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/gp.se.txt | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/gp.se.txt (limited to 'inc/3rdparty/site_config/standard/gp.se.txt') diff --git a/inc/3rdparty/site_config/standard/gp.se.txt b/inc/3rdparty/site_config/standard/gp.se.txt new file mode 100755 index 00000000..158ae4ed --- /dev/null +++ b/inc/3rdparty/site_config/standard/gp.se.txt @@ -0,0 +1,11 @@ +body: //div[@id='articleContainer'] +author: //div[@id='articleContent']//div[contains(@class, 'byline')]//span[contains(@class, 'name fn')] +strip_id_or_class: toolbar +strip_id_or_class: ADad +strip_id_or_class: articleSerieWrapper +strip_id_or_class: articleFloatContainer +strip: //div[contains(@class, 'byline')]//img +prune: no + +test_url: http://www.gp.se/nyheter/bohuslan/1.2045564-styckade-mannen-hade-mordat-hustrun +test_url: http://www.gp.se/1.16560 \ No newline at end of file -- cgit v1.2.3