Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/musicvault.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     parse_duration,
   8     unified_strdate,
   9 )
  10
  11
  12 class MusicVaultIE(InfoExtractor):
  13     _VALID_URL = r'https?://www\.musicvault\.com/(?P<uploader_id>[^/?#]*)/video/(?P<display_id>[^/?#]*)_(?P<id>[0-9]+)\.html'
  14     _TEST = {
  15         'url': 'http://www.musicvault.com/the-allman-brothers-band/video/straight-from-the-heart_1010863.html',
  16         'md5': '2cdbb3ae75f7fb3519821507d2fb3c15',
  17         'info_dict': {
  18             'id': '1010863',
  19             'ext': 'mp4',
  20             'uploader_id': 'the-allman-brothers-band',
  21             'title': 'Straight from the Heart',
  22             'duration': 244,
  23             'uploader': 'The Allman Brothers Band',
  24             'thumbnail': 're:^https?://.*/thumbnail/.*',
  25             'upload_date': '19811216',
  26             'location': 'Capitol Theatre (Passaic, NJ)',
  27             'description': 'Listen to The Allman Brothers Band perform Straight from the Heart at Capitol Theatre (Passaic, NJ) on Dec 16, 1981',
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         mobj = re.match(self._VALID_URL, url)
  33         display_id = mobj.group('display_id')
  34         webpage = self._download_webpage(url, display_id)
  35
  36         thumbnail = self._search_regex(
  37             r'<meta itemprop="thumbnail" content="([^"]+)"',
  38             webpage, 'thumbnail', fatal=False)
  39
  40         data_div = self._search_regex(
  41             r'(?s)<div class="data">(.*?)</div>', webpage, 'data fields')
  42         uploader = self._html_search_regex(
  43             r'<h1.*?>(.*?)</h1>', data_div, 'uploader', fatal=False)
  44         title = self._html_search_regex(
  45             r'<h2.*?>(.*?)</h2>', data_div, 'title')
  46         upload_date = unified_strdate(self._html_search_regex(
  47             r'<h3.*?>(.*?)</h3>', data_div, 'uploader', fatal=False))
  48         location = self._html_search_regex(
  49             r'<h4.*?>(.*?)</h4>', data_div, 'location', fatal=False)
  50
  51         duration = parse_duration(self._html_search_meta('duration', webpage))
  52
  53         VIDEO_URL_TEMPLATE = 'http://cdnapi.kaltura.com/p/%(uid)s/sp/%(wid)s/playManifest/entryId/%(entry_id)s/format/url/protocol/http'
  54         kaltura_id = self._search_regex(
  55             r'<div id="video-detail-player" data-kaltura-id="([^"]+)"',
  56             webpage, 'kaltura ID')
  57         video_url = VIDEO_URL_TEMPLATE % {
  58             'entry_id': kaltura_id,
  59             'wid': self._search_regex(r'/wid/_([0-9]+)/', webpage, 'wid'),
  60             'uid': self._search_regex(r'uiconf_id/([0-9]+)/', webpage, 'uid'),
  61         }
  62
  63         return {
  64             'id': mobj.group('id'),
  65             'url': video_url,
  66             'ext': 'mp4',
  67             'display_id': display_id,
  68             'uploader_id': mobj.group('uploader_id'),
  69             'thumbnail': thumbnail,
  70             'description': self._html_search_meta('description', webpage),
  71             'upload_date': upload_date,
  72             'location': location,
  73             'title': title,
  74             'uploader': uploader,
  75             'duration': duration,
  76         }