From 4e067ceabd705201a16b4c92cf4b23f3b990326c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Sun, 13 Jul 2014 10:15:40 +0200 Subject: updated specific configuration for parsing --- inc/3rdparty/site_config/standard/schneier.com.txt | 48 +++++++++++----------- 1 file changed, 24 insertions(+), 24 deletions(-) mode change 100644 => 100755 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 old mode 100644 new mode 100755 index 67181b65..0074a86a --- a/inc/3rdparty/site_config/standard/schneier.com.txt +++ b/inc/3rdparty/site_config/standard/schneier.com.txt @@ -1,25 +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 +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