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/politico.com.txt | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/politico.com.txt (limited to 'inc/3rdparty/site_config/standard/politico.com.txt') diff --git a/inc/3rdparty/site_config/standard/politico.com.txt b/inc/3rdparty/site_config/standard/politico.com.txt new file mode 100644 index 00000000..121fd5b9 --- /dev/null +++ b/inc/3rdparty/site_config/standard/politico.com.txt @@ -0,0 +1,13 @@ +title://div[contains(@class, "article")]/h1 +body://div[contains(@class,"story-text")] + +# Why doesn't this work? next_page_link://ul[contains(@class,"pagination")]/li/a[@rel="next"] + +next_page_link://ul[contains(@class,"pagination")]/li[contains(@class, "current")]/following-sibling::node()/a +date://meta[@name="publish_date"]/@content + +strip://div[contains(@class, "breadcrumbs")] +strip://a[contains(@class, "hidden")] +strip://div[contains(@class, "story-embed")] +strip://div[contains(@class, "story-text")]//p/a[contains(text(), "Also on POLITICO:")]/.. +test_url: http://www.politico.com/news/stories/0712/78105.html \ No newline at end of file -- cgit v1.2.3