From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- golem.de.txt | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 golem.de.txt (limited to 'golem.de.txt') diff --git a/golem.de.txt b/golem.de.txt new file mode 100644 index 0000000..6afdebe --- /dev/null +++ b/golem.de.txt @@ -0,0 +1,25 @@ +# Jens Kohl, jens.kohl@... +# - Added publication date +# - Striped pagination block +# - Added single page link +# - Added xpath-querys for the printer friendly version + +title: //h1 +body: //div[@class='formatted'] +prune: no + +date: substring-after(//li[2][@class="text1"], 'Datum:') +strip: //ol[@class="list-chapters"] +strip_comments: yes + +# next: commands for printer friendly pages +single_page_link: //a[contains(@href, 'print.php?a=')]/@href +title: //body/h3 +strip_image_src: staticrl/images/logo.jpg +strip_image_src: http://cpx.golem.de/cpx.php?class=7 +strip: //body/h3 +strip: //body/b[1] +strip: //body/b[2] +strip: //body/b[3] +strip: //div[1] +test_url: http://www.golem.de/1112/88696.html \ No newline at end of file -- cgit v1.3.1