From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- schneier.com.txt | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 schneier.com.txt (limited to 'schneier.com.txt') diff --git a/schneier.com.txt b/schneier.com.txt new file mode 100644 index 0000000..0074a86 --- /dev/null +++ b/schneier.com.txt @@ -0,0 +1,25 @@ +author: //p[@class='mastname'] + +body: //div[@class='indivbody'] +date: //div[@class='indivbody']/h2[1] + +# Remove blog title. Specify first occurrence in case h1 is used in article +strip: //div[@class='indivbody']/h1[1] + +# Remove blog description (the first p element) +strip: //div[@class='indivbody']/p[1] + +# Remove navigation (second p element) +strip: //div[@class='indivbody']/p[2] + +# Remove duplicate of article title. Specify first occurrence in case h3 is used in article +strip: //div[@class='indivbody']/h3[1] + +# Remove publishing date, it's extracted by rule above +strip: //div[@class='indivbody']/h2[1] + +# Remove duplicate of date at end, and newsletter signup +strip: //p[@class='posted'] + +# Leave date at top +test_url: http://www.schneier.com/blog/archives/2010/12/security_in_202.html \ No newline at end of file -- cgit v1.3.1