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 --- .../site_config/standard/nintendoworldreport.com.txt | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/nintendoworldreport.com.txt (limited to 'inc/3rdparty/site_config/standard/nintendoworldreport.com.txt') diff --git a/inc/3rdparty/site_config/standard/nintendoworldreport.com.txt b/inc/3rdparty/site_config/standard/nintendoworldreport.com.txt new file mode 100644 index 00000000..409a8977 --- /dev/null +++ b/inc/3rdparty/site_config/standard/nintendoworldreport.com.txt @@ -0,0 +1,13 @@ +body: //div[@id="main"] +title: //div[@id="main"]/h3 + +# Remove ‘Review’ and ‘Wii’. +strip: //div[@class="badge"] + +# Remove duplicate title and country flag. +strip: //h3 + +# Commented out below are attempts to extract the author and date, which did not work. +# author: //p[@class="extra "]/a +# date: //p[@class="extra "]/span[@class="when"] +test_url: http://www.nintendoworldreport.com/review/28400 \ No newline at end of file -- cgit v1.2.3