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/historytoday.com.txt | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/historytoday.com.txt (limited to 'inc/3rdparty/site_config/standard/historytoday.com.txt') diff --git a/inc/3rdparty/site_config/standard/historytoday.com.txt b/inc/3rdparty/site_config/standard/historytoday.com.txt new file mode 100644 index 00000000..dc687f3f --- /dev/null +++ b/inc/3rdparty/site_config/standard/historytoday.com.txt @@ -0,0 +1,10 @@ +body://div[@id = 'content'] +author://span[@class = 'authors'] +author://span[@class = 'ht-vtag'][1] +date:substring-before(//meta[@name = 'dc.date']/@content,'T') +strip://div[contains(@class, 'region-ubercontent')] +strip://h1 +strip://div[@id = 'ht-author'] +strip://ul[@class = 'links inline'] +strip://div[@id = 'ht-tools'] +test_url: http://www.historytoday.com/carol-dyhouse/skin-deep-fall-fur \ No newline at end of file -- cgit v1.2.3