[muscivault] Add extractor (Fixes #3593)

This commit is contained in:
Philipp Hagemeister 2014-08-27 01:44:47 +02:00
parent 191b7cbba9
commit da9ec3b932
3 changed files with 80 additions and 1 deletions

View File

@ -209,6 +209,7 @@ from .mtv import (
MTVIggyIE, MTVIggyIE,
) )
from .musicplayon import MusicPlayOnIE from .musicplayon import MusicPlayOnIE
from .musicvault import MusicVaultIE
from .muzu import MuzuTVIE from .muzu import MuzuTVIE
from .myspace import MySpaceIE from .myspace import MySpaceIE
from .myspass import MySpassIE from .myspass import MySpassIE

View File

@ -114,7 +114,7 @@ class InfoExtractor(object):
upload_date: Video upload date (YYYYMMDD). upload_date: Video upload date (YYYYMMDD).
If not explicitly set, calculated from timestamp. If not explicitly set, calculated from timestamp.
uploader_id: Nickname or id of the video uploader. uploader_id: Nickname or id of the video uploader.
location: Physical location of the video. location: Physical location where the video was filmed.
subtitles: The subtitle file contents as a dictionary in the format subtitles: The subtitle file contents as a dictionary in the format
{language: subtitles}. {language: subtitles}.
duration: Length of the video in seconds, as an integer. duration: Length of the video in seconds, as an integer.

View File

@ -0,0 +1,78 @@
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
strip_jsonp,
parse_duration,
unified_strdate,
)
class MusicVaultIE(InfoExtractor):
_VALID_URL = r'https?://www\.musicvault\.com/(?P<uploader_id>[^/?#]*)/video/(?P<display_id>[^/?#]*)_(?P<id>[0-9]+)\.html'
_TEST = {
'url': 'http://www.musicvault.com/the-allman-brothers-band/video/straight-from-the-heart_1010863.html',
'md5': '2cdbb3ae75f7fb3519821507d2fb3c15',
'info_dict': {
'id': '1010863',
'ext': 'mp4',
'uploader_id': 'the-allman-brothers-band',
'title': 'Straight from the Heart',
'duration': 244,
'uploader': 'The Allman Brothers Band',
'thumbnail': 're:^https?://.*/thumbnail/.*',
'upload_date': '19811216',
'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',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('display_id')
webpage = self._download_webpage(url, display_id)
thumbnail = self._search_regex(
r'<meta itemprop="thumbnail" content="([^"]+)"',
webpage, 'thumbnail', fatal=False)
data_div = self._search_regex(
r'(?s)<div class="data">(.*?)</div>', webpage, 'data fields')
uploader = self._html_search_regex(
r'<h1.*?>(.*?)</h1>', data_div, 'uploader', fatal=False)
title = self._html_search_regex(
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(
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(
r'<div id="video-detail-player" data-kaltura-id="([^"]+)"',
webpage, 'kaltura ID')
video_url = VIDEO_URL_TEMPLATE % {
'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 {
'id': mobj.group('id'),
'url': video_url,
'ext': 'mp4',
'display_id': display_id,
'uploader_id': mobj.group('uploader_id'),
'thumbnail': thumbnail,
'description': self._html_search_meta('description', webpage),
'upload_date': upload_date,
'location': location,
'title': title,
'uploader': uploader,
'duration': duration,
}