๐๐ ๐๐จ๐ฐ๐๐ซ๐๐ ๐๐ฒ๐ง๐๐ฆ๐ข๐ ๐๐๐ ๐๐๐ซ๐๐ฉ๐๐ซ ๐ข๐ง ๐๐ฑ๐๐๐ฅ | ๐๐ฒ๐ญ๐ก๐จ๐ง+๐๐ ๐ข๐ง ๐๐ฑ๐๐๐ฅ | ๐ฑ๐ฅ๐ฐ๐ข๐ง๐ ๐ฌ ๐๐ข๐ญ๐ - ๐๐๐ซ๐ญ ๐.
- Amar Harolikar
- Apr 15
- 2 min read
Updated: Apr 24
Extract structured data from websites into Excel - with Jina AI and Gemini.
Detailed info , source codes, how-to guides, resources and templates available on REX
๐๐ข๐ญ๐ก ๐ฑ๐ฅ๐ฐ๐ข๐ง๐ ๐ฌ ๐๐ข๐ญ๐, ๐๐ข๐ซ๐๐๐ญ๐ฅ๐ฒ ๐ข๐ง๐ฌ๐ข๐๐ ๐๐ฑ๐๐๐ฅ:
โธ Scrape webpages from a user defined URL list
โธ Define custom columns to be pulled
โธ Add extraction rules and filter conditions
โธ Get formatted Excel tables
๐๐ง ๐ญ๐ก๐ ๐๐๐๐ค๐ ๐ซ๐จ๐ฎ๐ง๐, ๐ฑ๐ฅ๐ฐ๐ข๐ง๐ ๐ฌ ๐๐ข๐ญ๐:
โธ Extracts content in markdown from Jina AI via an API call
โธ Auto-generates JSON schema and structured prompt for Gemini
โธ Gets structured output from Google Gemini via an API call
โธ Generates detailed logs.
๐๐ซ๐๐๐ญ๐ข๐๐๐ฅ ๐ฎ๐ฌ๐ ๐๐๐ฌ๐๐ฌ
โธ Lead gen
โธ Market research
โธ Real estate analysis
โธ Job market intel
๐๐ซ๐ฒ ๐ข๐ญ ๐จ๐ฎ๐ญ
โธ Single Excel file - download below
โธ Excel โ Home โ Add-in โ 'xlwings Lite'
โธ Get API keys for Gemini and Jina AI - no credit card, takes less than a minute. aistudio.google.com / jina.ai
๐๐จ๐๐ฌ + ๐ฐ๐๐ฅ๐ค๐ญ๐ก๐ซ๐จ๐ฎ๐ ๐ก๐ฌ
Go to rex.tigzig.com and head to the xlwings Lite section - full templates, how-to guides, backend code, and technical breakdowns for every xlwings Lite app in the series.
๐๐๐ฌ๐ญ ๐ฑ๐ฅ๐ฐ๐ข๐ง๐ ๐ฌ ๐๐ข๐ญ๐ ๐๐ฎ๐ข๐ฅ๐๐ฌ
โธ AI Technical Analysis
โธ Formatted PDF Report
โธ Web Report
โธ Complex visualizations with subplots
โธ Remote Database Queries
โธ API calls
โธ AI Schema detection
โธ Automated workflows
โธ Exploratory Data Analysis
โธ Machine Learning Models
๐ฑ๐ฅ๐ฐ๐ข๐ง๐ ๐ฌ ๐๐ข๐ญ๐
Built by ย Felix Zumstein, xlwings Lite is a free and powerful Python-in-Excel solution that enables complex automation workflows, custom functions, database access, AI agents, LLMs, analytics, ML, APIs, and web services.
๐ ๐ข๐ง๐ ๐๐ซ๐ข๐ง๐ญ
This is an example app to show how to set up AI web scraping inside Excel using xlwings Lite. Works well for simple sites; complex or recursive scrapes need custom code. Always check site terms, robots.txt, and rate limits.