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 --- .../standard/sz-magazin.sueddeutsche.de.txt | 26 +++++++++++----------- 1 file changed, 13 insertions(+), 13 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/sz-magazin.sueddeutsche.de.txt (limited to 'inc/3rdparty/site_config/standard/sz-magazin.sueddeutsche.de.txt') diff --git a/inc/3rdparty/site_config/standard/sz-magazin.sueddeutsche.de.txt b/inc/3rdparty/site_config/standard/sz-magazin.sueddeutsche.de.txt old mode 100644 new mode 100755 index c3e34977..e058032c --- a/inc/3rdparty/site_config/standard/sz-magazin.sueddeutsche.de.txt +++ b/inc/3rdparty/site_config/standard/sz-magazin.sueddeutsche.de.txt @@ -1,15 +1,15 @@ -title: //h1 -body://div[@class='drucken'] -author: substring-after(//span[@class='autor'], 'Von ') -author: //span[@class='autor'] - -single_page_link://a[contains(@href, '/drucken/')] -convert_double_br_tags:yes - -dissolve://div[@class='vorspann'] - -strip://h1 -strip_id_or_class: klassifizierung -strip_id_or_class: source +title: //h1 +body://div[@class='drucken'] +author: substring-after(//span[@class='autor'], 'Von ') +author: //span[@class='autor'] + +single_page_link://a[contains(@href, '/drucken/')] +convert_double_br_tags:yes + +dissolve://div[@class='vorspann'] + +strip://h1 +strip_id_or_class: klassifizierung +strip_id_or_class: source strip_id_or_class: autor test_url: http://sz-magazin.sueddeutsche.de/texte/anzeigen/37567 \ No newline at end of file -- cgit v1.2.3