mirror of
https://github.com/ParkerTenBroeck/ParkerTenBroeck.github.io.git
synced 2026-06-06 21:14:06 -04:00
88x31, robots
This commit is contained in:
parent
be158ab925
commit
b3c7294a89
8 changed files with 140 additions and 81 deletions
BIN
content/blog/88x31/aperturelabs.gif
Normal file
BIN
content/blog/88x31/aperturelabs.gif
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1.4 KiB |
BIN
content/blog/88x31/bootleg64_spinbutton.gif
Normal file
BIN
content/blog/88x31/bootleg64_spinbutton.gif
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 15 KiB |
BIN
content/blog/88x31/bunbrowser.gif
Normal file
BIN
content/blog/88x31/bunbrowser.gif
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 1.2 KiB |
|
|
@ -23,6 +23,10 @@ other
|
||||||
|
|
||||||
{{ badge88x31(src="madeon-linux.gif", alt="made on Linux badge") }}
|
{{ badge88x31(src="madeon-linux.gif", alt="made on Linux badge") }}
|
||||||
{{ badge88x31(link="https://nixos.org/", src="nixos.png", alt="NixOS badge", new_tab=true) }}
|
{{ badge88x31(link="https://nixos.org/", src="nixos.png", alt="NixOS badge", new_tab=true) }}
|
||||||
|
{{ badge88x31(link="https://rust-lang.org/", src="rustnow.gif", alt="Rust badge", new_tab=true) }}
|
||||||
|
{{ badge88x31(link="https://www.w3.org/QA/Tips/iso-date", src="iso-date.gif", alt="ISO 8601 badge", new_tab=true) }}
|
||||||
|
{{ badge88x31(link="https://www.aperturescience.com/", src="aperturelabs.gif", alt="Aperture Labs badge", new_tab=true) }}
|
||||||
|
{{ badge88x31(src="niko-chuckle.gif", alt="Niko Chuckle Viewed badge") }}
|
||||||
{{ badge88x31(src="bestviewed.gif", alt="Best Viewed badge") }}
|
{{ badge88x31(src="bestviewed.gif", alt="Best Viewed badge") }}
|
||||||
{{ badge88x31(src="roroqa.gif", alt="Rendered On RISC OS badge") }}
|
{{ badge88x31(src="roroqa.gif", alt="Rendered On RISC OS badge") }}
|
||||||
{{ badge88x31(src="right_to_repair_01.jpg", alt="Right To Repair badge") }}
|
{{ badge88x31(src="right_to_repair_01.jpg", alt="Right To Repair badge") }}
|
||||||
|
|
@ -30,4 +34,5 @@ other
|
||||||
{{ badge88x31(src="greyasashe.gif", alt="Grey as ash badge") }}
|
{{ badge88x31(src="greyasashe.gif", alt="Grey as ash badge") }}
|
||||||
{{ badge88x31(src="button-devils.gif", alt="Devils badge") }}
|
{{ badge88x31(src="button-devils.gif", alt="Devils badge") }}
|
||||||
{{ badge88x31(src="b5can_s.gif", alt="Can badge") }}
|
{{ badge88x31(src="b5can_s.gif", alt="Can badge") }}
|
||||||
|
{{ badge88x31(src="bootleg64_spinbutton.gif", alt="bootleg64 badge") }}
|
||||||
|
{{ badge88x31(src="bunbrowser.gif", alt="Bunny badge") }}
|
||||||
|
|
|
||||||
BIN
content/blog/88x31/iso-date.gif
Normal file
BIN
content/blog/88x31/iso-date.gif
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 447 B |
BIN
content/blog/88x31/niko-chuckle.gif
Normal file
BIN
content/blog/88x31/niko-chuckle.gif
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 2 KiB |
BIN
content/blog/88x31/rustnow.gif
Normal file
BIN
content/blog/88x31/rustnow.gif
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 2.9 KiB |
|
|
@ -1,95 +1,149 @@
|
||||||
User-agent: TurnitinBot
|
# AI scrapers
|
||||||
Disallow: /
|
User-agent: AddSearchBot
|
||||||
|
User-agent: AI2Bot
|
||||||
User-agent: Google-Extended
|
User-agent: AI2Bot-DeepResearchEval
