gistfile1.txt

import os
import docx
from datetime import datetime
from multiprocessing import Pool

def extract_paragraphs(args):
    docx_file, keywords = args
    doc = docx.Document(docx_file)
    paragraphs = []
    for para in doc.paragraphs:
        text = para.text
        for keyword in keywords:
            if keyword in text:
                paragraphs.append((text, doc.core_properties.created))
                break
    return paragraphs

def process_documents(directory, keywords, num_processes):
    docx_files = [os.path.join(directory, f) for f in os.listdir(directory) if f.endswith('.docx')]
    with Pool(processes=num_processes) as pool:
        args = [(file, keywords) for file in docx_files]
        results = pool.map(extract_paragraphs, args)
    return results

if __name__ == "__main__":
    keywords = ["EKS Blueprints"]
    directory = "2x2s"
    num_processes = 10  # Number of concurrent processes to use

    all_paragraphs = process_documents(directory, keywords, num_processes)

    # Flatten the list of lists into a single list
    paragraphs = [p for sublist in all_paragraphs for p in sublist]

    # Process the extracted paragraphs
    for paragraph, creation_date in paragraphs:
        print(f"Paragraph: {paragraph}\nCreation Date: {creation_date}\n")