title: //div[@class='articleHead']//h1 author: //div[@class="author-name"]/a[1] body: //div[@class="main"] # remove 'From the Lab' and 'Recent posts' text strip: //div[@class='blogLabel'] # remove byline and meta info strip: //div[@class="article-meta"] strip: //div[@class="author-info"] #strip tags and categories strip: //div[@class="department"] #strip product cap links strip: //div[@class="cap-main"] strip: //div[@id="compare-lede"] test_url: http://www.techhive.com/article/3023383/streaming-media/vlc-for-apple-tv-review-goodbye-format-woes.html