aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/auengine.py
blob: 40ea5ec95f89f8d20ac8eb0b81350a7c5c14440b (plain)
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
import os.path
import re
import urllib
import urlparse

from .common import InfoExtractor

class AuengineIE(InfoExtractor):
    _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'[^A-Za-z0-9]?(?:file|url):\s*["\'](http[^\'"&]*)', webpage)
        links = [urllib.unquote(l) for l in links]
        for link in links:
            root, pathext = os.path.splitext(urlparse.urlparse(link).path)
            if pathext == '.png':
                thumbnail = link
            elif pathext == '.mp4':
                url = link
                ext = pathext
        if ext == title[-len(ext):]:
            title = title[:-len(ext)]
        ext = ext[1:]
        return [{
            'id':        video_id,
            'url':       url,
            'ext':       ext,
            'title':     title,
            'thumbnail': thumbnail,
        }]