From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- sportschau.de.txt | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 sportschau.de.txt (limited to 'sportschau.de.txt') diff --git a/sportschau.de.txt b/sportschau.de.txt new file mode 100644 index 0000000..1e58b52 --- /dev/null +++ b/sportschau.de.txt @@ -0,0 +1,22 @@ +title://div[@id='ardContent']/h1 + +author://p[@id='ardAutor'] +author://span[@id='ardQuelle'] +author:string('sportschau.de') + +date:substring-after(//span[@id='ardStand'], 'Stand: ') + +body://div[@id='ardContent'] + +strip://div[@id='ardContent']/h1 +strip://p[@id='ardAutor'] +strip: //div[@class='embeddedPlayer_clipinfo'] +strip: //div[@class='ardMehrZumThemaRechts'] +strip: //*[contains(@class, 'inv')] + +strip: //p[@id='ardAbbinder'] +strip: //div[@class='socialBookmarks'] +strip: //div[@id='ardContentEnd'] +strip: //div[@id='ardDisclaimer'] +strip: //div[@id='ardRechteSpalte'] +test_url: http://www.sportschau.de/sp/fussball/news201203/17/analyse_leverkusen_gladbach.jsp \ No newline at end of file -- cgit v1.3.1