# TIDY #tidy: no # PRUNE #prune: no # SINGLE PAGE single_page_link: //div[@class='showlinks']/a # TITLE title: //h1[@class="title"] # AUTHOR author: //div[contains(@class,"field-field-article-display-authors")]/div/div/a/text() # DATE date: //div[contains(@class,"field-field-article-issue")]/div/div/a/text() | //span[@class="date-display-single"] # BODY body: //div[contains(@class,"content-resize")] # Remove clutter strip: //div[@class="article-sidebar"] strip: //div[@class="showlinks"] strip: //div[contains(@class,"premium-box")] strip: //div[contains(@class,"premium-box")] strip: //table[contains(@border,"2")] # Fix picture captions wrap_in(small): //p/img/following-sibling::em wrap_in(small): //p[img]/text() # Fix sub-headlines wrap_in(h3): //div[contains(@class,"field-field-article-subtitle")]/div/div/text() test_url: http://www.foreignaffairs.com/articles/138810/pierre-n-leval/the-long-arm-of-international-law