blob: 2136de3fdc9a159317a707bcf303a7166c008aee (
plain) (
tree)
|
|
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
strip: //p/following-sibling::*[0]
test_url: http://www.mainpost.de/ueberregional/meinung/Dioxin-Skandal-bringt-Agrarministerin-in-Bedraengnis;art9517,5920211
|
