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/technologizer.com.txt | 5 +++++ 1 file changed, 5 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/technologizer.com.txt (limited to 'inc/3rdparty/site_config/standard/technologizer.com.txt') diff --git a/inc/3rdparty/site_config/standard/technologizer.com.txt b/inc/3rdparty/site_config/standard/technologizer.com.txt new file mode 100755 index 00000000..179bf5a6 --- /dev/null +++ b/inc/3rdparty/site_config/standard/technologizer.com.txt @@ -0,0 +1,5 @@ +next_page_link: //a[contains(., 'NEXT PAGE')] +# following::node() selects text nodes too whereas following::* selects only elements. +strip: //span[@class='pageo']/following::node() +strip: //span[@class='pageo'] +test_url: http://technologizer.com/2010/03/08/the-secret-origin-of-windows/ \ No newline at end of file -- cgit v1.2.3