|
||||||
Disallow: /
|
User-agent: Ai2Bot-Dolma
|
||||||
|
User-agent: aiHitBot
|
||||||
User-agent: GPTBot
|
User-agent: amazon-kendra
|
||||||
Disallow: /
|
|
||||||
|
|
||||||
User-agent: CCBot
|
|
||||||
Disallow: /
|
|
||||||
|
|
||||||
User-agent: Omgilibot
|
|
||||||
Disallow: /
|
|
||||||
|
|
||||||
User-agent: 008
|
|
||||||
Disallow: /
|
|
||||||
|
|
||||||
User-agent: voltron
|
|
||||||
Disallow: /
|
|
||||||
|
|
||||||
User-agent: Bytespider
|
|
||||||
Disallow: /
|
|
||||||
|
|
||||||
User-agent: AdsBot-Google
|
|
||||||
Disallow: /
|
|
||||||
|
|
||||||
User-agent: Amazonbot
|
User-agent: Amazonbot
|
||||||
Disallow: /
|
User-agent: AmazonBuyForMe
|
||||||
|
User-agent: Amzn-SearchBot
|
||||||
User-agent: Anthropic-ai
|
User-agent: Amzn-User
|
||||||
Disallow: /
|
User-agent: Andibot
|
||||||
|
User-agent: Anomura
|
||||||
User-agent: AwarioRssBot
|
User-agent: anthropic-ai
|
||||||
Disallow: /
|
User-agent: ApifyBot
|
||||||
|
User-agent: ApifyWebsiteContentCrawler
|
||||||
User-agent: AwarioSmartBot
|
User-agent: Applebot
|
||||||
Disallow: /
|
User-agent: Applebot-Extended
|
||||||
|
User-agent: Aranet-SearchBot
|
||||||
|
User-agent: atlassian-bot
|
||||||
|
User-agent: Awario
|
||||||
|
User-agent: AzureAI-SearchBot
|
||||||
|
User-agent: bedrockbot
|
||||||
|
User-agent: bigsur.ai
|
||||||
|
User-agent: Bravebot
|
||||||
|
User-agent: Brightbot 1.0
|
||||||
|
User-agent: BuddyBot
|
||||||
User-agent: Bytespider
|
User-agent: Bytespider
|
||||||
Disallow: /
|
|
||||||
|
|
||||||
User-agent: CCBot
|
User-agent: CCBot
|
||||||
Disallow: /
|
User-agent: Channel3Bot
|
||||||
|
User-agent: ChatGLM-Spider
|
||||||
|
User-agent: ChatGPT Agent
|
||||||
User-agent: ChatGPT-User
|
User-agent: ChatGPT-User
|
||||||
Disallow: /
|
User-agent: Claude-SearchBot
|
||||||
|
User-agent: Claude-User
|
||||||
User-agent: ClaudeBot
|
|
||||||
Disallow: /
|
|
||||||
|
|
||||||
User-agent: Claude-Web
|
User-agent: Claude-Web
|
||||||
Disallow: /
|
User-agent: ClaudeBot
|
||||||
|
User-agent: Cloudflare-AutoRAG
|
||||||
User-agent: Cohere-ai
|
User-agent: CloudVertexBot
|
||||||
Disallow: /
|
User-agent: cohere-ai
|
||||||
|
User-agent: cohere-training-data-crawler
|
||||||
User-agent: DataForSeoBot
|
User-agent: Cotoyogi
|
||||||
Disallow: /
|
User-agent: Crawl4AI
|
||||||
|
User-agent: Crawlspace
|
||||||
|
User-agent: Datenbank Crawler
|
||||||
|
User-agent: DeepSeekBot
|
||||||
|
User-agent: Devin
|
||||||
|
User-agent: Diffbot
|
||||||
|
User-agent: DuckAssistBot
|
||||||
|
User-agent: Echobot Bot
|
||||||
|
User-agent: EchoboxBot
|
||||||
|
User-agent: ExaBot
|
||||||
User-agent: FacebookBot
|
User-agent: FacebookBot
|
||||||
Disallow: /
|
User-agent: facebookexternalhit
|
||||||
|
User-agent: Factset_spyderbot
|
||||||
|
User-agent: FirecrawlAgent
|
||||||
|
User-agent: FriendlyCrawler
|
||||||
|
User-agent: Gemini-Deep-Research
|
||||||
|
User-agent: Google-Agent
|
||||||
|
User-agent: Google-CloudVertexBot
|
||||||
User-agent: Google-Extended
|
User-agent: Google-Extended
|
||||||
Disallow: /
|
User-agent: Google-Firebase
|
||||||
|
User-agent: Google-NotebookLM
|
||||||
|
User-agent: GoogleAgent-Mariner
|
||||||
|
User-agent: GoogleOther
|
||||||
|
User-agent: GoogleOther-Image
|
||||||
|
