Robots.txt

Robots.txt Rules

Crawler Rules
addsearchbot
  • Allow: /
ai2bot
  • Allow: /
ai2bot-deepresearcheval
  • Allow: /
ai2bot-dolma
  • Allow: /
aiwebindex
  • Allow: /
amazon-qbusiness
  • Allow: /
amazonbuyforme
  • Allow: /
amazonbot
  • Allow: /
amzn-searchbot
  • Allow: /
amzn-user
  • Allow: /
anchor browser
  • Allow: /
anthropic-ai
  • Allow: /
apifybot
  • Allow: /
apifywebsitecontentcrawler
  • Allow: /
applebot
  • Allow: /
  • Allow: /
applebot-extended
  • Allow: /
atlassian-bot
  • Allow: /
autorag
  • Allow: /
awariosmartbot
  • Allow: /
azureai-searchbot
  • Allow: /
big sur ai
  • Allow: /
bigsur.ai
  • Allow: /
brandwatch
  • Allow: /
bravebot
  • Allow: /
brightbot
  • Allow: /
bytespider
  • Allow: /
ccbot
  • Allow: /
channel3bot
  • Allow: /
chatglm-spider
  • Allow: /
chatgpt-user
  • Allow: /
claude-code
  • Allow: /
claude-searchbot
  • Allow: /
claude-user
  • Allow: /
claude-web
  • Allow: /
claudebot
  • Allow: /
code
  • Allow: /
cohere-ai
  • Allow: /
cohere-training-data-crawler
  • Allow: /
cotoyogi
  • Allow: /
crawl4ai
  • Allow: /
cursor
  • Allow: /
datenbank crawler
  • Allow: /
datenbank-crawler
  • Allow: /
deepseekbot
  • Allow: /
devin
  • Allow: /
diffbot
  • Allow: /
direqt anomura
  • Allow: /
duckassistbot
  • Allow: /
echobot bot
  • Allow: /
exabot
  • Allow: /
facebookbot
  • Allow: /
factset_spyderbot
  • Allow: /
firecrawlagent
  • Allow: /
geisthaus-pagefetcher
  • Allow: /
gptbot
  • Allow: /
  • Allow: /
iask
  • Allow: /
iaskbot
  • Allow: /
iaskspider
  • Allow: /
icc crawler
  • Allow: /
icc-crawler
  • Allow: /
imagesiftbot
  • Allow: /
imagespider
  • Allow: /
kagi-fetcher
  • Allow: /
kangaroo bot
  • Allow: /
kangaroo-bot
  • Allow: /
kimi-user
  • Allow: /
klaviyoaibot
  • Allow: /
kunato
  • Allow: /
laion-huggingface-processor
  • Allow: /
lcc
  • Allow: /
linerbot
  • Allow: /
linkupbot
  • Allow: /
liner bot
  • Allow: /
manus-user
  • Allow: /
meta-externalagent
  • Allow: /
meta-externalfetcher
  • Allow: /
meta-webindexer
  • Allow: /
mistral.ai
  • Allow: /
mistralai-user
  • Allow: /
netestate imprint crawler
  • Allow: /
novellum ai crawl
  • Allow: /
novellum
  • Allow: /
novaact
  • Allow: /
oai-searchbot
  • Allow: /
omgili
  • Allow: /
opencode
  • Allow: /
pangubot
  • Allow: /
perplexity-user
  • Allow: /
perplexitybot
  • Allow: /
peopleinc-dcipher-scraper/1.1.0
  • Allow: /
petalbot
  • Allow: /
phindbot
  • Allow: /
poggio-citations
  • Allow: /
qualifiedbot
  • Allow: /
seekrbot
  • Allow: /
semrushbot-ocob
  • Allow: /
semrushbotswa
  • Allow: /
shap-user
  • Allow: /
shapbot
  • Allow: /
sbintuitionsbot
  • Allow: /
spider
  • Allow: /
terracotta
  • Allow: /
timpibot
  • Allow: /
tavilybot
  • Allow: /
tongyibot
  • Allow: /
trae
  • Allow: /
twinagent
  • Allow: /
useai
  • Allow: /
velen crawler
  • Allow: /
velenpublicwebcrawler
  • Allow: /
webzio-extended
  • Allow: /
wrtn
  • Allow: /
yiyanbot
  • Allow: /
youbot
  • Allow: /
zanistabot
  • Allow: /
  • Allow: /ad/tech/how-to-set-up-the-smartest-galaxy-ai-features-on-your-new-samsung-galaxy
  • Disallow: /
All
  • Allow: /
  • Allow: /*?page=[0-9]
  • Disallow: /search
  • Disallow: /archive/
  • Disallow: /cdn-cgi/
"008"
  • Allow: /
ddm-dcipher/1.0.7
  • Allow: /
httrack
  • Allow: /
nutch
  • Allow: /
offline explorer
  • Allow: /
scrapy
  • Allow: /
  • Allow: /ad/article/samsung-galaxy-ai-changing-smartphone-photography
  • Allow: /ad/article/how-samsung-galaxy-ai-can-upgrade-your-smartphone
  • Allow: /ad/article/samsung-galaxy-ai-automates-everyday-tasks
  • Disallow: /

Sitemaps

Priority Location
3https://mashable.com/sitemap-index.xml
2https://mashable.com/sitemap-news-0.xml
1https://mashable.com/sitemap-live-blogs-0.xml

Raw Text

# Ziff Davis content is made available for your non-commercial use subject to our
# Terms of Use here: https://www.ziffdavis.com/terms-of-use
# Use of any robot, crawler, or other tool to scrape, harvest, extract, or retrieve any content on
# this website using automated means is prohibited without written permission from Ziff Davis.
# Prohibited uses include but are not limited to:
# (1) text and data mining under Art. 4 of the EU Directive on Copyright in the Digital Single
# Market;
# (2) development or operation of artificial intelligence or machine learning software or
# databases, including by training, fine-tuning, embedding, and retrieval-augmented generation;
# (3) creating data sets containing our content or sharing it with others; and
# (4) any commercial purposes.
# Contact licensing@ziffdavis.com for assistance.

