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/goal.com.txt | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/goal.com.txt (limited to 'inc/3rdparty/site_config/standard/goal.com.txt') diff --git a/inc/3rdparty/site_config/standard/goal.com.txt b/inc/3rdparty/site_config/standard/goal.com.txt new file mode 100644 index 00000000..075c4d2b --- /dev/null +++ b/inc/3rdparty/site_config/standard/goal.com.txt @@ -0,0 +1,16 @@ +title: //div[@id='article_headline']//h1 +date: //div[contains(@class, 'articleDate')]//h4 +body: //div[@id='article_headline']/h2 | //div[@id='large_article_image' or @id='article_content'] + +strip_id_or_class: relatedLinksBox +strip_id_or_class: betting-widget +strip_image_src: install_flash.gif + +strip: //table[contains(@style, 'float: right; width: 285px;')] +strip: //div[@class='caption'] + +tidy: no +prune: no + +test_url: http://www.goal.com/en-gb/news/3284/euro-2012/2012/05/31/3139032/video-profile-back-to-his-very-best-for-bayern-frances-flair-and- +test_url: http://www.goal.com/en-gb/news/3284/euro-2012/2012/05/31/3139869/lampard-injury-a-bitter-blow-for-england-and-sorry-way-to# \ No newline at end of file -- cgit v1.2.3