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/faz.net.txt | 30 +++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/faz.net.txt (limited to 'inc/3rdparty/site_config/standard/faz.net.txt') diff --git a/inc/3rdparty/site_config/standard/faz.net.txt b/inc/3rdparty/site_config/standard/faz.net.txt new file mode 100644 index 00000000..4fe5968b --- /dev/null +++ b/inc/3rdparty/site_config/standard/faz.net.txt @@ -0,0 +1,30 @@ +# Title +title: //p[@class='Content HeadlineShort'] + +# Authors +# some are known and have a link, others don't +author: substring-after(//span[@class='Autor'], 'Von') + +# Date +date: //span[@class='Datum'] + +# Body +body: //div[@class='Artikel'] + +# Removements before body text +strip: //div[@class='Breadcrumbs'] +strip: //div[@class='QuickSearchBox'] +strip: //div[@class='FAZArtikelEinleitung'] +strip: //div[@class='FAZArtikelReiter'] +strip: //div[@class='clear'] + +# General removements +strip: //span[@class='Bildnachweis'] + +# Removements after body text +strip: //div[@class='ArtikelAbbinder'] +strip: //div[@class='ArtikelKommentieren Artikelfuss GETS;tk;boxen.top-lesermeinungen;tp;content'] +strip: //div[@class='FAZArtikelKommentare FAZArtikelContent'] +strip: //div[@class='FAZArtikelFunktionen'] +strip: //div[@id='FAZContentRight'] +test_url: http://www.faz.net/aktuell/gesellschaft/ehe-haltbarkeitsformel-verliebe-dich-oft-verlobe-dich-selten-heirate-vielleicht-11685306.html \ No newline at end of file -- cgit v1.2.3