1 title: //div[@class="articleHeader"]/h1
2 author: //p[@class="byline"]
3 date: //p[contains(@class,"publishedDate")]/span
4 # remove the right menu
5 strip: //div[contains(@class,"aside")]
6 # remove some SharePoint webpart label junk
7 strip: //div[@id="ctl00_PlaceHolderMain_ArticleLeadField_label"]
8 strip: //div[@id="ctl00_PlaceHolderMain_PublishingPageContentField_label"]
9 test_url: http://forsvaret.no/aktuelt/publisert/nyheter/Sider/F5-fly-til-Skedsmo.aspx