# ID: 1
# Robots.txt für die-tagespost.de
# Stand: 22.09.2025
# Änderung: KI-Crawler wie Google-Extended und GPTBot werden nun zugelassen, um eine Indexierung und Zitation in KI-Diensten zu ermöglichen.

User-agent: *
Disallow: /_/ecards.html
Disallow: /_/ecards.html*
Disallow: /_/epaper/
Disallow: /_/sendmail.html*
Disallow: /_/tools/bb_redirect.html*
Disallow: /_/tools/diaview.html?prev=true*
Disallow: /_/tools/pdfpage.html
Disallow: /_/tools/pdfpage.html?arid=*
Disallow: /_/tools/pdfpage.html*
Disallow: /?_FCLIST=*
Disallow: /?voteerg=*
Disallow: /*_FORMAT=PRINT*
Disallow: /*?_CMFUNC*
Disallow: /*?_FRAME=*
Disallow: /*?_UNLOCK=nocache
Disallow: /*?fcms=*
Disallow: /*?fcms=*
Disallow: /*?ID=*
Disallow: /*?link2=*
Disallow: /*?pin_type=*
Disallow: /*?po_id=*
Disallow: /*?select1=*
Disallow: /*?SID*
Disallow: /*?sid*
Disallow: /*.asp$
Disallow: /*.exec$
Disallow: /*&list=1$
Disallow: /*ID=*
Disallow: /*index.php?option=*&task=*&id=*&Itemid=*
Disallow: /*Z$
Disallow: /2008/
Disallow: /admin/*
Disallow: /abfall/
Disallow: /au/
Disallow: /backup/
Disallow: /bcw_rightbox/
Disallow: /chat/
Disallow: /cme*
Disallow: /cmspic/
Disallow: /Dokumente/
Disallow: /dpa/
Disallow: /kiosk/
Disallow: /kiosk/*epa*
Disallow: /kiosk/suche/*
Disallow: /kiosk/ausgaben/*
Disallow: /flash/
Disallow: /hugo/
Disallow: /import/
Disallow: /kna-nachrichten/
Disallow: /linkatory/
Disallow: /mobile/
Disallow: /msuup/
Disallow: /online_test/
Disallow: /ordner/
Disallow: /suche/
Disallow: /tgs-videos/
Disallow: /tscontent/
Disallow: /wetterImages/
Disallow: /_/pics/spacer.gif
Disallow: /leserbefragung2022
Disallow: /apa-epaper/

# Block für Baidu (chinesische Suchmaschine) und Semrush (SEO-Tool) wird beibehalten, kann bei Bedarf entfernt werden.
User-agent: SemrushBot-SA
Disallow: /

User-agent: Baiduspider
Disallow: /

# Legal notice: die-tagespost.de expressly reserves the right to use its content for commercial text and data mining (§44 b UrhG).
# The use of robots or other automated means to access faz.net or collect or mine data without the express permission of die-tagespost.de is strictly prohibited.
# die-tagespost.de may, in its discretion, permit certain automated access to certain die-tagespost.de pages,
# If you would like to apply for permission to crawl die-tagespost.de, collect or use data, please email info@die-tagespost.de.

Sitemap: https://www.die-tagespost.de/sitemap.sitemap.xml
Sitemap: https://www.die-tagespost.de/online-Artikel.sitemap.xml
Sitemap: https://www.die-tagespost.de/News-XML.sitemap.xml