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
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
|
# coding: utf-8
from __future__ import unicode_literals
import json
from .common import InfoExtractor
from ..utils import (
url_infer_protocol,
js_to_json
)
class UDNEmbedIE(InfoExtractor):
_VALID_URL = r'(?:https?:)?//video\.udn\.com/embed/news/(?P<id>\d+)'
_TESTS = [{
'url': 'http://video.udn.com/embed/news/300040',
'md5': 'de06b4c90b042c128395a88f0384817e',
'info_dict': {
'id': '300040',
'ext': 'mp4',
'title': '生物老師男變女 全校挺"做自己"',
'thumbnail': 're:^https?://.*\.jpg$',
}
}, {
'url': '//video.udn.com/embed/news/300040',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
page = self._download_webpage(url, video_id)
options = json.loads(js_to_json(self._html_search_regex(
r'var options\s*=\s*([^;]+);', page, 'video urls dictionary')))
video_urls = options['video']
if video_urls.get('youtube'):
return self.url_result(video_urls.get('youtube'), 'Youtube')
try:
del video_urls['youtube']
except KeyError:
pass
formats = [{
'url': self._download_webpage(
url_infer_protocol(url, api_url), video_id,
'retrieve url for %s video' % video_type),
'format_id': video_type,
'preference': 0 if video_type == 'mp4' else -1,
} for video_type, api_url in video_urls.items()]
self._sort_formats(formats)
thumbnail = None
if options.get('gallery') and len(options['gallery']):
thumbnail = options['gallery'][0].get('original')
return {
'id': video_id,
'formats': formats,
'title': options['title'],
'thumbnail': thumbnail
}
|
