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 re
from .common import InfoExtractor
from ..utils import (
compat_urllib_request,
compat_urllib_parse,
)
class SinaIE(InfoExtractor):
_VALID_URL = r'''https?://(.*?\.)?video\.sina\.com\.cn/
(
(.+?/(((?P<pseudo_id>\d+).html)|(.*?(\#|(vid=))(?P<id>\d+?)($|&))))
|
# This is used by external sites like Weibo
(api/sinawebApi/outplay.php/(?P<token>.+?)\.swf)
)
'''
_TEST = {
'url': 'http://video.sina.com.cn/news/vlist/zt/chczlj2013/?opsubject_id=top12#110028898',
'file': '110028898.flv',
'md5': 'd65dd22ddcf44e38ce2bf58a10c3e71f',
'info_dict': {
'title': '《中国新闻》 朝鲜要求巴拿马立即释放被扣船员',
}
}
@classmethod
def suitable(cls, url):
return re.match(cls._VALID_URL, url, flags=re.VERBOSE) is not None
def _extract_video(self, video_id):
data = compat_urllib_parse.urlencode({'vid': video_id})
url_doc = self._download_xml('http://v.iask.com/v_play.php?%s' % data,
video_id, 'Downloading video url')
image_page = self._download_webpage(
'http://interface.video.sina.com.cn/interface/common/getVideoImage.php?%s' % data,
video_id, 'Downloading thumbnail info')
return {'id': video_id,
'url': url_doc.find('./durl/url').text,
'ext': 'flv',
'title': url_doc.find('./vname').text,
'thumbnail': image_page.split('=')[1],
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
video_id = mobj.group('id')
if mobj.group('token') is not None:
# The video id is in the redirected url
self.to_screen('Getting video id')
request = compat_urllib_request.Request(url)
request.get_method = lambda: 'HEAD'
(_, urlh) = self._download_webpage_handle(request, 'NA', False)
return self._real_extract(urlh.geturl())
elif video_id is None:
pseudo_id = mobj.group('pseudo_id')
webpage = self._download_webpage(url, pseudo_id)
video_id = self._search_regex(r'vid:\'(\d+?)\'', webpage, 'video id')
return self._extract_video(video_id)
|
