import os
import fitz
import spacy
import re


def extract_text_from_pdf(pdf_path):
    text = ""
    try:
        with fitz.open(pdf_path) as doc:
            for page in doc:
                text += page.get_text("text") + "\n"
    except Exception as e:
        print(f"Cannot process {pdf_path}: {e}")
    return text


def remove_sensitive_info(text):
    nlp = spacy.load("en_core_web_sm")
    doc = nlp(text)
    cleaned_text = text

    for ent in doc.ents:
        if ent.label_ in ["PERSON", "GPE", "ORG", "LOC"]:
            cleaned_text = cleaned_text.replace(ent.text, "[REDACTED]")

    cleaned_text = re.sub(r'\(?\d{3,4}\)?[- ]?\d{7,8}', '[PHONE NUMBER]', cleaned_text)

    return cleaned_text


def process_pdfs_in_folder(folder_path, output_file):
    with open(output_file, 'w', encoding='utf-8') as out_file:
        for file_name in os.listdir(folder_path):
            if file_name.lower().endswith(".pdf"):
                pdf_path = os.path.join(folder_path, file_name)
                print(f"Processing file: {pdf_path}")
                text = extract_text_from_pdf(pdf_path)
                cleaned_text = remove_sensitive_info(text)
                out_file.write(cleaned_text + "\n\n")


folder_path = "path/to/pdf/folder"
output_file = "output.txt"
process_pdfs_in_folder(folder_path, output_file)