Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.olostep.com/llms.txt

Use this file to discover all available pages before exploring further.

The verified Olostep Web Scraper node gives you six operations inside n8n’s visual builder: scrape a URL, search the web, get AI answers, batch-scrape thousands of URLs, crawl a site, or map all its links. View on n8n →

​
Before you start

  • An Olostep account with an API key: get one free, no credit card required. Your first 500 credits are included.
  • n8n running: either n8n Cloud or a self-hosted instance. Community nodes must be enabled (they are by default on most setups).
  • No coding required: everything in this guide is done through n8n’s visual editor.

​
Setup

1

Search for the Olostep node

Open any workflow, click +, and search for Olostep. Select Olostep Web Scraper from the results.Search for Olostep in the n8n node picker
2

Install the node

Click the result to open the Node details panel, then click Install node. n8n will install n8n-nodes-olostep and prompt you to restart. Do that before continuing.Olostep Web Scraper node details with Install node button
If Community Nodes is disabled for your workspace, an admin needs to enable it first. See the n8n community nodes guide.
3

Add your API key

Open the Olostep node in your workflow, click Set up Credential (in the Parameters tab), add your API key, and click Save.Olostep credentials form in n8n with API Key fieldGet your key from the Olostep dashboard →
4

Wire it up and run

Connect the Olostep node to a trigger and any downstream steps, then execute your workflow.n8n workflow canvas with Schedule Trigger connected to Olostep node

​
Actions

Scrape Website

Pull content from any URL as Markdown, HTML, JSON, or plain text. Handles JS-rendered pages with optional wait times and country targeting.

Search

Run a web search and get structured results (titles, URLs, and snippets) as JSON.

Answers (AI)

Ask a natural-language question and get an answer with cited sources. Useful before LLM nodes when you need grounded responses.

Batch Scrape URLs

Submit up to 10,000 URLs in one job, processed in parallel. Returns a batch_id; retrieve results asynchronously.

Create Crawl

Start from a URL, follow links, and scrape all subpages. Good for docs sites, blogs, or full-site ingestion. Returns a crawl_id.

Create Map

Get every URL on a site without scraping content. Use it for discovery before a batch job. Returns a map_id.
Batch, Crawl, and Map are async. Store the returned ID and use a Wait node or a second workflow to retrieve results once processing completes.

​
Example workflow: Lead enrichment from Google Sheets

What it does: When you paste a company URL into a Google Sheet, this workflow automatically scrapes the company’s website, extracts key information with an AI node, and writes the results back to the same row, turning a blank spreadsheet into a filled-out lead database. Nodes used: Google Sheets trigger → Olostep Scrape Website → OpenAI → Code → Google Sheets update Lead enrichment workflow in n8n: Google Sheets trigger connected to Olostep, OpenAI, Code, and Google Sheets update nodes

​
Step 1: Set up your Google Sheet

Create a sheet with these columns: Company URL, Industry, Description, Company Size, Enriched. The workflow reads from Company URL and fills in the rest.

​
Step 2: Add a Google Sheets trigger

In n8n, add a Google Sheets trigger node. Set the event to Row Added, point it at your sheet, and set it to watch the Company URL column. Now every time you paste a new URL into the sheet, this workflow fires.

​
Step 3: Add Olostep Scrape Website

Connect an Olostep Web Scraper node after the trigger. Set:
  • Action: Scrape Website
  • URL: {{ $json["Company URL"] }} (pulls the URL from the new row)
  • Output Format: Markdown
Markdown works best here because it strips navigation, ads, and boilerplate. The AI node in the next step gets clean prose about the company instead of raw HTML noise.

​
Step 4: Add an OpenAI node

Connect an OpenAI node. Set the model to gpt-4o-mini (fast and cheap for extraction tasks) and use this prompt: 
You are a sales researcher. Based on the company website content below, extract:
1. Industry (one phrase, e.g. "B2B SaaS", "E-commerce", "Healthcare")
2. One-sentence company description (max 20 words)
3. Estimated company size (Startup / SMB / Mid-market / Enterprise)

Return only a JSON object with keys: industry, description, company_size.

Website content:
{{ $json.markdownContent }}
The markdownContent field is what Olostep returns from the scrape, as clean plain text.

​
Step 5: Parse the AI response and write back

Add a Code node to parse the JSON from OpenAI: 
const parsed = JSON.parse($input.first().json.message.content);
return [{ json: parsed }];
Then connect a Google Sheets node set to Update Row. Map the columns:
  • Industry → {{ $json.industry }}
  • Description → {{ $json.description }}
  • Company Size → {{ $json.company_size }}
  • Enriched → Yes

​
What you get

Paste a URL like https://notion.so into your sheet, and within ~10 seconds the row fills in:
Company URLIndustryDescriptionCompany SizeEnriched
https://notion.soProductivity SaaSAll-in-one workspace for notes, docs, and databasesMid-marketYes
From here you can extend this workflow: add a Slack notification when enrichment completes, filter by industry before writing back, or replace Google Sheets with HubSpot to update contacts directly.

​
Templates

Ready-to-import n8n workflows built with Olostep:

Crawl docs → AI knowledge base

Crawl documentation sites with Olostep and structure the output into an AI-ready knowledge base.

Google Maps leads → decision-maker enrichment

Scrape business leads from Google Maps and enrich them with decision-maker details.

Mine user complaints → insight report

Analyze complaints with Olostep + Gemini and generate structured insight reports in Google Docs.

Amazon product extraction → Google Sheets

Extract Amazon product URLs and metadata with Olostep, then sync the results to Sheets.
Browse all Olostep workflows on n8n.io →

​
Parsers

Add a parser ID to the Parser field on any Scrape or Batch action to get structured data instead of raw content:
ParserExtracts
@olostep/amazon-productTitle, price, rating, reviews, images, variants
@olostep/google-searchResult titles, URLs, snippets
@olostep/google-mapsBusiness name, address, rating, reviews
@olostep/extract-emailsEmail addresses from any page
@olostep/extract-socialsSocial profile links (X, GitHub, LinkedIn, etc.)
@olostep/extract-calendarsGoogle Calendar and ICS links
See the full list in the Olostep parser store →

​
Troubleshooting

Copy the key directly from olostep.com/dashboard with no trailing spaces. Delete and recreate the credential in n8n if the error persists.
Increase Wait Before Scraping (try 2000–5000ms for JS-heavy pages). Confirm the URL is publicly accessible without a login. If a specific domain is consistently failing, contact info@olostep.com.
The URLs to Scrape field expects a JSON array:
[
  { "url": "https://example.com/page-1", "custom_id": "p1" },
  { "url": "https://example.com/page-2", "custom_id": "p2" }
]
Use a Code node upstream to build this array from your data if needed.
Add a Wait node between scrape steps, or switch to Batch Scrape URLs instead of looping single scrapes. Check current usage in the dashboard.
On n8n Cloud, community nodes must be enabled by a workspace owner. On self-hosted, make sure N8N_COMMUNITY_PACKAGES_ENABLED=true is set in your environment. See n8n’s installation guide.

Scrapes API

Full reference for the scrape endpoint

Batches API

How batch jobs work and how to retrieve results

Crawls API

Crawl configuration and result retrieval

Maps API

URL discovery and filtering options

​
Get Started

Ready to automate your web search, scraping, and crawling workflows?

n8n Website

n8n platform

Install the Node

Install n8n-nodes-olostep and start building automated workflows
Connect Olostep with n8n and automate your web data extraction today!