blob: ac49aef92a4dfc8123a63d51c30de45633125802 (
plain) (
tree)
|
|
# main sportsillustrated.com articles
body: //div[@id="cnnStoryContent"]
title: //div[@id="cnnStoryHeadline"]//h1
author: //div[@id="cnnSubBanner"]//strong
date: substring-after(//div[@id="cnnTimeStamp"], "Updated: ")
date: substring-after(//div[@id="cnnTimeStamp"], "Posted: ")
# kill ugly font buttons
strip: //div[@id="cnnSCFontButtons"]
# kill misc filler videos & etc
strip: //div[@class="cnnDivideContent"]
strip: //*[@class="cnnTMbox"]
# si vault articles
# -------------
body: //div[@class="siv_artPara"]
title: //div[@class="siv_artHeader"]//h1
author: //div[@class="byline"]
date: //div[@class="date"]
next_page_link: //div[@id='cnnStoryContinue']/a
strip_id_or_class: cnnstorypagination
test_url: http://cnnsi.com/2012/writers/peter_king/01/08/wild.card.round/index.html
|