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
|
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
HEADRequest,
)
class AparatIE(InfoExtractor):
_VALID_URL = r'^https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
_TEST = {
'url': 'http://www.aparat.com/v/wP8On',
'md5': '6714e0af7e0d875c5a39c4dc4ab46ad1',
'info_dict': {
'id': 'wP8On',
'ext': 'mp4',
'title': 'تیم گلکسی 11 - زومیت',
},
# 'skip': 'Extremely unreliable',
}
def _real_extract(self, url):
m = re.match(self._VALID_URL, url)
video_id = m.group('id')
# Note: There is an easier-to-parse configuration at
# http://www.aparat.com/video/video/config/videohash/%video_id
# but the URL in there does not work
embed_url = ('http://www.aparat.com/video/video/embed/videohash/' +
video_id + '/vt/frame')
webpage = self._download_webpage(embed_url, video_id)
video_urls = re.findall(r'fileList\[[0-9]+\]\s*=\s*"([^"]+)"', webpage)
for i, video_url in enumerate(video_urls):
req = HEADRequest(video_url)
res = self._request_webpage(
req, video_id, note=u'Testing video URL %d' % i, errnote=False)
if res:
break
else:
raise ExtractorError(u'No working video URLs found')
title = self._search_regex(r'\s+title:\s*"([^"]+)"', webpage, u'title')
thumbnail = self._search_regex(
r'\s+image:\s*"([^"]+)"', webpage, u'thumbnail', fatal=False)
return {
'id': video_id,
'title': title,
'url': video_url,
'ext': 'mp4',
'thumbnail': thumbnail,
}
|
