extract_pdf.py

import pypdf
import json

def extract_pdf_text(pdf_path):
    try:
        reader = pypdf.PdfReader(pdf_path)
        text = ""
        for page in reader.pages:
            text += page.extract_text() + "\n"
        return text
    except Exception as e:
        return f"Error: {str(e)}"

# Extract text from both PDFs
pdf1_path = "Assignment for Associate Product Manager/6814842c327d0_Assessment_for_APM_Role.pdf"
pdf2_path = "Assignment for Associate Product Manager/assignment task UnStop.pdf"

print("=" * 80)
print("PDF 1: 6814842c327d0_Assessment_for_APM_Role.pdf")
print("=" * 80)
pdf1_text = extract_pdf_text(pdf1_path)
print(pdf1_text)

print("\n" + "=" * 80)
print("PDF 2: assignment task UnStop.pdf")
print("=" * 80)
pdf2_text = extract_pdf_text(pdf2_path)
print(pdf2_text)