blob: 00e4cf6331f97a535d5cc62dd453ed7dd392143c (
plain) (
tree)
|
|
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
|
