From 90a1a78b1e2f4d40e1d9b8e6f46aca129a9d7bcf Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Mon, 27 Oct 2014 06:46:13 +0100 Subject: updated site_config --- inc/3rdparty/site_config/standard/cn.reuters.com.txt | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'inc/3rdparty/site_config/standard/cn.reuters.com.txt') diff --git a/inc/3rdparty/site_config/standard/cn.reuters.com.txt b/inc/3rdparty/site_config/standard/cn.reuters.com.txt index b3878662..28f10472 100755 --- a/inc/3rdparty/site_config/standard/cn.reuters.com.txt +++ b/inc/3rdparty/site_config/standard/cn.reuters.com.txt @@ -1,5 +1,9 @@ title: //div[@id='maincontent']//h1 body: //div[@id='resizeableText'] +single_page_link: concat(//link[@rel='canonical']/@href, '?sp=true') + test_url: http://cn.reuters.com/article/CNAnalysesNews/idCNKBS0FF0NM20140710 -test_url: http://cn.reuters.feedsportal.com/CNAnalysesNews \ No newline at end of file +test_url: http://cn.reuters.feedsportal.com/CNAnalysesNews +# multipage link +test_url: http://cn.reuters.com/article/idCNKBS0FF0UL20140710 \ No newline at end of file -- cgit v1.2.3