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/www1.folha.uol.com.br.txt | 28 +++++++++++----------- 1 file changed, 14 insertions(+), 14 deletions(-) mode change 100644 => 100755 inc/3rdparty/site_config/standard/www1.folha.uol.com.br.txt (limited to 'inc/3rdparty/site_config/standard/www1.folha.uol.com.br.txt') diff --git a/inc/3rdparty/site_config/standard/www1.folha.uol.com.br.txt b/inc/3rdparty/site_config/standard/www1.folha.uol.com.br.txt old mode 100644 new mode 100755 index 0846be2c..97a5c19d --- a/inc/3rdparty/site_config/standard/www1.folha.uol.com.br.txt +++ b/inc/3rdparty/site_config/standard/www1.folha.uol.com.br.txt @@ -1,15 +1,15 @@ -body://div[@id='articleNew'] -strip://div[@id='articleBy'] -strip://div[@id='articleDate'] -strip://td[@class='articleGraphicCredit'] -strip://h1 -strip://div[@id='articleEnd'] -strip://p[@class='tagline'] -strip://div[@class='openBox adslibraryArticle'] -strip_id_or_class:ad-180x150-1 - - -title: //div[@id="articleNew"]/h1 -author: //div[@id="articleBy"]/p/b -date: substring-before(//div[@id="articleDate"], "-") +body://div[@id='articleNew'] +strip://div[@id='articleBy'] +strip://div[@id='articleDate'] +strip://td[@class='articleGraphicCredit'] +strip://h1 +strip://div[@id='articleEnd'] +strip://p[@class='tagline'] +strip://div[@class='openBox adslibraryArticle'] +strip_id_or_class:ad-180x150-1 + + +title: //div[@id="articleNew"]/h1 +author: //div[@id="articleBy"]/p/b +date: substring-before(//div[@id="articleDate"], "-") test_url: http://www1.folha.uol.com.br/mundo/1115805-ex-ditador-argentino-videla-e-condenado-a-50-anos-de-prisao.shtml \ No newline at end of file -- cgit v1.2.3