IP = 193.62.193.80
robots.txt# Robots exclusion file for http://www.ebi.ac.uk/
# See https://gitlab.ebi.ac.uk/ebiwd/ebi.ac.uk-root-assets
# Any questions/comments to www-dev@ebi.ac.uk
User-agent: sogou spider
Disallow: /Tools/services
User-agent: Baiduspider
Disallow: /chebi
User-agent: MJ12bot
Disallow: /
User-agent: naverbot
Disallow: /
User-agent: SemrushBot
Disallow: /biomodels
User-agent: SemrushBot-SA
Disallow: /biomodels
User-agent: Twiceler
Disallow: /
User-agent: discobot
Disallow: /
#User-agent: msnbot
#Disallow: /
User-agent: EBISearch
Crawl-Delay: 0
User-agent: *
Crawl-Delay: 10
Disallow: /*private*
Disallow: /~
Disallow: /3D
Disallow: /abc
Disallow: /awstats
Disallow: /beta/
Disallow: /bioinformatics
Disallow: /biosamples/beta
Disallow: /biomodels/papers
Disallow: /cgi-bin/printable
Disallow: /cgi-bin/webservices
Disallow: /cgi-bin/*?
Disallow: /cgi_files
Disallow: /citexplore
Disallow: /Compass
Disallow: /contrib
Disallow: /cpg
Disallow: /Databases/Genome_MOT/
Disallow: /dbases
Disallow: /dbest
Disallow: /disease
Disallow: /downloads
Disallow: /dx.doi.org
Disallow: /ebibbs
Disallow: /ebi_docs
Disallow: /ega/dev
Disallow: /embnet.news
Disallow: /ena/data/warehouse
Disallow: /ena/data/view
Disallow: /ensembl/biomart
Disallow: /EnsMart
Disallow: /epo
Disallow: /epo-dev
Disallow: /errors
Disallow: /es/doku
Disallow: /euro2004
Disallow: /eurocarb
Disallow: /euprojects
Disallow: /fiv97
Disallow: /flybase
Disallow: /fssp
Disallow: /Genome_MOT
Disallow: /genomes/mot/
Disallow: /Groups/images
Disallow: /Groups/include
Disallow: /hinxton
Disallow: /images
Disallow: /include
Disallow: /industry/private
Disallow: /industry_SME
Disallow: /info
Disallow: /Information/images
Disallow: /Information/include
Disallow: /Information/local
Disallow: /Information/Seminars/EU1998/
Disallow: /intact/graph2MIF
Disallow: /intact/hierarchView
Disallow: /intact/mine/
Disallow: /intact/search
Disallow: /intact/statisticView
Disallow: /integr8
Disallow: /interpro/internal-tools
Disallow: /interpro/internal-tools/
Disallow: /interpro/ISpy
Disallow: /interpro/RI*
Disallow: /ismb97
Disallow: /local
Disallow: /login
Disallow: /metabolights/MTBLS*/files/*
Disallow: /metagenomics/beta
Disallow: /miamexpress/devhelp
Disallow: /microarray/ArrayExpress
Disallow: /microarray-as/atlas/qr
Disallow: /microarray/ExpressionProfiler
Disallow: /microarray/General/Internal
Disallow: /microarray/MIAMExpress
Disallow: /microarray/interfaces
Disallow: /_mm
Disallow: /msd.old/
Disallow: /msd-srv/ssm/cgi-bin/
Disallow: /newt
Disallow: /oib97
Disallow: /oib98
Disallow: /parasites
Disallow: /pdbe-srv/view/search
Disallow: /powerpoint
Disallow: /profiles
Disallow: /proteincol
Disallow: /protein_profiles
Disallow: /proteomeApplications
Disallow: /PSD
Disallow: /pub
Disallow: /research/cgg
Disallow: /RHdb
Disallow: /scripts
Disallow: /searches/netsearch.html
Disallow: /services.html
Disallow: /services/images
Disallow: /services/include
Disallow: /sift
Disallow: /site_indexer
Disallow: /sites/ebi.ac.uk/files/person/image/Emanuele_Alpi.jpeg
Disallow: /sites/ebi.ac.uk/files/styles/medium/public/person/image/Emanuele_Alpi.jpeg
Disallow: /soaplab
Disallow: /software
Disallow: /SSC
Disallow: /subs
Disallow: /sw
Disallow: /Systems
Disallow: /tc-test
Disallow: /Templates
Disallow: /test
Disallow: /text
Disallow: /textonly
Disallow: /thornton-srv/databases/enzymes
Disallow: /thornton-srv/databases/practicals
Disallow: /thornton-srv/databases/targets
Disallow: /tops
Disallow: /wc2002
Disallow: /webservices/documentation/
Disallow: /xs
#Drupal site
# Directories
Disallow: /includes/
Disallow: /misc/
Disallow: /modules/
Disallow: /profiles/
Disallow: /scripts/
Disallow: /themes/
# Files
Disallow: /CHANGELOG.txt
Disallow: /cron.php
Disallow: /INSTALL.mysql.txt
Disallow: /INSTALL.pgsql.txt
Disallow: /INSTALL.sqlite.txt
Disallow: /install.php
Disallow: /INSTALL.txt
Disallow: /LICENSE.txt
Disallow: /MAINTAINERS.txt
Disallow: /update.php
Disallow: /UPGRADE.txt
Disallow: /xmlrpc.php
# Paths (clean URLs)
Disallow: /admin
Disallow: /comment/reply
Disallow: /filter/tips
Disallow: /node/add
Disallow: /search
Disallow: /user/register
Disallow: /user/password
Disallow: /user/login
Disallow: /user/logout
Disallow: /ega/user/register
Disallow: /ega/user/password
Disallow: /ega/user/login
Disallow: /ega/user/logout
# Taxonomies
Disallow: /taxonomy
# Nodes
Disallow: /training/Studentships
Disallow: /training/studentships/howtoapply
Disallow: /training/studentships/phdprojects
Disallow: /training/online/print
Disallow: /training/online/printpdf
#Block robots for RDF services, RT#19945
#NB only Google and Yahoo understand wildcards
Disallow: /rdf/services/*/sparql
Disallow: /interpro/*export=fasta
Disallow: /interpro/*export=ids
Disallow: /interpro/*export=tsv
Disallow: /interpro/condensed
Disallow: /interpro/*/proteins-matched
Disallow: /panda/jira/
# Block robots for EBI internal seminars & internal events
Disallow: /about/events/seminars/
Disallow: /about/events/events/internal-seminar/
Disallow: /about/events/internal-events/
Disallow: /about/events/events/internal-event/
# INC0060214 - Block EMDB search
Disallow: /emdb/search
User-agent: Googlebot
Disallow: /ebisearch/summary/api/identificationsearchboxs4/*
# Disable confluence/jira
Disallow: /seqdb/confluence
Disallow: /panda/jira
Look up this url in the url tool
https://www.ebi.ac.uk/.well-known/acme-challenge: 404 text/html; charset=UTF-8
https://www.ebi.ac.uk/.well-known/csvm: 404 text/html; charset=UTF-8
https://www.ebi.ac.uk/.well-known/nostr.json: 404 text/html; charset=UTF-8
https://www.ebi.ac.uk/.well-known/security.txt: 404 text/html; charset=UTF-8
https://www.ebi.ac.uk/.well-known/traffic-advice: 404 text/html; charset=UTF-8