doczyai-pipelines/ops_scripts/CNC/local_pdf_files_info.py

import os
import csv
import glob
from PyPDF2 import PdfReader
from concurrent.futures import ThreadPoolExecutor, as_completed

"""
This script will collect the following information for all PDF files in a directory and its subdirectories:
- File Name
- File Path
- Page Count

The information will be saved in a CSV file.

NOTE: This script is required mainly in the pre-doczy analysis. There might not be need for this since CNC project is already processed through the textract pipeline. 

"""



def get_pdf_info(pdf_path):
    try:
        with open(pdf_path, 'rb') as file:
            pdf_reader = PdfReader(file)
            page_count = len(pdf_reader.pages)
    except Exception as e:
        print(f"Error reading {pdf_path}: {e}")
        page_count = None
    return os.path.basename(pdf_path), pdf_path, page_count

def collect_pdf_info(directory, output_csv):
    pdf_files = glob.glob(os.path.join(directory, '**', '*.pdf'), recursive=True)

    with open(output_csv, mode='w', newline='', encoding='utf-8') as csv_file:
        csv_writer = csv.writer(csv_file)
        csv_writer.writerow(['File Name', 'File Path', 'Page Count'])

        with ThreadPoolExecutor() as executor:

            futures = {executor.submit(get_pdf_info, pdf): pdf for pdf in pdf_files}

            for future in as_completed(futures):
                result = future.result()
                if result:
                    csv_writer.writerow(result)

    print(f"CSV file '{output_csv}' created successfully.")

directory = 'T:/AArete Client Work/Doczy-Production/Restricted/icertis_contracts'
output_csv = 'icertis/icertis_files.csv'
collect_pdf_info(directory, output_csv)