diff options
author | Philipp Hagemeister <phihag@phihag.de> | 2013-11-18 13:56:45 +0100 |
---|---|---|
committer | Philipp Hagemeister <phihag@phihag.de> | 2013-11-18 13:56:45 +0100 |
commit | 9906d397a05de3c89fb0ba2d60c284c16cb72581 (patch) | |
tree | 82c257a0c7688d5777f19eb459e263d03cb3bf4d | |
parent | ae8f7871412ae9db40c5060d2d24e5a50f5fe9d0 (diff) |
[auengine] Simplify
-rw-r--r-- | youtube_dl/extractor/auengine.py | 30 |
1 files changed, 17 insertions, 13 deletions
diff --git a/youtube_dl/extractor/auengine.py b/youtube_dl/extractor/auengine.py index 0febbff4f..90dfa9a46 100644 --- a/youtube_dl/extractor/auengine.py +++ b/youtube_dl/extractor/auengine.py @@ -1,10 +1,10 @@ -import os.path import re from .common import InfoExtractor from ..utils import ( compat_urllib_parse, - compat_urllib_parse_urlparse, + determine_ext, + ExtractorError, ) class AUEngineIE(InfoExtractor): @@ -25,22 +25,26 @@ class AUEngineIE(InfoExtractor): 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 = [compat_urllib_parse.unquote(l) for l in links] + 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: - root, pathext = os.path.splitext(compat_urllib_parse_urlparse(link).path) - if pathext == '.png': + if link.endswith('.png'): thumbnail = link - elif pathext == '.mp4': - url = link - ext = pathext + elif '/videos/' in link: + video_url = link + if not video_url: + raise ExtractorError(u'Could not find video URL') + ext = u'.' + determine_ext(video_url) if ext == title[-len(ext):]: title = title[:-len(ext)] - ext = ext[1:] - return [{ + + return { 'id': video_id, - 'url': url, + 'url': video_url, 'ext': ext, 'title': title, 'thumbnail': thumbnail, - }] + } |