Scrape any web page into structured JSON data with ScrapeNinja and AI
UnknownWhat this workflow does
This AI workflow has 6 nodes and runs manually, when you click “Execute workflow”. Along the way it connects Google Gemini Chat Model and CUSTOM (community).
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Scrape Ninja: uses Scrape Ninja
- Cleanup HTML (Scrape Ninja): cleanup html
- Generate JS eval code via LLM (Basic LLM Chain): sends a prompt to an LLM, with model: Google Gemini Chat Model
- Eval generated code to extract data (Scrape Ninja): extract custom
Services it uses
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that CUSTOM is verified or supports 3.0 (used in ScrapeNinja, Cleanup HTML, Eval generated code to extract data).
Nodes used (4)
- Scrape Ninja
CUSTOM.scrapeNinja - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Manual Trigger
n8n-nodes-base.manualTrigger - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm
From the author
Disclaimer: This template only works on self-hosted for now, as it uses a community node. Use Case Web scrapers often break due to web page layout changes. This workflow attempts to mitigate this problem by auto-generating web scraping data extractor code via…