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 --- .../site_config/standard/sydsvenskan.se.txt | 29 ++++++++++++++-------- 1 file changed, 18 insertions(+), 11 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/sydsvenskan.se.txt (limited to 'inc/3rdparty/site_config/standard/sydsvenskan.se.txt') diff --git a/inc/3rdparty/site_config/standard/sydsvenskan.se.txt b/inc/3rdparty/site_config/standard/sydsvenskan.se.txt old mode 100644 new mode 100755 index da6772aa..24ba1426 --- a/inc/3rdparty/site_config/standard/sydsvenskan.se.txt +++ b/inc/3rdparty/site_config/standard/sydsvenskan.se.txt @@ -1,11 +1,18 @@ -title: //h1 - -author: //a[contains(@href, '/sok/?')]/text() - -date: substring-after(//span[@class='date'], 'Publicerad ') - -body: //div[@class='two_column_left'] -strip_id_or_class: story -strip: //div[@class='leadText saplo:lead']/h5 - -test_url: http://www.sydsvenskan.se/kultur-och-nojen/-jag-vill-garna--stanna-- \ No newline at end of file +title: //h1 + +author: //a[contains(@href, '/sok/?')]/text() + +date: //meta[@name='bi3dPubDate']/@content + +body: (//div[contains(@class, 'slider_wrapper')])[1] | //div[@id='article_image' or @class='two_column_left'] +strip_id_or_class: story +strip_id_or_class: article_body_ad +strip: //div[@class='leadText saplo:lead']/h5 + +replace_string(
):

+ +prune: no + +test_url: http://www.sydsvenskan.se/malmo/allt-jag-ager-ligger-pa-botten/ +test_url: http://www.sydsvenskan.se/kultur-och-nojen/-jag-vill-garna--stanna-- +test_url: http://www.sydsvenskan.se/rss.xml \ No newline at end of file -- cgit v1.2.3