46 lines
1022 B
Plaintext
46 lines
1022 B
Plaintext
# Author: zinnober
|
|
|
|
tidy: no
|
|
prune: no
|
|
|
|
# Set author
|
|
author: //a[@rel='author']
|
|
|
|
# Set date
|
|
date: //span[@class='Datum']
|
|
|
|
# Content is here
|
|
body: //div[@class='Artikel']
|
|
|
|
# Tidy up before article
|
|
strip: //div[@id='FAZHeaderNeu']
|
|
strip: //h2[@itemprop='headline']
|
|
strip: //span[@class='Datum']
|
|
strip: //span[@class='Autor']
|
|
strip_id_or_class: ArticlePagerTop
|
|
strip: //div[@class='FAZArtikelEinleitung']/h2
|
|
|
|
# General cleanup
|
|
strip: //div[@class='clear']
|
|
strip: //span[@class='Bildnachweis']
|
|
strip: //iframe
|
|
strip_id_or_class: Community
|
|
strip: ' · '
|
|
|
|
# Remove tracking and ads
|
|
strip_image_src: /l.gif?
|
|
strip: //img[@width='1']
|
|
strip_id_or_class: invisible
|
|
strip_id_or_class: Anzeige
|
|
strip_id_or_class: billboard
|
|
|
|
# Remove clutter after article
|
|
strip_id_or_class: Tagline
|
|
strip_id_or_class: ArtikelAbbinder
|
|
strip_id_or_class: FAZArtikelKommentare
|
|
strip_id_or_class: ArtikelKommentieren
|
|
strip_id_or_class: FAZContentRight
|
|
|
|
# Try it yourself
|
|
test_url: http://blogs.faz.net/wost/2014/08/17/viel-fuck-und-wenig-guter-sex-1239/
|