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 --- .../site_config/standard/brasil.elpais.com.txt | 23 ++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100755 inc/3rdparty/site_config/standard/brasil.elpais.com.txt (limited to 'inc/3rdparty/site_config/standard/brasil.elpais.com.txt') diff --git a/inc/3rdparty/site_config/standard/brasil.elpais.com.txt b/inc/3rdparty/site_config/standard/brasil.elpais.com.txt new file mode 100755 index 00000000..0b8feb6a --- /dev/null +++ b/inc/3rdparty/site_config/standard/brasil.elpais.com.txt @@ -0,0 +1,23 @@ +title: //meta[@name='DC.title']/@content +title: //div[contains(@class, 'cabecera_noticia')]//h1 +date: //meta[@name='DC.date']/@content +date: //meta[@name='date']/@content +body: //div[@class='columna_texto'] +body: //div[@id='cuerpo_noticia'] +body: //div[@class='estructura_2col_1zq']//div[@class='margen_n'] + +prune: no + +strip_id_or_class: disposicion_vertical +strip_id_or_class: ampliar_foto +strip_id_or_class: utilidades +strip_id_or_class: info_relacionada +strip_id_or_class: m-kiosko +strip_id_or_class: info_complementa + +strip: //p[@class='nota_pie'] +strip: //div[starts-with(@id, 'sumario') and contains(., 'más información')] +strip: //div[@id='coment' or @id='foros_not'] + +test_url: http://elpais.com/elpais/2012/02/06/gente/1328526783_491687.html +test_url: http://www.elpais.com/articulo/cultura/mano/retrato/materia/elpepicul/20120207elpepicul_2/Tes -- cgit v1.2.3