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
|
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class NRLTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nrl\.com/tv(/[^/]+)*/(?P<id>[^/?&#]+)'
_TEST = {
'url': 'https://www.nrl.com/tv/news/match-highlights-titans-v-knights-862805/',
'info_dict': {
'id': 'YyNnFuaDE6kPJqlDhG4CGQ_w89mKTau4',
'ext': 'mp4',
'title': 'Match Highlights: Titans v Knights',
},
'params': {
# m3u8 download
'skip_download': True,
'format': 'bestvideo',
},
}
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
q_data = self._parse_json(self._search_regex(
r"(?s)q-data='({.+?})'", webpage, 'player data'), display_id)
ooyala_id = q_data['videoId']
return self.url_result(
'ooyala:' + ooyala_id, 'Ooyala', ooyala_id, q_data.get('title'))
|
