From 03ff2cc1c49c82daf2218b76e169c2d679447f03 Mon Sep 17 00:00:00 2001 From: oteng Date: Mon, 5 Jan 2015 16:28:24 +0000 Subject: [PATCH] [Auengine] corrected extractions logic The way the video download url was been extracted was not working well so i change it for it to extract the correct url --- .gitignore | 2 ++ youtube_dl/extractor/auengine.py | 18 +++++++----------- 2 files changed, 9 insertions(+), 11 deletions(-) diff --git a/.gitignore b/.gitignore index 86312d4e4..0422adf44 100644 --- a/.gitignore +++ b/.gitignore @@ -31,3 +31,5 @@ updates_key.pem test/testdata .tox youtube-dl.zsh +.idea +.idea/* \ No newline at end of file diff --git a/youtube_dl/extractor/auengine.py b/youtube_dl/extractor/auengine.py index 014a21952..17c3ad2ef 100644 --- a/youtube_dl/extractor/auengine.py +++ b/youtube_dl/extractor/auengine.py @@ -29,17 +29,12 @@ class AUEngineIE(InfoExtractor): webpage = self._download_webpage(url, video_id) title = self._html_search_regex(r'(?P<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: + video_url = re.findall(r'http://\w+.auengine.com/vod/.*[^\W]', webpage) + video_url = map(compat_urllib_parse.unquote, video_url)[0] + thumbnail = re.findall(r'http://\w+.auengine.com/thumb/.*[^\W]', webpage) + thumbnail = map(compat_urllib_parse.unquote, thumbnail)[0] + + if video_url == "" and thumbnail =="": raise ExtractorError('Could not find video URL') ext = '.' + determine_ext(video_url) if ext == title[-len(ext):]: @@ -52,3 +47,4 @@ class AUEngineIE(InfoExtractor): 'thumbnail': thumbnail, 'http_referer': 'http://www.auengine.com/flowplayer/flowplayer.commercial-3.2.14.swf', } +