mirror of
https://github.com/ytdl-org/youtube-dl
synced 2024-11-18 08:19:27 +01:00
1cc79574fc
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail. · Use _match_id consistently whenever possible · Fix some outdated tests · Use consistent valid URL (always match the whole protocol, no ^ at start required) · Use modern test definitions
55 lines
1.7 KiB
Python
55 lines
1.7 KiB
Python
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
from ..compat import compat_urllib_parse
|
|
from ..utils import (
|
|
determine_ext,
|
|
ExtractorError,
|
|
)
|
|
|
|
|
|
class AUEngineIE(InfoExtractor):
|
|
_VALID_URL = r'http://(?:www\.)?auengine\.com/embed\.php\?.*?file=(?P<id>[^&]+).*?'
|
|
|
|
_TEST = {
|
|
'url': 'http://auengine.com/embed.php?file=lfvlytY6&w=650&h=370',
|
|
'md5': '48972bdbcf1a3a2f5533e62425b41d4f',
|
|
'info_dict': {
|
|
'id': 'lfvlytY6',
|
|
'ext': 'mp4',
|
|
'title': '[Commie]The Legend of the Legendary Heroes - 03 - Replication Eye (Alpha Stigma)[F9410F5A]'
|
|
}
|
|
}
|
|
|
|
def _real_extract(self, url):
|
|
video_id = self._match_id(url)
|
|
|
|
webpage = self._download_webpage(url, video_id)
|
|
title = self._html_search_regex(r'<title>(?P<title>.+?)</title>', webpage, '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('Could not find video URL')
|
|
ext = '.' + determine_ext(video_url)
|
|
if ext == title[-len(ext):]:
|
|
title = title[:-len(ext)]
|
|
|
|
return {
|
|
'id': video_id,
|
|
'url': video_url,
|
|
'title': title,
|
|
'thumbnail': thumbnail,
|
|
'http_referer': 'http://www.auengine.com/flowplayer/flowplayer.commercial-3.2.14.swf',
|
|
}
|