1 author: //p[@class='mastname']
3 body: //div[@class='indivbody']
4 date: //div[@class='indivbody']/h2[1]
6 # Remove blog title. Specify first occurrence in case h1 is used in article
7 strip: //div[@class='indivbody']/h1[1]
9 # Remove blog description (the first p element)
10 strip: //div[@class='indivbody']/p[1]
12 # Remove navigation (second p element)
13 strip: //div[@class='indivbody']/p[2]
15 # Remove duplicate of article title. Specify first occurrence in case h3 is used in article
16 strip: //div[@class='indivbody']/h3[1]
18 # Remove publishing date, it's extracted by rule above
19 strip: //div[@class='indivbody']/h2[1]
21 # Remove duplicate of date at end, and newsletter signup
22 strip: //p[@class='posted']
25 test_url: http://www.schneier.com/blog/archives/2010/12/security_in_202.html