X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fauengine.py;h=a1b666be0a4ce1610cfad79f5393ec23a9427bc8;hb=8a1b9b068ef80c81e68bc87edb5219caa4381652;hp=94322cf595d0b1cc471e6186512ff799c3f55be4;hpb=e4decf2750ee3b0cfdb6c866a1496d0dd96914fa;p=youtube-dl diff --git a/youtube_dl/extractor/auengine.py b/youtube_dl/extractor/auengine.py index 94322cf59..a1b666be0 100644 --- a/youtube_dl/extractor/auengine.py +++ b/youtube_dl/extractor/auengine.py @@ -1,38 +1,50 @@ -import os.path +from __future__ import unicode_literals + import re from .common import InfoExtractor +from ..compat import compat_urllib_parse from ..utils import ( - compat_urllib_parse, - compat_urllib_parse_urlparse, + determine_ext, + ExtractorError, + remove_end, ) -class AuengineIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?auengine\.com/embed.php\?.*?file=([^&]+).*?' + +class AUEngineIE(InfoExtractor): + _VALID_URL = r'http://(?:www\.)?auengine\.com/embed\.php\?.*?file=(?P[^&]+).*?' + + _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): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1) + video_id = self._match_id(url) + webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'(?P<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] - for link in links: - root, pathext = os.path.splitext(compat_urllib_parse_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, + title = self._html_search_regex( + r'\s*(?P<title>.+?)\s*', webpage, 'title') + video_urls = re.findall(r'http://\w+.auengine.com/vod/.*[^\W]', webpage) + video_url = compat_urllib_parse.unquote(video_urls[0]) + thumbnails = re.findall(r'http://\w+.auengine.com/thumb/.*[^\W]', webpage) + thumbnail = compat_urllib_parse.unquote(thumbnails[0]) + + if not video_url: + raise ExtractorError('Could not find video URL') + + ext = '.' + determine_ext(video_url) + title = remove_end(title, 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', + }