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/scilogs.de.txt | 15 +++++++++++++++ 1 file changed, 15 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/scilogs.de.txt (limited to 'inc/3rdparty/site_config/standard/scilogs.de.txt') diff --git a/inc/3rdparty/site_config/standard/scilogs.de.txt b/inc/3rdparty/site_config/standard/scilogs.de.txt new file mode 100755 index 00000000..b24d7844 --- /dev/null +++ b/inc/3rdparty/site_config/standard/scilogs.de.txt @@ -0,0 +1,15 @@ +title: //h1 +author: //div[@class='date']/a +date: substring-after(//div[@class='date'], ',') +body: //div[@class='entrybody'] + +strip_id_or_class: socialshareprivacy +strip: //div[@class='entrybody']/br[1] + +# Strip related articles +# 'p'-Tag strips 'Ähnliche Artikel: ' (
tags become

) +strip: //div[@class='entrybody']/p[last()] +strip: //div[@class='entrybody']/ul[last()] + +convert_double_br_tags: yes +test_url: http://www.scilogs.de/wblogs/blog/formbar/fusion/2012-10-08/rundgang-durch-deutschlands-gr-tes-fusionsexperiment \ No newline at end of file -- cgit v1.2.3