From: Philipp Hagemeister Date: Thu, 11 Jul 2013 10:11:00 +0000 (+0200) Subject: [ehow] improve minor bits X-Git-Url: http://git.bitcoin.ninja/?a=commitdiff_plain;h=81082e046eef7afa012076546b22e9f43d0c1e0f;p=youtube-dl [ehow] improve minor bits --- diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 4b67f333b..1c28cdbc9 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -13,7 +13,7 @@ from .dailymotion import DailymotionIE from .depositfiles import DepositFilesIE from .dotsub import DotsubIE from .dreisat import DreiSatIE -from .ehow import EhowIE +from .ehow import EHowIE from .eighttracks import EightTracksIE from .escapist import EscapistIE from .facebook import FacebookIE diff --git a/youtube_dl/extractor/ehow.py b/youtube_dl/extractor/ehow.py index a664b081a..1f0b3888e 100644 --- a/youtube_dl/extractor/ehow.py +++ b/youtube_dl/extractor/ehow.py @@ -1,10 +1,15 @@ import re -from ..utils import compat_urllib_parse + +from ..utils import ( + compat_urllib_parse, + determine_ext +) from .common import InfoExtractor -class EhowIE(InfoExtractor): - _VALID_URL = r'(?:http://)?(?:www\.)?ehow\.com/([^/]+)' +class EHowIE(InfoExtractor): + IE_NAME = u'eHow' + _VALID_URL = r'(?:https?://)?(?:www\.)?ehow\.com/[^/_?]*_(?P[0-9]+)' _TEST = { u'url': u'http://www.ehow.com/video_12245069_hardwood-flooring-basics.html', u'file': u'12245069.flv', @@ -18,9 +23,9 @@ class EhowIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group(1).split("_")[1] + video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - video_url = self._search_regex(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', + video_url = self._search_regex(r'(?:file|source)=(http[^\'"&]*)', webpage, u'video URL') final_url = compat_urllib_parse.unquote(video_url) thumbnail_url = self._search_regex(r'', @@ -28,11 +33,13 @@ class EhowIE(InfoExtractor): uploader = self._search_regex(r'', webpage, u'uploader') title = self._search_regex(r'', - webpage, u'Video title').replace(' | eHow','') + webpage, u'Video title').replace(' | eHow', '') description = self._search_regex(r'', webpage, u'video description') - ext = final_url.split('.')[-1] - return [{ + ext = determine_ext(final_url) + + return { + '_type': 'video', 'id': video_id, 'url': final_url, 'ext': ext, @@ -40,5 +47,5 @@ class EhowIE(InfoExtractor): 'thumbnail': thumbnail_url, 'description': description, 'uploader': uploader, - }] + }