2014-07-13 04:15:40 -04:00
|
|
|
title: substring-before(//title, '|')
|
|
|
|
|
body: //*[@id='content-left']
|
|
|
|
|
|
|
|
|
|
# Why is this not working here?
|
|
|
|
|
# body: //*[@id='content-left']/div[@class='content-container'][2]/div[@class='content-body']/div[@class='inner-container']/div[@class='detail']
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#Header
|
|
|
|
|
strip_id_or_class: 'subHead'
|
|
|
|
|
strip_id_or_class: 'fl_right'
|
|
|
|
|
strip_id_or_class: 'infolink'
|
|
|
|
|
strip_id_or_class: 'content-head'
|
|
|
|
|
strip_id_or_class: 'tab'
|
|
|
|
|
strip_id_or_class: 'tab-active'
|
|
|
|
|
strip: //*[contains(@class,'trenner')]
|
|
|
|
|
|
|
|
|
|
# Headline
|
|
|
|
|
strip: //h1/*
|
|
|
|
|
strip_id_or_class: 'font16'
|
|
|
|
|
|
|
|
|
|
#Images
|
|
|
|
|
strip_id_or_class: 'leftimage'
|
|
|
|
|
strip_id_or_class: 'rightimage'
|
|
|
|
|
|
|
|
|
|
#Comments
|
|
|
|
|
strip: //table
|
2013-12-06 04:13:03 -05:00
|
|
|
strip: //p/following-sibling::*[0]
|
2014-10-27 01:46:13 -04:00
|
|
|
test_url: http://www.mainpost.de/regional/wuerzburg/Autobahnschuetze-Staatsanwalt-fordert-zwoelf-Jahre;art492151,8386332
|
