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/welt.de.txt | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/welt.de.txt (limited to 'inc/3rdparty/site_config/standard/welt.de.txt') diff --git a/inc/3rdparty/site_config/standard/welt.de.txt b/inc/3rdparty/site_config/standard/welt.de.txt new file mode 100644 index 00000000..6e4f828f --- /dev/null +++ b/inc/3rdparty/site_config/standard/welt.de.txt @@ -0,0 +1,22 @@ +# set body +tidy: no +body: //div[contains(@class, 'articleContent')] + +# remove clutter +strip: //div[@class='advertising'] +strip: //div[@class='themenalarm'] +strip: //div[contains(@class, 'inTextTeaser')] + +# remove captions +strip: //span[@class='copyRight'] + +# remove photo galleries and extras +strip: //div[contains(@class, 'textGallery')] +strip: //div[contains(@class, 'videoGallery')] +strip: //div[contains(@class, 'imageGallery')] +strip: //div[contains(@class, 'openContent')] + +# remove comments +strip: //div[@id = 'writeComment'] + +test_url: http://www.welt.de/vermischtes/weltgeschehen/article11050589/27-Bergleute-in-neuseelaendischer-Mine-vermisst.html \ No newline at end of file -- cgit v1.2.3