1 # include the lead graphic in the body, if available
2 body: //div[contains(concat(' ', normalize-space(@id), ' '), ' lead_graphic ')] | //div[contains(concat(' ', normalize-space(@itemprop), ' '), ' articleBody ')]
3 title: //h1[contains(concat(' ', normalize-space(@itemprop), ' '), ' headline ')]
4 date: //time[contains(concat(' ', normalize-space(@itemprop), ' '), ' datePublished ')]
6 strip_id_or_class: photo_credit
7 strip_id_or_class: photo_caption
8 strip_id_or_class: inline_gallery
9 # pull quote, often inside a blockquote element
11 strip_id_or_class: credit
12 strip_id_or_class: figcaption
13 strip_id_or_class: related_item
15 test_url: http://www.businessweek.com/magazine/buyback-insurance-a-good-deal-for-retailers-07282011.html
16 test_url: http://www.businessweek.com/articles/2012-06-06/american-pain-the-largest-u-dot-s-dot-pill-mills-rise-and-fall
17 test_url: http://www.businessweek.com/articles/2014-07-09/american-apparel-dov-charneys-sleazy-struggle-for-control