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/reuters.com.txt | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/reuters.com.txt (limited to 'inc/3rdparty/site_config/standard/reuters.com.txt') diff --git a/inc/3rdparty/site_config/standard/reuters.com.txt b/inc/3rdparty/site_config/standard/reuters.com.txt new file mode 100644 index 00000000..c5c94a4f --- /dev/null +++ b/inc/3rdparty/site_config/standard/reuters.com.txt @@ -0,0 +1,10 @@ +title: //h1[@class='headline3'] +author: substring-after(//p[@class="byline"], 'By ') +date: //meta[@name="REVISION_DATE"]/@content +body: //div[@id='articleImage' or @id='frame_fd1fade'] | //span[@id='articleText'] | //div[@class='pageNavigation'] +strip: //li[@class='next'] +strip: //span[@class='articleLocation'] +prune: no +tidy: no + +test_url: http://www.reuters.com/article/2011/04/08/us-ivorycoast-killings-idUSTRE73732A20110408 \ No newline at end of file -- cgit v1.2.3