From ac4d114214d820b20e18518a2dbc809337e39043 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Fri, 6 Dec 2013 10:13:03 +0100 Subject: [add] new specific configuration files --- inc/3rdparty/site_config/standard/schneier.com.txt | 25 ++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/schneier.com.txt (limited to 'inc/3rdparty/site_config/standard/schneier.com.txt') diff --git a/inc/3rdparty/site_config/standard/schneier.com.txt b/inc/3rdparty/site_config/standard/schneier.com.txt new file mode 100644 index 00000000..67181b65 --- /dev/null +++ b/inc/3rdparty/site_config/standard/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 v1.2.3