feat: Revise robots.txt again
This commit is contained in:
parent
d3cee29532
commit
20dcf4f265
1 changed files with 45 additions and 20 deletions
|
@ -1,48 +1,73 @@
|
||||||
User-agent: *
|
|
||||||
Allow: *
|
|
||||||
Sitemap: https://pre.hn/sitemap.xml.gz
|
Sitemap: https://pre.hn/sitemap.xml.gz
|
||||||
|
|
||||||
User-agent: Google-Extended
|
User-agent: *
|
||||||
|
Disallow:
|
||||||
|
|
||||||
|
User-agent: AdsBot-Google
|
||||||
Disallow: /
|
Disallow: /
|
||||||
|
|
||||||
# AI Data Scraper
|
User-agent: Amazonbot
|
||||||
# https://darkvisitors.com/agents/anthropic-ai
|
Disallow: /
|
||||||
|
|
||||||
User-agent: anthropic-ai
|
User-agent: anthropic-ai
|
||||||
Disallow: /
|
Disallow: /
|
||||||
|
|
||||||
# AI Data Scraper
|
User-agent: AwarioRssBot
|
||||||
# https://darkvisitors.com/agents/bytespider
|
Disallow: /
|
||||||
|
|
||||||
|
User-agent: AwarioSmartBot
|
||||||
|
Disallow: /
|
||||||
|
|
||||||
User-agent: Bytespider
|
User-agent: Bytespider
|
||||||
Disallow: /
|
Disallow: /
|
||||||
|
|
||||||
# AI Data Scraper
|
|
||||||
# https://darkvisitors.com/agents/ccbot
|
|
||||||
|
|
||||||
User-agent: CCBot
|
User-agent: CCBot
|
||||||
Disallow: /
|
Disallow: /
|
||||||
|
|
||||||
# AI Data Scraper
|
User-agent: ChatGPT-User
|
||||||
# https://darkvisitors.com/agents/facebookbot
|
Disallow: /
|
||||||
|
|
||||||
|
User-agent: ClaudeBot
|
||||||
|
Disallow: /
|
||||||
|
|
||||||
|
User-agent: Claude-Web
|
||||||
|
Disallow: /
|
||||||
|
|
||||||
|
User-agent: cohere-ai
|
||||||
|
Disallow: /
|
||||||
|
|
||||||
|
User-agent: DataForSeoBot
|
||||||
|
Disallow: /
|
||||||
|
|
||||||
User-agent: FacebookBot
|
User-agent: FacebookBot
|
||||||
Disallow: /
|
Disallow: /
|
||||||
|
|
||||||
# AI Data Scraper
|
|
||||||
# https://darkvisitors.com/agents/google-extended
|
|
||||||
|
|
||||||
User-agent: Google-Extended
|
User-agent: Google-Extended
|
||||||
Disallow: /
|
Disallow: /
|
||||||
|
|
||||||
# AI Data Scraper
|
|
||||||
# https://darkvisitors.com/agents/gptbot
|
|
||||||
|
|
||||||
User-agent: GPTBot
|
User-agent: GPTBot
|
||||||
Disallow: /
|
Disallow: /
|
||||||
|
|
||||||
# AI Data Scraper
|
User-agent: ImagesiftBot
|
||||||
# https://darkvisitors.com/agents/omgili
|
Disallow: /
|
||||||
|
|
||||||
|
User-agent: magpie-crawler
|
||||||
|
Disallow: /
|
||||||
|
|
||||||
User-agent: omgili
|
User-agent: omgili
|
||||||
Disallow: /
|
Disallow: /
|
||||||
|
|
||||||
|
User-agent: omgilibot
|
||||||
|
Disallow: /
|
||||||
|
|
||||||
|
User-agent: peer39_crawler
|
||||||
|
Disallow: /
|
||||||
|
|
||||||
|
User-agent: peer39_crawler/1.0
|
||||||
|
Disallow: /
|
||||||
|
|
||||||
|
User-agent: PerplexityBot
|
||||||
|
Disallow: /
|
||||||
|
|
||||||
|
User-agent: YouBot
|
||||||
|
Disallow: /
|
||||||
|
|
Loading…
Reference in a new issue