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/neh.gov.txt | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/neh.gov.txt (limited to 'inc/3rdparty/site_config/standard/neh.gov.txt') diff --git a/inc/3rdparty/site_config/standard/neh.gov.txt b/inc/3rdparty/site_config/standard/neh.gov.txt new file mode 100644 index 00000000..45136a2b --- /dev/null +++ b/inc/3rdparty/site_config/standard/neh.gov.txt @@ -0,0 +1,17 @@ +#host configuration should be http://www.neh.gov/news/humanities/ + + +#meta data +title:substring-after(substring-after(//title,':'),':') +author:substring-after(//h2[@class = 'subHead'],'By') +date:substring-before(substring-after(//title,':'),':') + +#img and caption handling +wrap_in(small)://div[@id = 'mainContent']/table/descendant::p/descendant::text() +wrap_in(fieldset)://div[@id = 'mainContent']/table + +# clean up +strip: //table[@class = 'marginpaddingTop'] +strip: //h2[@class = 'subHead'] + +test_url: http://www.neh.gov/news/humanities/2011-11/IslamicScholar.html \ No newline at end of file -- cgit v1.2.3