[musicvault] Use the Kaltura extractor

This commit is contained in:
Naglis Jonaitis 2015-02-26 23:47:45 +02:00
parent 0d97ef43be
commit da419e2332
1 changed files with 7 additions and 20 deletions

View File

@ -3,17 +3,13 @@ from __future__ import unicode_literals
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
parse_duration,
unified_strdate,
)
class MusicVaultIE(InfoExtractor): class MusicVaultIE(InfoExtractor):
_VALID_URL = r'https?://www\.musicvault\.com/(?P<uploader_id>[^/?#]*)/video/(?P<display_id>[^/?#]*)_(?P<id>[0-9]+)\.html' _VALID_URL = r'https?://www\.musicvault\.com/(?P<uploader_id>[^/?#]*)/video/(?P<display_id>[^/?#]*)_(?P<id>[0-9]+)\.html'
_TEST = { _TEST = {
'url': 'http://www.musicvault.com/the-allman-brothers-band/video/straight-from-the-heart_1010863.html', 'url': 'http://www.musicvault.com/the-allman-brothers-band/video/straight-from-the-heart_1010863.html',
'md5': '2cdbb3ae75f7fb3519821507d2fb3c15', 'md5': '3adcbdb3dcc02d647539e53f284ba171',
'info_dict': { 'info_dict': {
'id': '1010863', 'id': '1010863',
'ext': 'mp4', 'ext': 'mp4',
@ -22,9 +18,10 @@ class MusicVaultIE(InfoExtractor):
'duration': 244, 'duration': 244,
'uploader': 'The Allman Brothers Band', 'uploader': 'The Allman Brothers Band',
'thumbnail': 're:^https?://.*/thumbnail/.*', 'thumbnail': 're:^https?://.*/thumbnail/.*',
'upload_date': '19811216', 'upload_date': '20131219',
'location': 'Capitol Theatre (Passaic, NJ)', 'location': 'Capitol Theatre (Passaic, NJ)',
'description': 'Listen to The Allman Brothers Band perform Straight from the Heart at Capitol Theatre (Passaic, NJ) on Dec 16, 1981', 'description': 'Listen to The Allman Brothers Band perform Straight from the Heart at Capitol Theatre (Passaic, NJ) on Dec 16, 1981',
'timestamp': int,
} }
} }
@ -43,34 +40,24 @@ class MusicVaultIE(InfoExtractor):
r'<h1.*?>(.*?)</h1>', data_div, 'uploader', fatal=False) r'<h1.*?>(.*?)</h1>', data_div, 'uploader', fatal=False)
title = self._html_search_regex( title = self._html_search_regex(
r'<h2.*?>(.*?)</h2>', data_div, 'title') r'<h2.*?>(.*?)</h2>', data_div, 'title')
upload_date = unified_strdate(self._html_search_regex(
r'<h3.*?>(.*?)</h3>', data_div, 'uploader', fatal=False))
location = self._html_search_regex( location = self._html_search_regex(
r'<h4.*?>(.*?)</h4>', data_div, 'location', fatal=False) r'<h4.*?>(.*?)</h4>', data_div, 'location', fatal=False)
duration = parse_duration(self._html_search_meta('duration', webpage))
VIDEO_URL_TEMPLATE = 'http://cdnapi.kaltura.com/p/%(uid)s/sp/%(wid)s/playManifest/entryId/%(entry_id)s/format/url/protocol/http'
kaltura_id = self._search_regex( kaltura_id = self._search_regex(
r'<div id="video-detail-player" data-kaltura-id="([^"]+)"', r'<div id="video-detail-player" data-kaltura-id="([^"]+)"',
webpage, 'kaltura ID') webpage, 'kaltura ID')
video_url = VIDEO_URL_TEMPLATE % { wid = self._search_regex(r'/wid/_([0-9]+)/', webpage, 'wid')
'entry_id': kaltura_id,
'wid': self._search_regex(r'/wid/_([0-9]+)/', webpage, 'wid'),
'uid': self._search_regex(r'uiconf_id/([0-9]+)/', webpage, 'uid'),
}
return { return {
'id': mobj.group('id'), 'id': mobj.group('id'),
'url': video_url, '_type': 'url_transparent',
'ext': 'mp4', 'url': 'kaltura:%s:%s' % (wid, kaltura_id),
'ie_key': 'Kaltura',
'display_id': display_id, 'display_id': display_id,
'uploader_id': mobj.group('uploader_id'), 'uploader_id': mobj.group('uploader_id'),
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'description': self._html_search_meta('description', webpage), 'description': self._html_search_meta('description', webpage),
'upload_date': upload_date,
'location': location, 'location': location,
'title': title, 'title': title,
'uploader': uploader, 'uploader': uploader,
'duration': duration,
} }