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 --- .../site_config/standard/articles.courant.com.txt | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) mode change 100644 => 100755 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 old mode 100644 new mode 100755 index a08f2041..984d81de --- a/inc/3rdparty/site_config/standard/articles.courant.com.txt +++ b/inc/3rdparty/site_config/standard/articles.courant.com.txt @@ -1,11 +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. +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