golem.de.txt

# Author: zinnober
# Rewrite of original template which fetched the printer-version without pictures

# As of 2020, this cookie is required to fetch articles because of the GDPR cookie warning
http_header(Cookie): golem_consent20=cmp|220101
http_header(user-agent): Googlebot

tidy: no
prune: no

# Set full title
title: //h1

date: //time
author: //a[@rel='author']

# Content is here
body: //article

# Fetch full multipage articles
next_page_link: //a[@id='atoc_next']

# Remove tracking and ads
strip_id_or_class: iqadtile4
strip_id_or_class: gbox_affiliate
strip_id_or_class: seminars
strip_id_or_class: supplementary

# General Cleanup
strip_id_or_class: list-jtoc
strip_id_or_class: table-jtoc
strip_id_or_class: implied
strip_id_or_class: social-tools
strip_id_or_class: comments
strip_id_or_class: footer
strip_id_or_class: job-market
strip_id_or_class: tags
strip_id_or_class: topictags
strip: //div[contains(@class, 'authors--withsource')]
strip: //div[@class='toc']
strip: //li[not(.//text()[normalize-space()])][not(@class)]

# Tidy up galleries (could still be improved, though)
strip: //img[@src='']
# This removes valid lists:
# https://www.golem.de/news/sap-berater-der-coolste-job-nach-tourismusmanager-und-bierbrauer-1807-135389-2.html
# strip: //li[not(*)]
strip: //div[contains(@style,'margin')]
strip: //figure[contains(@id,'gvideo')]
strip: //figure/figcaption[contains(text(), 'Bitte aktivieren Sie Javascript')]

# Golem Plus Paywall
http_header(Cookie): golem_multipage=single                   
requires_login: yes                                           
login_uri: https://account.golem.de/user/login                
login_username_field: email                                   
login_password_field: password                                
not_logged_in_xpath: //button[contains(@class, 'golem_login')]


# Try yourself
test_url: http://www.golem.de/news/intel-core-i7-5960x-im-test-die-pc-revolution-beginnt-mit-octacore-und-ddr4-1408-108893.html
test_url: http://www.golem.de/news/test-infamous-first-light-neonbunter-actionspass-1408-108914.html
test_url: https://www.golem.de/news/ressourcenschonend-programmieren-so-wurden-spiele-fuer-den-commodore-64-und-atari-entwickelt-2307-175508.html