From f35b84c807265f10024e52309b5cac4ca95a9510 Mon Sep 17 00:00:00 2001 From: "M.Yasoob Khalid" Date: Thu, 11 Jul 2013 14:25:14 +0500 Subject: [PATCH] added an IE for Ehow videos --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/ehow.py | 42 ++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+) create mode 100644 youtube_dl/extractor/ehow.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index e111df6f7..d2a71a6f1 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -13,6 +13,7 @@ from .dailymotion import DailymotionIE from .depositfiles import DepositFilesIE from .dotsub import DotsubIE from .dreisat import DreiSatIE +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 new file mode 100644 index 000000000..1844d8b00 --- /dev/null +++ b/youtube_dl/extractor/ehow.py @@ -0,0 +1,42 @@ +import re +from ..utils import compat_urllib_parse +from .common import InfoExtractor + + +class EhowIE(InfoExtractor): + _VALID_URL = r'(?:http://)?(?:www\.)?ehow\.com/([^/]+)' + _TEST = { + u'url': u'http://www.break.com/video/when-girls-act-like-guys-2468056', + u'file': u'2468056.mp4', + u'md5': u'a3513fb1547fba4fb6cfac1bffc6c46b', + u'info_dict': { + u"title": u"When Girls Act Like D-Bags" + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group(1).split("_")[1] + webpage = self._download_webpage(url, video_id) + video_url = self._search_regex(r'[^A-Za-z0-9]?(?:file|source)=(http[^\'"&]*)', + webpage, u'video URL') + final_url = compat_urllib_parse.unquote(video_url) + thumbnail_url = self._search_regex(r'', + webpage, u'thumbnail URL') + uploader = self._search_regex(r'', + webpage, u'uploader') + title = self._search_regex(r'', + webpage, u'Video title').replace(' | eHow','') + description = self._search_regex(r'', + webpage, u'video description') + ext = final_url.split('.')[-1] + return [{ + 'id': video_id, + 'url': final_url, + 'ext': ext, + 'title': title, + 'thumbnail': thumbnail_url, + 'description': description, + 'uploader': uploader, + }] +