1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
|
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import ExtractorError
class BYUtvIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<video_id>[^/?#]+)'
_TEST = {
'url': 'http://www.byutv.org/watch/44e80f7b-e3ba-43ba-8c51-b1fd96c94a79/granite-flats-talking',
'info_dict': {
'id': 'granite-flats-talking',
'ext': 'mp4',
'description': 'md5:4e9a7ce60f209a33eca0ac65b4918e1c',
'title': 'Talking',
'thumbnail': 're:^https?://.*promo.*'
},
'params': {
'skip_download': True,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('video_id')
webpage = self._download_webpage(url, video_id)
episode_code = self._search_regex(
r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')
episode_json = re.sub(
r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', episode_code)
ep = json.loads(episode_json)
if ep['providerType'] == 'Ooyala':
return {
'_type': 'url_transparent',
'ie_key': 'Ooyala',
'url': 'ooyala:%s' % ep['providerId'],
'id': video_id,
'title': ep['title'],
'description': ep.get('description'),
'thumbnail': ep.get('imageThumbnail'),
}
else:
raise ExtractorError('Unsupported provider %s' % ep['provider'])
|
