From 3e8bf367fc25e4aaea48751f3454ec63c63270de Mon Sep 17 00:00:00 2001 From: timgws Date: Wed, 29 May 2013 10:42:09 +1000 Subject: Update mashable.com.txt Add the author & date of the mashable article. Make sure that the primary image is provided as part of the article. --- mashable.com.txt | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/mashable.com.txt b/mashable.com.txt index 2c5a14a..b6efb6c 100644 --- a/mashable.com.txt +++ b/mashable.com.txt @@ -1,4 +1,11 @@ -title: //header[@class='entry-title']/h1 -body: //div[@class='description'] +title: //h1[@class='title'] +author: substring-after(//span[@class='author_name'], 'By ') +date: //time + +body: //article strip: //div[@class='ytm-gallery-box'] -test_url: http://mashable.com/2011/12/05/india-wants-google-and-facebook-to-censor-user-content/ \ No newline at end of file +strip: //div[contains(@class, 'adsense')] +strip: //aside[contains(@class, 'social')] +strip_id_or_class: article-topics + +test_url: http://mashable.com/2013/05/24/myspace-architects-rebuilding-a-brand/ -- cgit v1.3.1