twitter.com/robots.txt:
#Google Search Engine Robot
User-agent: Googlebot
Allow: /?_escaped_fragment_
Allow: /*?lang=
Allow: /hashtag/*?src=
Allow: /search?q=%23
Allow: /i/api/
Disallow: /search/realtime
Disallow: /search/users
Disallow: /search/*/grid
Disallow: /*?
Disallow: /*/followers
Disallow: /*/following
Disallow: /account/deactivated
Disallow: /settings/deactivated
#Yahoo! Search Engine Robot
User-Agent: Slurp
Allow: /?_escaped_fragment_
Allow: /*?lang=
Allow: /hashtag/*?src=
Allow: /search?q=%23
Allow: /i/api/
Disallow: /search/realtime
Disallow: /search/users
Disallow: /search/*/grid
Disallow: /*?
Disallow: /*/followers
Disallow: /*/following
Disallow: /account/deactivated
Disallow: /settings/deactivated
#Yandex Search Engine Robot
User-agent: Yandex
Allow: /?_escaped_fragment_
Allow: /*?lang=
Allow: /hashtag/*?src=
Allow: /search?q=%23
Allow: /i/api/
Disallow: /search/realtime
Disallow: /search/users
Disallow: /search/*/grid
Disallow: /*?
Disallow: /*/followers
Disallow: /*/following
Disallow: /account/deactivated
Disallow: /settings/deactivated
#Microsoft Search Engine Robot
User-Agent: msnbot
Disallow: /
#Bing Search Engine Robot
User-Agent: bingbot
Disallow: /
# Every bot that might possibly read and respect this file.
User-agent: *
Allow: /*?lang=
Allow: /hashtag/*?src=
Allow: /search?q=%23
Allow: /i/api/
Disallow: /search/realtime
Disallow: /search/users
Disallow: /search/*/grid
Disallow: /*?
Disallow: /*/followers
Disallow: /*/following
Disallow: /account/deactivated
Disallow: /settings/deactivated
Disallow: /oauth
Disallow: /1/oauth
Disallow: /i/streams
Disallow: /i/hello
# WHAT-4882 - Block indexing of links in notification emails. This applies to all bots.
Disallow: /i/u
Noindex: /i/u
# Wait 1 second between successive requests. See ONBOARD-2698 for details.
Crawl-delay: 1
# Independent of user agent. Links in the sitemap are full URLs using https:// and need to match
# the protocol of the sitemap.
Sitemap: https://twitter.com/sitemap.xml
в яндексе
Прочее:
Ping/Trace,
История в Веб-архиве,
История владельцев,
Валидность HTML,
Валидность CSS,
Проверка на вирусы.
Запрашиваемая страница недоступна!
|