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/kicker.de.txt | 38 ++++++++++++------------- 1 file changed, 19 insertions(+), 19 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/kicker.de.txt (limited to 'inc/3rdparty/site_config/standard/kicker.de.txt') diff --git a/inc/3rdparty/site_config/standard/kicker.de.txt b/inc/3rdparty/site_config/standard/kicker.de.txt old mode 100644 new mode 100755 index 7d5daa4b..db4f63c4 --- a/inc/3rdparty/site_config/standard/kicker.de.txt +++ b/inc/3rdparty/site_config/standard/kicker.de.txt @@ -1,21 +1,21 @@ -# set body -body: //div[@id='ovArtikel'] - -# set title -title: //div[@id='ovArtikel']/h1 -# strip main title and leave sub title -strip: //div[@id='ovArtikel']/h1 - -date: //div[@class='publicdate'] - -#remove captions -strip: //*/div[@class='bu'] -strip: //*/div[@class='credit'] - -#remove adds -strip: //*/div[@class='ad-head'] -strip: //*/div[@class='linksebay'] - -# remove video content +# set body +body: //div[@id='ovArtikel'] + +# set title +title: //div[@id='ovArtikel']/h1 +# strip main title and leave sub title +strip: //div[@id='ovArtikel']/h1 + +date: //div[@class='publicdate'] + +#remove captions +strip: //*/div[@class='bu'] +strip: //*/div[@class='credit'] + +#remove adds +strip: //*/div[@class='ad-head'] +strip: //*/div[@class='linksebay'] + +# remove video content strip: //*/div[@class='ovVideo'] test_url: http://www.kicker.de/news/fussball/frauen/wmfr/frauen-weltmeisterschaft/2011/3/1123662/spielbericht_frankreich-frauen_deutschland-frauen.html \ No newline at end of file -- cgit v1.2.3