/web-scraper-for-VCs-and-startups

Created this bot to aid part of my work that required me to collate many AI startups in Singapore. This allowed me to quickly gain information on the company via their website, and categorise them into categories that would be of interest to our firm.

Primary LanguagePython

Process:

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

Happy web scraping!