w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[hark] Modernize

Browse source
This commit is contained in:
Philipp Hagemeister 2014-10-24 22:31:55 +02:00
parent 8efd06aa42
commit cdc5cb7c2b
1 changed files with 22 additions and 26 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

46
youtube_dl/extractor/hark.py
View file

@ -1,37 +1,33 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import determine_ext
class HarkIE(InfoExtractor): class HarkIE(InfoExtractor):
_VALID_URL = r'https?://www\.hark\.com/clips/(.+?)-.+' _VALID_URL = r'https?://www\.hark\.com/clips/(?P<id>.+?)-.+'
_TEST = { _TEST = {
u'url': u'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013', 'url': 'http://www.hark.com/clips/mmbzyhkgny-obama-beyond-the-afghan-theater-we-only-target-al-qaeda-on-may-23-2013',
u'file': u'mmbzyhkgny.mp3', 'md5': '6783a58491b47b92c7c1af5a77d4cbee',
u'md5': u'6783a58491b47b92c7c1af5a77d4cbee', 'info_dict': {
u'info_dict': { 'id': 'mmbzyhkgny',
u'title': u"Obama: 'Beyond The Afghan Theater, We Only Target Al Qaeda' on May 23, 2013", 'ext': 'mp3',
u'description': u'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.', 'title': 'Obama: \'Beyond The Afghan Theater, We Only Target Al Qaeda\' on May 23, 2013',
u'duration': 11, 'description': 'President Barack Obama addressed the nation live on May 23, 2013 in a speech aimed at addressing counter-terrorism policies including the use of drone strikes, detainees at Guantanamo Bay prison facility, and American citizens who are terrorists.',
'duration': 11,
} }
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group(1) data = self._download_json(
json_url = "http://www.hark.com/clips/%s.json" %(video_id) 'http://www.hark.com/clips/%s.json' % video_id, video_id)
info_json = self._download_webpage(json_url, video_id)
info = json.loads(info_json)
final_url = info['url']
return {'id': video_id, return {
'url' : final_url, 'id': video_id,
'title': info['name'], 'url': data['url'],
'ext': determine_ext(final_url), 'title': data['name'],
'description': info['description'], 'description': data.get('description'),
'thumbnail': info['image_original'], 'thumbnail': data.get('image_original'),
'duration': info['duration'], 'duration': data.get('duration'),
} }