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 re
from .brightcove import BrightcoveIE
from .common import InfoExtractor
from ..utils import ExtractorError
class NownessIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nowness\.com/[^?#]*?/(?P<id>[0-9]+)/(?P<slug>[^/]+?)(?:$|[?#])'
_TEST = {
'url': 'http://www.nowness.com/day/2013/6/27/3131/candor--the-art-of-gesticulation',
'md5': '068bc0202558c2e391924cb8cc470676',
'info_dict': {
'id': '2520295746001',
'ext': 'mp4',
'description': 'Candor: The Art of Gesticulation',
'uploader': 'Nowness',
'title': 'Candor: The Art of Gesticulation',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('slug')
webpage = self._download_webpage(url, video_id)
player_url = self._search_regex(
r'"([^"]+/content/issue-[0-9.]+.js)"', webpage, 'player URL')
real_id = self._search_regex(
r'\sdata-videoId="([0-9]+)"', webpage, 'internal video ID')
player_code = self._download_webpage(
player_url, video_id,
note='Downloading player JavaScript',
errnote='Player download failed')
player_code = player_code.replace("'+d+'", real_id)
bc_url = BrightcoveIE._extract_brightcove_url(player_code)
if bc_url is None:
raise ExtractorError('Could not find player definition')
return {
'_type': 'url',
'url': bc_url,
'ie_key': 'Brightcove',
}
|
