Convert list of PDF documents to text files

pdf_2_txt.py

import os
from pypdf import PdfReader

# Get all PDF files in the current directory
pdf_files = [f for f in os.listdir('.') if f.endswith('.pdf')]

for pdf_file in pdf_files:
    # Create a PDF reader object
    reader = PdfReader(pdf_file)
    
    # Extract text from all pages
    text = ''
    for page in reader.pages:
        text += page.extract_text()
    
    # Save the extracted text to a .txt file with the same name
    txt_file = pdf_file.replace('.pdf', '.txt')
    with open(txt_file, 'w', encoding='utf-8') as f:
        f.write(text)