AcademyWorkflowsData and reporting

Web Site Scraper for LLMs with Airtop

Data, research and marketing teams that need the content of a whole site collected in one document.

Use it nowWant it running at your company?
  • Recommendedour rating
  • 4,403views on n8n

Use it now

Open inClaudeChatGPTGeminiPerplexity
Open on n8n.io ↗

Paste it straight onto an n8n canvas with Ctrl+V or Cmd+V.

Third party software. By copying, downloading or installing it you accept the Academy legal notice: you are responsible for reviewing its code and permissions before use.

web-site-scraper-for-llms-with-airtop.json

Loading the file...

What it does

Reads a seed URL from a Google Sheet, scrapes each page with Airtop and saves the content to a Google Doc. New links that match a filter string are added back to the sheet, and the cycle repeats for the depth you set. The result is a document of site content ready to feed an LLM.

Use cases

  1. 01Gather a site's pages into one document for an LLM
  2. 02Collect content across linked pages for research
  3. 03Build a list of pages and links for lead generation

Connects

Google Sheets · Google Docs · Code · Airtop

Questions about
Web Site Scraper for LLMs with Airtop.

What is Web Site Scraper for LLMs with Airtop used for?

Data, research and marketing teams that need the content of a whole site collected in one document. Reads a seed URL from a Google Sheet, scrapes each page with Airtop and saves the content to a Google Doc. New links that match a filter string are added back to the sheet, and the cycle repeats for the depth you set. The result is a document of site content ready to feed an LLM.

How do I import Web Site Scraper for LLMs with Airtop into n8n?

Copy the workflow JSON from this page and paste it onto the n8n canvas with Ctrl+V or Cmd+V. Then connect your credentials in each node.

Is Web Site Scraper for LLMs with Airtop safe to use?

It passed our automatic scan for credential theft, hidden instructions and risky install commands. Third party open source software. Sabemos AI does not maintain it. Check the code and permissions before you connect it to company data.

Related resources

Read the guide: AI data analysts: ask your data ↗

  1. 001markitdownOperations and analyst teams that need to give reports, contracts and spreadsheets to an AI assistant as plain text.OfficialMCP server · ★ 189k
  2. 002XLSXFinance and data teams that build or update Excel models and reports and want them to recalculate correctly.OfficialSkill
  3. 003server-fetchMarketing and research teams that want an AI assistant to read and summarise public web pages.OfficialMCP server
  4. 004Scrape and summarize webpages with AIMarketing and research teams that want quick summaries of articles from a website.RecommendedWorkflow · 292k views
  5. 005AI agent that can scrape webpagesOperations and research teams that want a chat agent able to read web pages and answer questions about their content.RecommendedWorkflow · 212k views
  6. 006Pull data from services without an n8n integrationOperations and data teams who need to connect n8n to a service that has no dedicated node.RecommendedWorkflow · 194k views