From ac4d114214d820b20e18518a2dbc809337e39043 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20L=C5=93uillet?= Date: Fri, 6 Dec 2013 10:13:03 +0100 Subject: [add] new specific configuration files --- inc/3rdparty/site_config/standard/kicker.de.txt | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 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 new file mode 100644 index 00000000..7d5daa4b --- /dev/null +++ b/inc/3rdparty/site_config/standard/kicker.de.txt @@ -0,0 +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 +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