ParsePDF - Python Script

ParsePDF Source Code

import pytesseract
from pdf2image import convert_from_path
import PyPDF2
import os

def extract_text_from_pdf(pdf_path):
    text = ""
    with open(pdf_path, "rb") as file:
        reader = PyPDF2.PdfReader(file)
        for page in reader.pages:
            text += page.extract_text() or ""

    if not text.strip():
        # If text extraction failed, use OCR
        images = convert_from_path(pdf_path)
        text = "\n".join(pytesseract.image_to_string(img) for img in images)
    
    return text

# Example usage
pdf_path = "example.pdf"
if os.path.exists(pdf_path):
    extracted_text = extract_text_from_pdf(pdf_path)
    print(extracted_text)
else:
    print("PDF file not found.")
        

Download Source Code