updated specific configuration for parsing

This commit is contained in:
Nicolas Lœuillet
2014-07-13 10:15:40 +02:00
parent 58dbe10388
commit 4e067ceabd
952 changed files with 7585 additions and 5682 deletions

34
inc/3rdparty/site_config/standard/computerbase.de.txt vendored Normal file → Executable file
View File

@ -1,18 +1,18 @@
title://h1
author://div[@id="news-meta"]/a
body://*[@id="main"]/div[1]
strip://*[@id="main"]/div[2]
strip://*[@id="main"]/div[3]
strip://*[@id="page"]//footer
#date: didn't manage to parse it
#Images have to be stripped because the page does it with overlay
strip://img
#figures are not displayed in instapaper...
strip://figure | //figcaption
title://h1
author://div[@id="news-meta"]/a
body://*[@id="main"]/div[1]
strip://*[@id="main"]/div[2]
strip://*[@id="main"]/div[3]
strip://*[@id="page"]//footer
#date: didn't manage to parse it
#Images have to be stripped because the page does it with overlay
strip://img
#figures are not displayed in instapaper...
strip://figure | //figcaption
test_url: http://www.computerbase.de/news/2012-06/verbraucherzentrale-mahnt-blizzard-fuer-diablo-3-ab/