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/theatlantic.com.txt | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/theatlantic.com.txt (limited to 'inc/3rdparty/site_config/standard/theatlantic.com.txt') diff --git a/inc/3rdparty/site_config/standard/theatlantic.com.txt b/inc/3rdparty/site_config/standard/theatlantic.com.txt new file mode 100644 index 00000000..267fd39c --- /dev/null +++ b/inc/3rdparty/site_config/standard/theatlantic.com.txt @@ -0,0 +1,18 @@ +title: //div[@id='article']/h1 +title: //h1 + +body: //div[@class='articleText'] +body: //div[@class='articleContent'] +body: //div[@id='article'] +date: //*[contains(@class, 'date')] +author: //div[@id='profile']//*[@class='authors']//a[1] +author: //*[@class='author']/span +prune: no + +strip: //div[@class='moreOnBoxWithImages'] + +single_page_link: //a[@class='print'] + +test_url: http://www.theatlantic.com/technology/archive/2011/04/want-to-see-how-crazy-a-bot-run-market-can-be/237773/ +test_url: http://www.theatlantic.com/magazine/archive/2007/11/the-autumn-of-the-multitaskers/6342/ +test_url: http://www.theatlantic.com/entertainment/archive/2012/04/30-rock-live-a-funny-reminder-of-why-sitcoms-arent-shot-live-anymore/256447/ \ No newline at end of file -- cgit v1.2.3