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
|
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
determine_ext,
ExtractorError,
)
class AUEngineIE(InfoExtractor):
_TEST = {
u'url': u'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
u'file': u'lfvlytY6.mp4',
u'md5': u'48972bdbcf1a3a2f5533e62425b41d4f',
u'info_dict': {
u"title": u"[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]"
}
}
_VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed.php\?.*?file=([^&]+).*?'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1)
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<title>(?P<title>.+?)</title>',
webpage, u'title')
title = title.strip()
links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage)
links = map(compat_urllib_parse.unquote, links)
thumbnail = None
video_url = None
for link in links:
if link.endswith('.png'):
thumbnail = link
elif '/videos/' in link:
video_url = link
if not video_url:
raise ExtractorError(u'Could not find video URL')
ext = u'.' + determine_ext(video_url)
if ext == title[-len(ext):]:
title = title[:-len(ext)]
return {
'id': video_id,
'url': video_url,
'title': title,
'thumbnail': thumbnail,
}
|
