1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-25 19:52:11 +00:00

[godtube] Add extractor (Closes #3367)

This commit is contained in:
Sergey M․ 2014-07-27 02:38:05 +07:00
parent 71aa656d13
commit cb3ff6fb01
2 changed files with 59 additions and 0 deletions

View file

@ -115,6 +115,7 @@ from .gamespot import GameSpotIE
from .gametrailers import GametrailersIE from .gametrailers import GametrailersIE
from .gdcvault import GDCVaultIE from .gdcvault import GDCVaultIE
from .generic import GenericIE from .generic import GenericIE
from .godtube import GodTubeIE
from .googleplus import GooglePlusIE from .googleplus import GooglePlusIE
from .googlesearch import GoogleSearchIE from .googlesearch import GoogleSearchIE
from .gorillavid import GorillaVidIE from .gorillavid import GorillaVidIE

View file

@ -0,0 +1,58 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
parse_duration,
parse_iso8601,
)
class GodTubeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?godtube\.com/watch/\?v=(?P<id>[\da-zA-Z]+)'
_TESTS = [
{
'url': 'https://www.godtube.com/watch/?v=0C0CNNNU',
'md5': '77108c1e4ab58f48031101a1a2119789',
'info_dict': {
'id': '0C0CNNNU',
'ext': 'mp4',
'title': 'Woman at the well.',
'duration': 159,
'timestamp': 1205712000,
'uploader': 'beverlybmusic',
'upload_date': '20080317',
'thumbnail': 're:^https?://.*\.jpg$',
},
},
]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
config = self._download_xml(
'http://www.godtube.com/resource/mediaplayer/%s.xml' % video_id.lower(),
video_id, 'Downloading player config XML')
video_url = config.find('.//file').text
uploader = config.find('.//author').text
timestamp = parse_iso8601(config.find('.//date').text)
duration = parse_duration(config.find('.//duration').text)
thumbnail = config.find('.//image').text
media = self._download_xml(
'http://www.godtube.com/media/xml/?v=%s' % video_id, video_id, 'Downloading media XML')
title = media.find('.//title').text
return {
'id': video_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
'timestamp': timestamp,
'uploader': uploader,
'duration': duration,
}