summaryrefslogtreecommitdiff
path: root/sueddeutsche.de.txt
diff options
context:
space:
mode:
authorThomas Andres <thomas@andres.in>2016-11-20 15:48:49 +0100
committerFiveFilters.org <fivefilters@fivefilters.org>2016-11-20 15:48:49 +0100
commita59f54cb20cc4bcf7ece5a785ca57f3ac1a12f88 (patch)
treea8ef69d3f9b48ad169f0f25e5536ebf67ed53c4e /sueddeutsche.de.txt
parentd508fe6c1713647e0a16104d87a049205622a6f8 (diff)
downloadftr-site-config-a59f54cb20cc4bcf7ece5a785ca57f3ac1a12f88.tar.gz
ftr-site-config-a59f54cb20cc4bcf7ece5a785ca57f3ac1a12f88.zip
Updated sueddeutsche.de (#221)
* Support for articles with multiple pages on sueddeutsche.de * Typo
Diffstat (limited to 'sueddeutsche.de.txt')
-rw-r--r--sueddeutsche.de.txt26
1 files changed, 25 insertions, 1 deletions
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(<h2>): <h3>
+replace_string(</h2>): </h3>
+
+#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