# Contrepoints.org # As of 2015-04, it's a wordpress-powered website. title: //h1[contains(concat(' ',normalize-space(@class),' '),' page-title ')]//span[contains(concat(' ',normalize-space(@class),' '),' inner-text ')] date: //time[contains(concat(' ',normalize-space(@class),' '),' art-date ')] author: //h1[contains(concat(' ',normalize-space(@class),' '),' author-name ')] body: //article[contains(concat(' ',normalize-space(@class),' '),' plain-art ')] # no toolbar, meta, etc, but misses excerpt # body: //div[contains(concat(' ',normalize-space(@class),' '),' entry ')] # Thus, we need to strip useless elements from the "plain-art" strip: //div[contains(concat(' ',normalize-space(@class),' '),' plain-post-topbar ')] strip: //div[contains(concat(' ',normalize-space(@class),' '),' single-type-block ')] strip: //header[contains(concat(' ',normalize-space(@class),' '),' entry-header ')] # And no pruning is needed because we stripped unwanted elements. prune: no test_url: http://www.contrepoints.org/2015/04/25/205709-leconomie-selon-ray-dalio test_url: http://www.contrepoints.org/2015/04/25/205734-huile-et-gaz-de-schiste-revolution-durable