From a59f54cb20cc4bcf7ece5a785ca57f3ac1a12f88 Mon Sep 17 00:00:00 2001 From: Thomas Andres Date: Sun, 20 Nov 2016 15:48:49 +0100 Subject: Updated sueddeutsche.de (#221) * Support for articles with multiple pages on sueddeutsche.de * Typo --- sueddeutsche.de.txt | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/sueddeutsche.de.txt b/sueddeutsche.de.txt index de619eb..ef6a995 100644 --- a/sueddeutsche.de.txt +++ b/sueddeutsche.de.txt @@ -1,9 +1,33 @@ +# Important Note: +# The last paragraph of any article seems to be a teaser from the sports section. + +tidy: no +prune: no +autodetect_on_failure: yes + +date: //time[@class='timeformat'] +title: //section[@class='header']//h2 body: //article[@id="sitecontent"] author: //meta[@name="author"]/@content -strip: //section[@class="header"] +replace_string(

):

+replace_string(

): + +#strip: //section[@class="header"] +strip: //section[@class='header']//time +strip: //section[@class='header']//strong strip: //div[@id="article-sidebar-wrapper"] strip: //p[@class="anzeige"] strip: //section[@class="authors"] +strip_id_or_class: teaserable-layout +strip: //noscript +strip: //div//i + +next_page_link: //a[@class='article-paging-nav-btn'] +# 1 page +test_url: http://www.sueddeutsche.de/reise/bergwinter-saisonstart-in-den-skigebieten-geht-schon-1.3251799 +# 2 pages +test_url: http://www.sueddeutsche.de/kultur/politik-und-philosophie-warum-trump-jedes-mittel-recht-ist-1.3256078 +# 3 pages test_url: http://www.sueddeutsche.de/muenchen/mietshaus-am-gaertnerplatz-alles-muss-raus-1.1556693 -- cgit v1.3.1