updated specific configuration for parsing

1 files changed, 21 insertions, 21 deletions

diff --git a/inc/3rdparty/site_config/standard/welt.de.txt b/inc/3rdparty/site_config/standard/welt.de.txt
index 6e4f828f..42e65e97 100644..100755
--- a/inc/3rdparty/site_config/standard/welt.de.txt
+++ b/inc/3rdparty/site_config/standard/welt.de.txt
@@ -1,22 +1,22 @@
-# set body

-tidy: no

-body: //div[contains(@class, 'articleContent')]

-

-# remove clutter

-strip: //div[@class='advertising']

-strip: //div[@class='themenalarm']

-strip: //div[contains(@class, 'inTextTeaser')]

-

-# remove captions

-strip: //span[@class='copyRight']

-

-# remove photo galleries and extras

-strip: //div[contains(@class, 'textGallery')]

-strip: //div[contains(@class, 'videoGallery')]

-strip: //div[contains(@class, 'imageGallery')]

-strip: //div[contains(@class, 'openContent')]

-

-# remove comments

-strip: //div[@id = 'writeComment']

-

+# set body
+tidy: no
+body: //div[contains(@class, 'articleContent')]
+
+# remove clutter
+strip: //div[@class='advertising']
+strip: //div[@class='themenalarm']
+strip: //div[contains(@class, 'inTextTeaser')]
+
+# remove captions
+strip: //span[@class='copyRight']
+
+# remove photo galleries and extras
+strip: //div[contains(@class, 'textGallery')]
+strip: //div[contains(@class, 'videoGallery')]
+strip: //div[contains(@class, 'imageGallery')]
+strip: //div[contains(@class, 'openContent')]
+
+# remove comments
+strip: //div[@id = 'writeComment']
+
 test_url: http://www.welt.de/vermischtes/weltgeschehen/article11050589/27-Bergleute-in-neuseelaendischer-Mine-vermisst.html
\ No newline at end of file