_id,
  57             'uploader_id': mobj.group('uploader_id'),
  58             'thumbnail': thumbnail,
  59             'description': self._html_search_meta('description', webpage),
  60             'location': location,
  61             'title': title,
  62             'uploader': uploader,
  63         }