1 # story has several pages, should be detected
2 body: //div[@id='storyBody']
3 body: //div[@id='article_body']
4 body: //div[@id='story_body']
6 title://h1[@id='article_headline']
9 author: //p[@class='author']/a
11 author: substring-after(//p[@class='byline'], 'By ')
14 date: //span[@class='published_date']
16 date: //span[@class='date']
18 date: substring-after(//div[contains(@class,'attributor')],'on')
19 strip_id_or_class: inset
20 strip: //p/span[@class='photoCredit']
23 strip_id_or_class: page_count
24 strip_id_or_class: tools
25 strip_id_or_class: pagination
27 single_page_link: //li[@id='stPrint']/a
29 test_url: http://www.businessweek.com/magazine/buyback-insurance-a-good-deal-for-retailers-07282011.html
30 test_url: http://www.businessweek.com/articles/2012-06-06/american-pain-the-largest-u-dot-s-dot-pill-mills-rise-and-fall