AI SCRAPER n8n INTEGRATION: AUTOMATE AI SCRAPER WITH N8N

This action lets you execute an existing scraper you've already configured in AI Scraper. Instead of setting up scraping parameters from scratch every time, you reference a pre-built scraper by name or ID—perfect for recurring extraction tasks where the configuration stays consistent but the target URL changes.

Key parameters:

• Scraper Name or ID: This required text field identifies which pre-configured scraper to run. Enter either the exact name or the unique ID from your AI Scraper dashboard.
• URL: An optional parameter that overrides the default target URL. Useful when you want to run the same scraper logic against different pages.
• Proxy Country: Required dropdown to select which country's proxy servers to route requests through. Use "Default" for automatic selection, or specify a country when geo-restricted content matters.
• Cookies: Optional text array for passing authentication cookies. Essential when scraping pages behind logins or when session data affects the content displayed.

When to use it: This action shines for production workflows where you've already perfected your scraper configuration. Run daily inventory checks, monitor specific product pages, or extract data from authenticated dashboards—all using proven scraper setups.

The Parse HTML action takes raw HTML content and extracts structured data using AI-powered parsing. Rather than scraping a live URL, you feed it HTML you've already obtained—from webhooks, API responses, or other workflow steps—and let AI Scraper intelligently pull out the data you need.

Key parameters:

• Content: Required text field where you paste or reference the HTML content to parse. This can be a static string or dynamic data from previous workflow nodes.
• Prompt: Optional guidance for the AI parser. Describe what you're looking for in plain language, like "Extract all product names and prices" or "Find the main article text and author name."
• Columns Input Mode: Determines how you'll define output columns. "Fields" mode lets you manually specify each column you want extracted.
• Columns - Name: Define the label for each data column you want to extract. Add multiple columns to structure your output data.
• Column Prompt: Optional per-column guidance. For complex extractions, tell the AI exactly what each column should contain.

When to use it: Ideal when HTML content arrives via webhooks, when you need to reprocess previously scraped pages, or when combining multiple HTML sources into a unified dataset. The AI parsing handles layout variations that would break traditional CSS selectors.

The Scrape URL action is your go-to for direct web scraping. Point it at any webpage, define the columns you want to extract, and let AI Scraper fetch and parse the content in one step. This combines fetching and parsing into a single, streamlined operation.

Key parameters:

• URL: Required text field for the webpage you want to scrape. Accepts any valid HTTP/HTTPS URL.
• Prompt: Optional high-level guidance for extraction. Describe what type of data matters: "Get all blog post titles and publication dates" or "Extract the pricing table data."
• Columns Input Mode: Choose how to define your output structure. "Fields" mode provides granular control over each column.
• Columns: Add column definitions to structure your extracted data. Each column becomes a field in your output.
• Mode: Select the scraping mode—"Standard" works for most public pages. Advanced modes handle JavaScript-heavy sites.
• Proxy Country: Optional dropdown for routing requests through specific country proxies. Critical for accessing geo-restricted content or avoiding regional blocks.

When to use it: Perfect for on-demand scraping triggered by other workflow events. A new row in your tracking spreadsheet? Automatically scrape that URL. Customer submits a competitor link? Extract pricing data instantly. This action handles the full scraping lifecycle in one node.