# Bot Disallows
# Block AI and other unwanted bots

User-agent: AddSearchBot
User-agent: AI2Bot
User-agent: Ai2Bot-DeepResearchEval
User-agent: Ai2Bot-Dolma
User-agent: AIWebIndex
User-agent: amazon-QBusiness
User-agent: AmazonBuyForMe
User-agent: Amazonbot
User-agent: Amzn-SearchBot
User-agent: Amzn-User
User-agent: Anchor Browser
User-agent: anthropic-ai
User-agent: ApifyBot
User-agent: ApifyWebsiteContentCrawler
User-agent: Applebot
User-agent: Applebot-extended
User-agent: atlassian-bot
User-agent: AutoRAG
User-agent: AwarioSmartBot
User-agent: AzureAI-SearchBot
User-agent: Big Sur AI
User-agent: bigsur.ai
User-agent: Brandwatch
User-agent: Bravebot
User-agent: Brightbot
User-agent: Bytespider
User-agent: CCBot
User-agent: Channel3Bot
User-agent: ChatGLM-Spider
User-agent: ChatGPT-User
User-agent: Claude-Code
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: Code
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Cotoyogi
User-agent: Crawl4AI
User-agent: Cursor
User-agent: Datenbank Crawler
User-agent: Datenbank-Crawler
User-agent: DeepSeekBot
User-agent: Devin
User-agent: Diffbot
User-agent: Direqt Anomura
User-agent: DuckAssistBot
User-agent: Echobot Bot
User-agent: ExaBot
User-agent: FacebookBot
User-agent: Factset_spyderbot
User-agent: FirecrawlAgent
User-agent: GeistHaus-PageFetcher
User-agent: GPTBot
User-agent: iAsk
User-agent: iAskBot
User-agent: iaskspider
User-agent: ICC Crawler
User-agent: ICC-Crawler
User-agent: ImageSiftBot
User-agent: imageSpider
User-agent: kagi-fetcher
User-agent: Kangaroo Bot
User-agent: Kangaroo-Bot
User-agent: Kimi-User
User-agent: KlaviyoAIBot
User-agent: Kunato
User-agent: laion-huggingface-processor
User-agent: LCC
User-agent: LinerBot
User-agent: LinkupBot
User-agent: LINER Bot
User-agent: Manus-User
User-agent: meta-externalagent
User-agent: meta-externalfetcher
User-agent: meta-webindexer
User-agent: mistral.ai
User-agent: MistralAI-User
User-agent: netEstate Imprint Crawler
User-agent: Novellum AI Crawl
User-agent: Novellum
User-agent: NovaAct
User-agent: OAI-SearchBot
User-agent: omgili
User-agent: opencode
User-agent: PanguBot
User-agent: Perplexity-User
User-agent: PerplexityBot
User-agent: PeopleInc-DCipher-Scraper/1.1.0
User-agent: PetalBot
User-agent: PhindBot
User-agent: Poggio-Citations
User-agent: QualifiedBot
User-agent: SeekrBot
User-agent: SemrushBot-OCOB
User-agent: SemrushBotSwa
User-agent: Shap-User
User-agent: ShapBot
User-agent: SBIntuitionsBot
User-agent: Spider
User-agent: TerraCotta
User-agent: Timpibot
User-agent: TavilyBot
User-agent: TongyiBot
User-agent: Trae
User-agent: TwinAgent
User-agent: UseAI
User-agent: Velen Crawler
User-agent: VelenPublicWebCrawler
User-agent: Webzio-Extended
User-agent: Wrtn
User-agent: YiyanBot
User-agent: YouBot
User-agent: ZanistaBot
Allow: /ad/tech/how-to-set-up-the-smartest-galaxy-ai-features-on-your-new-samsung-galaxy
Disallow: /

# END Ziff Managed/Shared content

# Ziff Davis content is made available for your non-commercial use subject to our
# Terms of Use here: https://www.ziffdavis.com/terms-of-use
# Use of any robot, crawler, or other tool to scrape, harvest, extract, or retrieve any content on
# this website using automated means is prohibited without written permission from Ziff Davis.
# Prohibited uses include but are not limited to:
# (1) text and data mining under Art. 4 of the EU Directive on Copyright in the Digital Single
# Market;
# (2) development or operation of artificial intelligence or machine learning software or
# databases, including by training, fine-tuning, embedding, and retrieval-augmented generation;
# (3) creating data sets containing our content or sharing it with others; and
# (4) any commercial purposes.
# Contact licensing@ziffdavis.com for assistance.

User-agent: *
Disallow: /search
Disallow: /archive/
Disallow: /cdn-cgi/
Allow: /*?page=[0-9]

User-agent: "008"
User-agent: Applebot
User-agent: DDM-DCipher/1.0.7
User-agent: GPTBot
User-agent: HTTrack
User-agent: Nutch
User-agent: Offline Explorer
User-agent: Scrapy
Allow: /ad/article/samsung-galaxy-ai-changing-smartphone-photography
Allow: /ad/article/how-samsung-galaxy-ai-can-upgrade-your-smartphone
Allow: /ad/article/samsung-galaxy-ai-automates-everyday-tasks
Disallow: /

Sitemap: https://mashable.com/sitemap-index.xml
Sitemap: https://mashable.com/sitemap-news-0.xml
Sitemap: https://mashable.com/sitemap-live-blogs-0.xml