User-agent: GoogleOther-Video
|
||||||
User-agent: GPTBot
|
User-agent: GPTBot
|
||||||
Disallow: /
|
User-agent: iAskBot
|
||||||
|
User-agent: iaskspider
|
||||||
|
User-agent: iaskspider/2.0
|
||||||
|
User-agent: IbouBot
|
||||||
|
User-agent: ICC-Crawler
|
||||||
User-agent: ImagesiftBot
|
User-agent: ImagesiftBot
|
||||||
Disallow: /
|
User-agent: imageSpider
|
||||||
|
User-agent: img2dataset
|
||||||
User-agent: Magpie-crawler
|
User-agent: ISSCyberRiskCrawler
|
||||||
Disallow: /
|
User-agent: kagi-fetcher
|
||||||
|
User-agent: Kangaroo Bot
|
||||||
User-agent: Omgili
|
User-agent: KlaviyoAIBot
|
||||||
Disallow: /
|
User-agent: KunatoCrawler
|
||||||
|
User-agent: laion-huggingface-processor
|
||||||
User-agent: Omgilibot
|
User-agent: LAIONDownloader
|
||||||
Disallow: /
|
User-agent: LCC
|
||||||
|
User-agent: LinerBot
|
||||||
User-agent: Peer39_crawler
|
User-agent: Linguee Bot
|
||||||
Disallow: /
|
User-agent: LinkupBot
|
||||||
|
User-agent: Manus-User
|
||||||
User-agent: Peer39_crawler/1.0
|
User-agent: meta-externalagent
|
||||||
Disallow: /
|
User-agent: Meta-ExternalAgent
|
||||||
|
User-agent: meta-externalfetcher
|
||||||
|
User-agent: Meta-ExternalFetcher
|
||||||
|
User-agent: meta-webindexer
|
||||||
|
User-agent: MistralAI-User
|
||||||
|
User-agent: MistralAI-User/1.0
|
||||||
|
User-agent: MyCentralAIScraperBot
|
||||||
|
User-agent: netEstate Imprint Crawler
|
||||||
|
User-agent: NotebookLM
|
||||||
|
User-agent: NovaAct
|
||||||
|
User-agent: OAI-SearchBot
|
||||||
|
User-agent: omgili
|
||||||
|
User-agent: omgilibot
|
||||||
|
User-agent: OpenAI
|
||||||
|
User-agent: Operator
|
||||||
|
User-agent: PanguBot
|
||||||
|
User-agent: Panscient
|
||||||
|
User-agent: panscient.com
|
||||||
|
User-agent: Perplexity-User
|
||||||
User-agent: PerplexityBot
|
User-agent: PerplexityBot
|
||||||
|
User-agent: PetalBot
|
||||||
|
User-agent: PhindBot
|
||||||
|
User-agent: Poggio-Citations
|
||||||
|
User-agent: Poseidon Research Crawler
|
||||||
|
User-agent: QualifiedBot
|
||||||
|
User-agent: QuillBot
|
||||||
|
User-agent: quillbot.com
|
||||||
|
User-agent: SBIntuitionsBot
|
||||||
|
User-agent: Scrapy
|
||||||
|
User-agent: SemrushBot-OCOB
|
||||||
|
User-agent: SemrushBot-SWA
|
||||||
|
User-agent: ShapBot
|
||||||
|
User-agent: Sidetrade indexer bot
|
||||||
|
User-agent: Spider
|
||||||
|
User-agent: TavilyBot
|
||||||
|
User-agent: TerraCotta
|
||||||
|
User-agent: Thinkbot
|
||||||
|
User-agent: TikTokSpider
|
||||||
|
User-agent: Timpibot
|
||||||
|
User-agent: TwinAgent
|
||||||
|
User-agent: VelenPublicWebCrawler
|
||||||
|
User-agent: WARDBot
|
||||||
|
User-agent: Webzio-Extended
|
||||||
|
User-agent: webzio-extended
|
||||||
|
User-agent: wpbot
|
||||||
|
User-agent: WRTNBot
|
||||||
|
User-agent: YaK
|
||||||
|
User-agent: YandexAdditional
|
||||||
|
User-agent: YandexAdditionalBot
|
||||||
|
User-agent: YouBot
|
||||||
|
User-agent: ZanistaBot
|
||||||
Disallow: /
|
Disallow: /
|
||||||
|
|
||||||
User-agent: YouBot
|
|
||||||
Disallow: /
|
# everyone else
|
||||||
|
User-agent: *
|
||||||
|
Allow: /
|
||||||
|
|
||||||
|
|
||||||
Sitemap: {{ get_url(path="sitemap.xml") }}
|
Sitemap: {{ get_url(path="sitemap.xml") }}
|
||||||
Loading…
Add table
Add a link
Reference in a new issue