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/politiken.dk.txt | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/politiken.dk.txt (limited to 'inc/3rdparty/site_config/standard/politiken.dk.txt') diff --git a/inc/3rdparty/site_config/standard/politiken.dk.txt b/inc/3rdparty/site_config/standard/politiken.dk.txt old mode 100644 new mode 100755 index 8deecbca..b13f8f87 --- a/inc/3rdparty/site_config/standard/politiken.dk.txt +++ b/inc/3rdparty/site_config/standard/politiken.dk.txt @@ -1,13 +1,13 @@ -# 21/10-2011: -# Added Author+Date -# Remove fakta-boks if found -# Deleted 'Læs også...' filter -# - Change in markup caused it to strip too much. - -author://span[@class='autor-name'] -date:substring-after(//div[@class='art-created'], ' ') -title: //h1[contains(@class, 'stor-type')] -body: //div[@id='art-body'] -strip: //div[@class='art-fakta article-box'] +# 21/10-2011: +# Added Author+Date +# Remove fakta-boks if found +# Deleted 'Læs ogsÃ¥...' filter +# - Change in markup caused it to strip too much. + +author://span[@class='autor-name'] +date:substring-after(//div[@class='art-created'], ' ') +title: //h1[contains(@class, 'stor-type')] +body: //div[@id='art-body'] +strip: //div[@class='art-fakta article-box'] test_url: http://politiken.dk/kultur/boger/skonlitteratur_boger/ECE1426386/makabre-tegneserie-zombier-aeder-alt-levende/ \ No newline at end of file -- cgit v1.2.3