AI Spun Webscraper

Sitemaps

🗺️

No sitemaps yet

Create your first sitemap to start scraping websites

Selectors

Editing selectors for: No sitemap selected

🎯

No selectors defined

Add selectors to extract data from web pages

Selector ID

Type

Allow multiple selections (collect all matching elements) When enabled, all matching elements will be collected instead of just the first one

CSS Selector

Click "Pick Element" to visually select elements on the page

Attribute Name

Test Selector

Run Settings

Rate Limiting

Delay between pages (ms) Delay in milliseconds between page loads to avoid overwhelming servers

Pagination

Maximum pages to scrape Maximum number of pages to scrape per sitemap

Infinite Scroll

Scroll delay (ms) Time to wait for new content to load after scrolling

Data Processing

Remove duplicate records Automatically remove duplicate records based on content

Scraped Data

0 Total Records

0 Sitemaps

Never Last Scraped

No data available
📊 No scraped data yet. Start scraping to see results here.

Export Data

Export Format

CSV Comma-separated values, compatible with Excel and Google Sheets

XLSX Excel format with advanced formatting support

Export Filters

Sitemap

Date From

Date To

Export Preview

0 records will be exported

AI API Configuration

Configure your AI service providers for enhanced data processing and analysis

🕷️ Apify Configuration

Apify provides powerful web scraping and automation capabilities. Configure your API key to enable advanced scraping features.

Apify API Key Get your API key from Apify Console

Apify Base URL Default Apify API endpoint

Apify Features

✓ Advanced web scraping with JavaScript rendering
✓ Proxy rotation and IP management
✓ Large-scale data extraction
✓ Anti-bot detection bypass
✓ Scheduled scraping tasks

🤖 OpenRouter Configuration

OpenRouter provides access to multiple AI models for data analysis, content generation, and intelligent processing.

OpenRouter API Key Get your API key from OpenRouter Dashboard

OpenRouter Base URL Default OpenRouter API endpoint

Preferred AI Model Choose the AI model for data processing tasks

OpenRouter Features

✓ Intelligent data classification and tagging
✓ Content summarization and analysis
✓ Data quality assessment
✓ Automated data cleaning and formatting
✓ Natural language processing

🔧 AI Processing Options

Configure how AI services are integrated into your scraping workflow

Enable automatic AI processing of scraped data Automatically analyze and enhance scraped data using AI

Enable AI-powered data cleaning Use AI to clean and standardize extracted data

Generate content summaries Create AI-generated summaries of scraped content

AI Processing Batch Size Number of records to process in each AI batch (1-100)

🔍 API Status

Apify: Not configured

OpenRouter: Not configured

About AI Spun Webscraper

Privacy & Security

AI Spun Webscraper runs entirely in your browser. No data is sent to external servers. All scraped data is stored locally in your browser's storage.

Your Privacy is Protected:

✓ All data processing happens locally in your browser
✓ No data is sent to remote servers or third parties
✓ No analytics or tracking is performed
✓ Scraped data remains on your device only
✓ Extension works completely offline after installation

This extension respects your privacy and operates with minimal permissions.

Data Storage

Sitemaps and settings are stored in Chrome's local storage
Scraped data is temporarily stored during scraping sessions
No personal information is collected or transmitted

How to Use

Create a Sitemap: Define the websites you want to scrape
Add Selectors: Use the visual selector tool to choose what data to extract
Configure Settings: Set rate limits and other scraping parameters
Start Scraping: Use the popup to begin data extraction
Export Data: Download your results as CSV or XLSX files

Supported Selector Types

Text: Extract text content from elements

Name: Extract and clean name fields with proper formatting

Email: Extract and validate email addresses from text or links

Phone: Extract and format phone numbers from text or links

URL: Extract links and URLs

Image: Extract image sources

Attribute: Extract specific HTML attributes

HTML: Extract raw HTML content

Number: Extract and parse numeric values

Date: Extract and parse date values

List: Extract multiple items from a list

Pagination: Handle multi-page navigation

Infinite Scroll: Handle dynamically loaded content

Version Information

Version: 0.0.5

Manifest Version: 3

Last Updated:

Features Added: UI improvements, Enhanced header link visibility, Better contrast