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/aftonbladet.se.txt | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/aftonbladet.se.txt (limited to 'inc/3rdparty/site_config/standard/aftonbladet.se.txt') diff --git a/inc/3rdparty/site_config/standard/aftonbladet.se.txt b/inc/3rdparty/site_config/standard/aftonbladet.se.txt new file mode 100755 index 00000000..b6c576a8 --- /dev/null +++ b/inc/3rdparty/site_config/standard/aftonbladet.se.txt @@ -0,0 +1,13 @@ +author: //article//address[contains(@class, 'author')] +body: //article[.//div[contains(@class, 'abBodyText')]]//*[contains(@class, 'abLeadText') or contains(@class, 'abBodyText') or contains(@class, 'abImageBlock') or contains(@class, 'abIGSatellite')] + +strip: //address//img +strip: //footer +strip_id_or_class: abSticky + +prune: no + +test_url: http://www.aftonbladet.se/sportbladet/hockey/sverige/allsvenskan/article17498194.ab +test_url: http://www.aftonbladet.se/debatt/article16207536.ab +test_url: http://www.aftonbladet.se/debatt/debattamnen/politik/article17483377.ab +test_url: http://www.aftonbladet.se/rss.xml \ No newline at end of file -- cgit v1.2.3