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/neh.gov.txt | 30 +++++++++++++-------------- 1 file changed, 15 insertions(+), 15 deletions(-) mode change 100644 => 100755 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 old mode 100644 new mode 100755 index 45136a2b..e7cc4313 --- a/inc/3rdparty/site_config/standard/neh.gov.txt +++ b/inc/3rdparty/site_config/standard/neh.gov.txt @@ -1,17 +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'] +#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