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/wmnf.org.txt | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 inc/3rdparty/site_config/standard/wmnf.org.txt (limited to 'inc/3rdparty/site_config/standard/wmnf.org.txt') diff --git a/inc/3rdparty/site_config/standard/wmnf.org.txt b/inc/3rdparty/site_config/standard/wmnf.org.txt new file mode 100644 index 00000000..ffb6b2d1 --- /dev/null +++ b/inc/3rdparty/site_config/standard/wmnf.org.txt @@ -0,0 +1,13 @@ +title: //div[@class="bodyText"]/h1/text() +body: //div[@class="bodyText"] + +# author and date are separated by only a newline +# can't figure out how to tokenize that yet +author: //div[@class="bodyText"]/span[@class="info"]/text() +date: //div[@class="bodyText"]/span[@class="info"]/text() + +# strip metdata from body text +strip: //div[@class="bodyText"]/h1/text() +strip: //div[@class="bodyText"]/span[@class="info"] +strip: //div[@class="bodyText"]/span[@class="info"] +test_url: http://www.wmnf.org/news_stories/light-rail-advocates-join-forces-to-combat-opposition-in-pinellas \ No newline at end of file -- cgit v1.2.3