From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- minnesota.publicradio.org.txt | 10 ++++++++++ 1 file changed, 10 insertions(+) create mode 100644 minnesota.publicradio.org.txt (limited to 'minnesota.publicradio.org.txt') diff --git a/minnesota.publicradio.org.txt b/minnesota.publicradio.org.txt new file mode 100644 index 0000000..773a627 --- /dev/null +++ b/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 v1.3.1