Ojarikre Gregory Egbenine

import os import re import PyPDF2 from PyPDF2 import PdfReader !python your_script.py def extract_owner_names(pdf_path): owner_names = [] with open(pdf_path, 'rb') as file: pdf_reader = PyPDF2.PdfReader(file) for page_number in range(len(pdf_reader.pages)): page = pdf_reader.pages[page_number] text = page.extract_text() # Define your regular expression pattern for detecting project owner names pattern = r'Project by: ([A-Za-z\s]+)' matches = re.findall(pattern, text) owner_names.extend(matches) return owner_names def main(): # Directory containing PDF files pdf_directory = '/content/list_of_PDFs' # List all PDF files in the directory pdf_files = [f for f in os.listdir(pdf_directory) if f.endswith('.pdf')] for pdf_file in pdf_files: pdf_path = os.path.join(pdf_directory, pdf_file) owners = extract_owner_names(pdf_path) if owners: print(f"Project owners in '{pdf_file}': {', '.join(owners)}") else: print(f"No project owners found in '{pdf_file}'") if __name__ == "__main__": main()