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 --- inc/3rdparty/site_config/standard/forsvaret.no.txt | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/forsvaret.no.txt (limited to 'inc/3rdparty/site_config/standard/forsvaret.no.txt') diff --git a/inc/3rdparty/site_config/standard/forsvaret.no.txt b/inc/3rdparty/site_config/standard/forsvaret.no.txt old mode 100644 new mode 100755 index 3085c8f2..c1bd2bac --- a/inc/3rdparty/site_config/standard/forsvaret.no.txt +++ b/inc/3rdparty/site_config/standard/forsvaret.no.txt @@ -1,9 +1,9 @@ -title: //div[@class="articleHeader"]/h1 -author: //p[@class="byline"] -date: //p[contains(@class,"publishedDate")]/span -# remove the right menu -strip: //div[contains(@class,"aside")] -# remove some SharePoint webpart label junk -strip: //div[@id="ctl00_PlaceHolderMain_ArticleLeadField_label"] +title: //div[@class="articleHeader"]/h1 +author: //p[@class="byline"] +date: //p[contains(@class,"publishedDate")]/span +# remove the right menu +strip: //div[contains(@class,"aside")] +# remove some SharePoint webpart label junk +strip: //div[@id="ctl00_PlaceHolderMain_ArticleLeadField_label"] strip: //div[@id="ctl00_PlaceHolderMain_PublishingPageContentField_label"] test_url: http://forsvaret.no/aktuelt/publisert/nyheter/Sider/F5-fly-til-Skedsmo.aspx \ No newline at end of file -- cgit v1.2.3