- Filter on Pitchbook, by Vertical, KW, location SGP
- OCR to company names and their respective websites
- Manually checked each link for valid website
- Found some more to make up to a list of 100
- ChatGPT to find links
- Wrote script for scalping email from website
- Wrote script for scalping company description from their website with google search API
- Used chatGPT to categorise the company into table format from description.
- Data cleaning
Happy web scraping!