mirror of
https://github.com/superseriousbusiness/gotosocial
synced 2025-06-05 21:59:39 +02:00
[chore] Update robots.txt with latest ai bullshit (#4024)
This commit is contained in:
@ -36,13 +36,15 @@ User-agent: Amazonbot
|
|||||||
User-agent: anthropic-ai
|
User-agent: anthropic-ai
|
||||||
User-agent: Applebot
|
User-agent: Applebot
|
||||||
User-agent: Applebot-Extended
|
User-agent: Applebot-Extended
|
||||||
|
User-agent: Brightbot 1.0
|
||||||
User-agent: Bytespider
|
User-agent: Bytespider
|
||||||
User-agent: CCBot
|
User-agent: CCBot
|
||||||
User-agent: ChatGPT-User
|
User-agent: ChatGPT-User
|
||||||
User-agent: ClaudeBot
|
|
||||||
User-agent: Claude-Web
|
User-agent: Claude-Web
|
||||||
|
User-agent: ClaudeBot
|
||||||
User-agent: cohere-ai
|
User-agent: cohere-ai
|
||||||
User-agent: cohere-training-data-crawler
|
User-agent: cohere-training-data-crawler
|
||||||
|
User-agent: Crawlspace
|
||||||
User-agent: Diffbot
|
User-agent: Diffbot
|
||||||
User-agent: DuckAssistBot
|
User-agent: DuckAssistBot
|
||||||
User-agent: FacebookBot
|
User-agent: FacebookBot
|
||||||
@ -56,17 +58,23 @@ User-agent: iaskspider/2.0
|
|||||||
User-agent: ICC-Crawler
|
User-agent: ICC-Crawler
|
||||||
User-agent: ImagesiftBot
|
User-agent: ImagesiftBot
|
||||||
User-agent: img2dataset
|
User-agent: img2dataset
|
||||||
|
User-agent: imgproxy
|
||||||
User-agent: ISSCyberRiskCrawler
|
User-agent: ISSCyberRiskCrawler
|
||||||
User-agent: Kangaroo Bot
|
User-agent: Kangaroo Bot
|
||||||
User-agent: Meta-ExternalAgent
|
User-agent: Meta-ExternalAgent
|
||||||
User-agent: Meta-ExternalFetcher
|
User-agent: Meta-ExternalFetcher
|
||||||
|
User-agent: NovaAct
|
||||||
User-agent: OAI-SearchBot
|
User-agent: OAI-SearchBot
|
||||||
User-agent: omgili
|
User-agent: omgili
|
||||||
User-agent: omgilibot
|
User-agent: omgilibot
|
||||||
|
User-agent: Operator
|
||||||
User-agent: PanguBot
|
User-agent: PanguBot
|
||||||
|
User-agent: Perplexity-User
|
||||||
User-agent: PerplexityBot
|
User-agent: PerplexityBot
|
||||||
User-agent: PetalBot
|
User-agent: PetalBot
|
||||||
User-agent: Scrapy
|
User-agent: Scrapy
|
||||||
|
User-agent: SemrushBot-OCOB
|
||||||
|
User-agent: SemrushBot-SWA
|
||||||
User-agent: Sidetrade indexer bot
|
User-agent: Sidetrade indexer bot
|
||||||
User-agent: Timpibot
|
User-agent: Timpibot
|
||||||
User-agent: VelenPublicWebCrawler
|
User-agent: VelenPublicWebCrawler
|
||||||
@ -132,7 +140,7 @@ Disallow: /nodeinfo/
|
|||||||
`
|
`
|
||||||
|
|
||||||
// MD5 hash of basic robots.txt.
|
// MD5 hash of basic robots.txt.
|
||||||
RobotsTxtETag = `ce6729aacbb16fae3628210c04b462b7`
|
RobotsTxtETag = `7b6b498f7381ac33cb3efb34c68f662d`
|
||||||
// MD5 hash of robots.txt with NodeInfo disallowed.
|
// MD5 hash of robots.txt with NodeInfo disallowed.
|
||||||
RobotsTxtDisallowNodeInfoETag = `a1e4ce6342978bc8d6c3e3dfab07cab4`
|
RobotsTxtDisallowNodeInfoETag = `6d21be573d502581a3bf7271b7e63fc8`
|
||||||
)
|
)
|
||||||
|
Reference in New Issue
Block a user