From 9a69161c8646f63b4d9fa17c6ac3ab922d625859 Mon Sep 17 00:00:00 2001 From: "FiveFilters.org" Date: Wed, 27 Feb 2013 23:43:10 +0100 Subject: Initial commit --- jetzt.sueddeutsche.de.txt | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) create mode 100644 jetzt.sueddeutsche.de.txt (limited to 'jetzt.sueddeutsche.de.txt') diff --git a/jetzt.sueddeutsche.de.txt b/jetzt.sueddeutsche.de.txt new file mode 100644 index 0000000..00e4cf6 --- /dev/null +++ b/jetzt.sueddeutsche.de.txt @@ -0,0 +1,22 @@ +title: //h1 +author: //p[contains(@class, 'author')]/a +date: //p[contains(@class, 'time')] +body: //div[@class='content']/div[contains(@class, 'text')] + +# prevent "no text" errors on multi-page articles +tidy: no + +# we use a custom next-link detector instead of the print view because +# it's pretty hard to strip out the unwanted parts in the print view +autodetect_next_page: no +next_page_link: //div[contains(@class, 'text')]/div/div[contains(@class, 'paging')]/a[@class='more '] + +strip: //h1 + +strip_id_or_class: meta +strip_id_or_class: author +strip_id_or_class: paging + +# prevent "Report an Error" from being recognized as footnote +footnotes: no +test_url: http://jetzt.sueddeutsche.de/texte/anzeigen/544308/Alles-flicken \ No newline at end of file -- cgit v1.3.1