ytdl-nightly/youtube_dl/extractor/auengine.py

53 lines
1.6 KiB
Python
Raw Normal View History

2014-01-07 10:04:48 +01:00
from __future__ import unicode_literals
2013-06-27 13:58:09 +02:00
import re
from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
2013-11-18 13:56:45 +01:00
determine_ext,
ExtractorError,
)
2013-06-27 13:58:09 +02:00
2014-01-07 10:04:48 +01:00
class AUEngineIE(InfoExtractor):
2013-07-03 16:36:36 +02:00
_TEST = {
2014-01-07 10:04:48 +01:00
'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
'file': 'lfvlytY6.mp4',
'md5': '48972bdbcf1a3a2f5533e62425b41d4f',
'info_dict': {
'title': '[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]'
2013-07-03 16:36:36 +02:00
}
}
_VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed\.php\?.*?file=([^&]+).*?'
2013-06-27 13:58:09 +02:00
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>',
2014-01-07 10:04:48 +01:00
webpage, 'title')
2013-06-27 13:58:09 +02:00
title = title.strip()
2013-11-18 13:56:45 +01:00
links = re.findall(r'\s(?:file|url):\s*["\']([^\'"]+)["\']', webpage)
links = map(compat_urllib_parse.unquote, links)
thumbnail = None
video_url = None
2013-06-27 13:58:09 +02:00
for link in links:
2013-11-18 13:56:45 +01:00
if link.endswith('.png'):
2013-06-27 13:58:09 +02:00
thumbnail = link
2013-11-18 13:56:45 +01:00
elif '/videos/' in link:
video_url = link
if not video_url:
raise ExtractorError(u'Could not find video URL')
2014-01-07 10:04:48 +01:00
ext = '.' + determine_ext(video_url)
2013-06-27 13:58:09 +02:00
if ext == title[-len(ext):]:
title = title[:-len(ext)]
2013-11-18 13:56:45 +01:00
return {
2013-06-27 13:58:09 +02:00
'id': video_id,
2013-11-18 13:56:45 +01:00
'url': video_url,
2013-06-27 13:58:09 +02:00
'title': title,
'thumbnail': thumbnail,
2013-11-18 13:56:45 +01:00
}