|
|
| Line 1: |
Line 1: |
| − | #
| |
| − | # robots.txt for http://www.wikipedia.org/ and friends
| |
| − | #
| |
| − | # Please note: There are a lot of pages on this site, and there are
| |
| − | # some misbehaved spiders out there that go _way_ too fast. If you're
| |
| − | # irresponsible, your access to the site may be blocked.
| |
| − | #
| |
| | | | |
| − | User-agent: Mediapartners-Google
| |
| − | Disallow:
| |
| − |
| |
| − | User-agent: Fasterfox
| |
| − | Disallow: /
| |
| − |
| |
| − | # Wikipedia work bots:
| |
| − | User-agent: IsraBot
| |
| − | Disallow:
| |
| − |
| |
| − | User-agent: Orthogaffe
| |
| − | Disallow:
| |
| − |
| |
| − | # Crawlers that are kind enough to obey, but which we'd rather not have
| |
| − | # unless they're feeding search engines.
| |
| − | User-agent: UbiCrawler
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: DOC
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: Zao
| |
| − | Disallow: /
| |
| − |
| |
| − | # Some bots are known to be trouble, particularly those designed to copy
| |
| − | # entire sites. Please obey robots.txt.
| |
| − | User-agent: sitecheck.internetseer.com
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: Zealbot
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: MSIECrawler
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: SiteSnagger
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: WebStripper
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: WebCopier
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: Fetch
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: Offline Explorer
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: Teleport
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: TeleportPro
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: WebZIP
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: linko
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: HTTrack
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: Microsoft.URL.Control
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: Xenu
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: larbin
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: libwww
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: ZyBORG
| |
| − | Disallow: /
| |
| − |
| |
| − | User-agent: Download Ninja
| |
| − | Disallow: /
| |
| − |
| |
| − | #
| |
| − | # Sorry, wget in its recursive mode is a frequent problem.
| |
| − | # Please read the man page and use it properly; there is a
| |
| − | # --wait option you can use to set the delay between hits,
| |
| − | # for instance.
| |
| − | #
| |
| − | User-agent: wget
| |
| − | Disallow: /
| |
| − |
| |
| − | #
| |
| − | # The 'grub' distributed client has been *very* poorly behaved.
| |
| − | #
| |
| − | User-agent: grub-client
| |
| − | Disallow: /
| |
| − |
| |
| − | #
| |
| − | # Doesn't follow robots.txt anyway, but...
| |
| − | #
| |
| − | User-agent: k2spider
| |
| − | Disallow: /
| |
| − |
| |
| − | #
| |
| − | # Hits many times per second, not acceptable
| |
| − | # http://www.nameprotect.com/botinfo.html
| |
| − | User-agent: NPBot
| |
| − | Disallow: /
| |
| − |
| |
| − | # A capture bot, downloads gazillions of pages with no public benefit
| |
| − | # http://www.webreaper.net/
| |
| − | User-agent: WebReaper
| |
| − | Disallow: /
| |
| − |
| |
| − | # Don't allow the wayback-maschine to index user-pages
| |
| − | User-agent: ia_archiver
| |
| − | Disallow: /
| |
| − | #Disallow: /SacredWiki/User
| |
| − | #Disallow: /SacredWiki/Benutzer
| |
| − |
| |
| − | #
| |
| − | # Friendly, low-speed bots are welcome viewing article pages, but not
| |
| − | # dynamically-generated pages please.
| |
| − | #
| |
| − | # Inktomi's "Slurp" can read a minimum delay between hits; if your
| |
| − | # bot supports such a thing using the 'Crawl-delay' or another
| |
| − | # instruction, please let us know.
| |
| − | #
| |
| − | User-agent: *
| |
| − | Disallow: /forum/
| |
| − | Disallow: /testforum/
| |
| − | Disallow: /t/
| |
| − | Disallow: /test/
| |
| − | Disallow: /SacredWiki/Especial:Search
| |
| − | Disallow: /SacredWiki/Especial%3ASearch
| |
| − | Disallow: /SacredWiki/Special:Random
| |
| − | Disallow: /SacredWiki/Special%3ARandom
| |
| − | Disallow: /SacredWiki/Special:Search
| |
| − | Disallow: /SacredWiki/Special%3ASearch
| |
| − | Disallow: /SacredWiki/Spesial:Search
| |
| − | Disallow: /SacredWiki/Spesial%3ASearch
| |
| − | Disallow: /SacredWiki/Spezial:Search
| |
| − | Disallow: /SacredWiki/Spezial%3ASearch
| |
| − | Disallow: /SacredWiki/Specjalna:Search
| |
| − | Disallow: /SacredWiki/Specjalna%3ASearch
| |
| − | Disallow: /SacredWiki/Speciaal:Search
| |
| − | Disallow: /SacredWiki/Speciaal%3ASearch
| |
| − | Disallow: /SacredWiki/Speciaal:Random
| |
| − | Disallow: /SacredWiki/Speciaal%3ARandom
| |
| − | Disallow: /SacredWiki/Speciel:Search
| |
| − | Disallow: /SacredWiki/Speciel%3ASearch
| |
| − | Disallow: /SacredWiki/Speciale:Search
| |
| − | Disallow: /SacredWiki/Speciale%3ASearch
| |
| − | Disallow: /SacredWiki/Istimewa:Search
| |
| − | Disallow: /SacredWiki/Istimewa%3ASearch
| |
| − | Disallow: /SacredWiki/Toiminnot:Search
| |
| − | Disallow: /SacredWiki/Toiminnot%3ASearch
| |
| − | #
| |
| − | # ar:
| |
| − | Disallow: /SacredWiki/%D8%AE%D8%A7%D8%B5:Search
| |
| − | Disallow: /SacredWiki/%D8%AE%D8%A7%D8%B5%3ASearch
| |
| − |
| |
| − | User-agent: Slurp
| |
| − | Crawl-delay: 60
| |
