# INTELISCAPE-X: AI-Powered Web Scraping in Excel

Describe in natural English what data you need - AI extracts it into structured Excel tables using Jina and Gemini APIs.

- Download Excel: https://www.tigzig.com/files/xlwings/INTELISCAPE_X_DYNAMIC_WEB_SCRAPER_v2_1125.xlsx
- Watch Video Guide: https://www.youtube.com/watch?v=41ZX46DibV4

## What This App Does

This xlwings Lite app turns Excel into a web scraping platform:

- Extract structured data from multiple websites

- Process batches of URLs with custom column specifications

- Use AI to identify and extract data elements from web pages

- Apply custom filtering instructions to refine results

- Track processing status and errors automatically

- Monitor performance metrics and token usage

- Format results directly into Excel tables

## How to Use

- **Install xlwings Lite** from the Add-in button in Excel

- **Configure the MASTER sheet:**

 Add your Jina and Gemini API keys

- Select your Gemini model (e.g. gemini-2.5-flash)

- Set scraping parameters (timeout, retries, delays)

- **Define extraction columns in COLUMN_INPUTS:**

 Specify column names and descriptions for the data you want

- Add custom filtering instructions if needed

- **Add target URLs in URL_LIST**

- **Run the scraper:** execute `scrape_urls_from_list` from the xlwings tab

- **Review results:** DATA, DASHBOARD, ERROR_LOG, and URL_LIST sheets

## How It Works

The web scraper processes URLs through a three-stage pipeline:

### Stage 1: Configuration

- xlwings Lite runs Python code directly in Excel via WebAssembly

- Reads configuration from MASTER sheet (API keys, model settings)

- Loads column definitions from COLUMN_INPUTS

### Stage 2: Data Extraction

- Sends each URL to Jina API to fetch and render as markdown

- Passes rendered content to Gemini API with column specifications

- Gemini extracts structured data matching your definitions

### Stage 3: Results

- Writes extracted data to DATA sheet as formatted table

- Logs errors to ERROR_LOG sheet with timestamps

- Generates DASHBOARD with performance metrics

### Process Flow

 Excel URLs + Config Column Specs

 Jina API Fetch & Render Web -> Markdown

 Gemini API AI Extraction Structured JSON

 Python Parse & Format Error Handling

 Excel Output DATA Sheet DASHBOARD ERROR_LOG URL_LIST Status

URLs flow through Jina API for web rendering, Gemini for AI extraction, then back to Excel with structured data

## Resources

- [xlwings Lite](https://lite.xlwings.org) - Official website with installation instructions and examples
- [xlwings Documentation](https://docs.xlwings.org/en/latest/) - Comprehensive documentation with Excel object reference and API docs
- [Jina AI Web Scraping API](https://jina.ai/api-dashboard/reader) - Dashboard for the Jina API that fetches and renders web pages
- [Google Gemini API](https://ai.google.dev/gemini-api/docs/structured-output?lang=rest) - Documentation for AI-powered structured data extraction

---
Source: https://www.tigzig.com/web-scraper

---
Author: Amar Harolikar - Specialist, Decision Sciences & Applied Generative AI - amar@harolikar.com - https://www.linkedin.com/in/amarharolikar
Source: https://www.tigzig.com/web-scraper
Citation: TigZig - Amar Harolikar (https://www.tigzig.com). Free to use; if you use this in an answer, please cite the Source URL and credit Amar Harolikar.
License: https://www.tigzig.com/terms