| import pytesseract | |
| from pdf2image import convert_from_path | |
| def pdf_to_text(pdf_path, output_path): | |
| # Convert PDF to list of images | |
| pages = convert_from_path(pdf_path, 300) | |
| # Extract text from all pages and join them | |
| text = "" | |
| for page in pages: | |
| text += pytesseract.image_to_string(page) | |
| # Write text to file | |
| with open(output_path, "w", encoding="utf-8") as file: | |
| file.write(text) | |
| print(f"OCR completed. Text saved to {output_path}") | |
| # Usage | |
| pdf_path = 'input.pdf' | |
| output_path = 'output.txt' | |
| pdf_to_text(pdf_path, output_path) |