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 --- .../site_config/standard/minnesota.publicradio.org.txt | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/minnesota.publicradio.org.txt (limited to 'inc/3rdparty/site_config/standard/minnesota.publicradio.org.txt') diff --git a/inc/3rdparty/site_config/standard/minnesota.publicradio.org.txt b/inc/3rdparty/site_config/standard/minnesota.publicradio.org.txt new file mode 100644 index 00000000..7e43d63c --- /dev/null +++ b/inc/3rdparty/site_config/standard/minnesota.publicradio.org.txt @@ -0,0 +1,10 @@ +title: //*[@class="article"]/h1 +date: //*[@class="article"]/div[@class="date"] + +# strip the title and date from the article text +strip: //*[@class="article"]/h1 +strip: //*[@class="article"]/div[@class="date"] + +# strip annoying
between metadata and article +strip: //*[@class="article"]/div[@class="date"]/following-sibling::br +test_url: http://minnesota.publicradio.org/display/web/2012/06/19/health/senators-want-health-care-ruling-on-tv/ \ No newline at end of file -- cgit v1.2.3