2014-07-13 10:15:40 +02:00
|
|
|
# story has several pages, should be detected
|
|
|
|
|
body: //div[@id='storyBody']
|
|
|
|
|
body: //div[@id='article_body']
|
|
|
|
|
body: //div[@id='story_body']
|
|
|
|
|
|
|
|
|
|
title://h1[@id='article_headline']
|
|
|
|
|
|
|
|
|
|
# article author
|
|
|
|
|
author: //p[@class='author']/a
|
|
|
|
|
# story author(s)
|
|
|
|
|
author: substring-after(//p[@class='byline'], 'By ')
|
|
|
|
|
|
|
|
|
|
# article date
|
|
|
|
|
date: //span[@class='published_date']
|
|
|
|
|
# story date
|
|
|
|
|
date: //span[@class='date']
|
|
|
|
|
|
|
|
|
|
date: substring-after(//div[contains(@class,'attributor')],'on')
|
|
|
|
|
strip_id_or_class: inset
|
|
|
|
|
strip: //p/span[@class='photoCredit']
|
|
|
|
|
strip: //h1
|
|
|
|
|
|
|
|
|
|
strip_id_or_class: page_count
|
|
|
|
|
strip_id_or_class: tools
|
|
|
|
|
strip_id_or_class: pagination
|
|
|
|
|
|
|
|
|
|
single_page_link: //li[@id='stPrint']/a
|
|
|
|
|
|
|
|
|
|
test_url: http://www.businessweek.com/magazine/buyback-insurance-a-good-deal-for-retailers-07282011.html
|
2013-12-06 10:13:03 +01:00
|
|
|
test_url: http://www.businessweek.com/articles/2012-06-06/american-pain-the-largest-u-dot-s-dot-pill-mills-rise-and-fall
|
