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/articles.courant.com.txt | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/articles.courant.com.txt (limited to 'inc/3rdparty/site_config/standard/articles.courant.com.txt') diff --git a/inc/3rdparty/site_config/standard/articles.courant.com.txt b/inc/3rdparty/site_config/standard/articles.courant.com.txt new file mode 100644 index 00000000..a08f2041 --- /dev/null +++ b/inc/3rdparty/site_config/standard/articles.courant.com.txt @@ -0,0 +1,11 @@ +title: //div[@class="mod-courantarticleheader mod-articleheader"]/h1 +date: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[@class="pubdate"] +author: //div[@class="mod-courantarticlebyline mod-articlebyline"]/span[3] + +strip_id_or_class: mod-article-byline +strip_id_or_class: mod-article-header +strip_id_or_class: mod-article-subtitle +#This leaves some crud after the article, but it's better than nothing. +#It would be ideal if we could set the body to every element matching //div[contains(@class, "mod-articletext")]/p, but it seems like body only takes the first matching element. + +test_url: http://articles.courant.com/2011-10-22/news/hc-green-drugsearch--1022-20111022_1_drugs-in-student-lockers-police-dogs-lockdown \ No newline at end of file -- cgit v1.2.3