#metadata title://div[@class = 'Topper']/h1 author://div[@class = 'Topper']/h3 date://div[@class = 'Topper']/h6 body://div[@class = 'Core'] # clean up strip://div[@class = 'Topper']/h1 strip://div[@class = 'Topper']/h3 strip://div[@class = 'Topper']/h4 strip://div[@class = 'Topper']/h5 strip://div[@class = 'Topper']/h6 strip://br[@clear = 'all'] strip://div[@class = 'adCore'] strip://div[@class = 'BookR'] strip://div[@class = 'InfoBox'] test_url: http://bookforum.com/inprint/018_04/8595