Pytesseract works but it is slow...
It is unfortunately too slow to use for the web scraping - it becomes a bottleneck. Try to find faster alternatives, maybe even less accurate just for the web scraping part?
Possible things to explore:
- Separate service running OCR away from main machine?
- Megaparse?
Pytesseract works but it is slow...
It is unfortunately too slow to use for the web scraping - it becomes a bottleneck. Try to find faster alternatives, maybe even less accurate just for the web scraping part?
Possible things to explore:
- Separate service running OCR away from main machine?
- Megaparse?