]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/auengine.py
Merge tag 'upstream/2014.12.01'
[youtubedl] / youtube_dl / extractor / auengine.py
1 from __future__ import unicode_literals
2
3 import re
4
5 from .common import InfoExtractor
6 from ..utils import (
7 compat_urllib_parse,
8 determine_ext,
9 ExtractorError,
10 )
11
12
13 class AUEngineIE(InfoExtractor):
14 _VALID_URL = r'http://(?:www\.)?auengine\.com/embed\.php\?.*?file=(?P<id>[^&]+).*?'
15
16 _TEST = {
17 'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
18 'md5': '48972bdbcf1a3a2f5533e62425b41d4f',
19 'info_dict': {
20 'id': 'lfvlytY6',
21 'ext': 'mp4',
22 'title': '[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]'
23 }
24 }
25
26 def _real_extract(self, url):
27 video_id = self._match_id(url)
28
29 webpage = self._download_webpage(url, video_id)
30 title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', webpage, 'title')
31 title = title.strip()
32 links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage)
33 links = map(compat_urllib_parse.unquote, links)
34
35 thumbnail = None
36 video_url = None
37 for link in links:
38 if link.endswith('.png'):
39 thumbnail = link
40 elif '/videos/' in link:
41 video_url = link
42 if not video_url:
43 raise ExtractorError('Could not find video URL')
44 ext = '.' + determine_ext(video_url)
45 if ext == title[-len(ext):]:
46 title = title[:-len(ext)]
47
48 return {
49 'id': video_id,
50 'url': video_url,
51 'title': title,
52 'thumbnail': thumbnail,
53 'http_referer': 'http://www.auengine.com/flowplayer/flowplayer.commercial-3.2.14.swf',
54 }