body: //div[@class="story-body"] # for video entries body: //div[contains(@class, "videoInStory") or @id="meta-information"] title: //h1[@class="story-header"] date: //span[@class="story-date"]/span[@class='date'] # for sport site date: //meta[@name='DCTERMS.created']/@content author: //div[@id='headline']//span[@class='byline-name'] # recipes, e.g. http://www.bbc.co.uk/food/recipes/mymincepies_71055 body: //div[contains(@class, 'hrecipe')]//div[@id='subcolumn-1'] #strip: //div[@class="story-feature narrow"] #strip: //div[@class="story-feature wide"] #strip: //div[@class="story-feature dslideshow-enclosure"] strip: //div[contains(@class, "story-feature")] strip: //span[@class="story-date"] #strip: //div[@class="caption body-narrow-width"] strip: //div[@class="warning"]//p strip: //div[@id='page-bookmark-links-head'] strip: //object strip: //div[contains(@class, "bbccom_advert_placeholder")] strip: //div[contains(@class, "embedded-hyper")] strip: //div[contains(@class, 'market-data')] strip: //a[contains(@class, 'hidden')] strip: //div[contains(@class, 'hypertabs')] strip: //div[contains(@class, 'related')] strip: //form[@id='comment-form'] strip: //div[contains(@class, 'comment-introduction')] strip: //div[contains(@class, 'share-tools')] strip: //div[@id='also-related-links'] replace_string(