]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/auengine.py
Merge tag 'upstream/2013.07.02'
[youtubedl] / youtube_dl / extractor / auengine.py
1 import os.path
2 import re
3
4 from .common import InfoExtractor
5 from ..utils import (
6 compat_urllib_parse,
7 compat_urllib_parse_urlparse,
8 )
9
10 class AUEngineIE(InfoExtractor):
11 _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed.php\?.*?file=([^&]+).*?'
12
13 def _real_extract(self, url):
14 mobj = re.match(self._VALID_URL, url)
15 video_id = mobj.group(1)
16 webpage = self._download_webpage(url, video_id)
17 title = self._html_search_regex(r'<title>(?P<title>.+?)</title>',
18 webpage, u'title')
19 title = title.strip()
20 links = re.findall(r'[^A-Za-z0-9]?(?:file|url):\s*["\'](http[^\'"&]*)', webpage)
21 links = [compat_urllib_parse.unquote(l) for l in links]
22 for link in links:
23 root, pathext = os.path.splitext(compat_urllib_parse_urlparse(link).path)
24 if pathext == '.png':
25 thumbnail = link
26 elif pathext == '.mp4':
27 url = link
28 ext = pathext
29 if ext == title[-len(ext):]:
30 title = title[:-len(ext)]
31 ext = ext[1:]
32 return [{
33 'id': video_id,
34 'url': url,
35 'ext': ext,
36 'title': title,
37 'thumbnail': thumbnail,
38 }]