summaryrefslogtreecommitdiff
path: root/faz.net.txt
diff options
context:
space:
mode:
authorFiveFilters.org <fivefilters@fivefilters.org>2013-02-27 23:43:10 +0100
committerFiveFilters.org <fivefilters@fivefilters.org>2013-02-27 23:43:10 +0100
commit9a69161c8646f63b4d9fa17c6ac3ab922d625859 (patch)
tree62a446347e1279f00383fdd7f9637cfd58a50879 /faz.net.txt
downloadftr-site-config-9a69161c8646f63b4d9fa17c6ac3ab922d625859.tar.gz
ftr-site-config-9a69161c8646f63b4d9fa17c6ac3ab922d625859.zip
Initial commit
Diffstat (limited to 'faz.net.txt')
-rw-r--r--faz.net.txt30
1 files changed, 30 insertions, 0 deletions
diff --git a/faz.net.txt b/faz.net.txt
new file mode 100644
index 0000000..6256b0b
--- /dev/null
+++ b/faz.net.txt
@@ -0,0 +1,30 @@
+# Title
+title: //p[@class='Content HeadlineShort']
+
+# Authors
+# some are known and have a link, others don't
+author: substring-after(//span[@class='Autor'], 'Von')
+
+# Date
+date: //span[@class='Datum']
+
+# Body
+body: //div[@class='Artikel']
+
+# Removements before body text
+strip: //div[@class='Breadcrumbs']
+strip: //div[@class='QuickSearchBox']
+strip: //div[@class='FAZArtikelEinleitung']
+strip: //div[@class='FAZArtikelReiter']
+strip: //div[@class='clear']
+
+# General removements
+strip: //span[@class='Bildnachweis']
+
+# Removements after body text
+strip: //div[@class='ArtikelAbbinder']
+strip: //div[@class='ArtikelKommentieren Artikelfuss GETS;tk;boxen.top-lesermeinungen;tp;content']
+strip: //div[@class='FAZArtikelKommentare FAZArtikelContent']
+strip: //div[@class='FAZArtikelFunktionen']
+strip: //div[@id='FAZContentRight']
+test_url: http://www.faz.net/aktuell/gesellschaft/ehe-haltbarkeitsformel-verliebe-dich-oft-verlobe-dich-selten-heirate-vielleicht-11685306.html \ No newline at end of file