pdf_parser/pdfs/pdf_parser.py

import os
from utils import (
    extract_filing_date,
    address_extraction,
    refer_exteraction,
    email_extraction,
    telephone_number_extraction,
)

import tika
from tika import parser

tika.initVM()


def main(PATH):
    """
    parses the required data from the pdfs
    """
    required_files = [file for file in os.listdir(PATH) if file.find(".pdf") != -1]
    for idx, file in enumerate(required_files):
        print(idx, file)
        content = parser.from_file(file)["content"].strip().replace("\n", "")
        print(extract_filing_date(content))
        print(address_extraction(content))
        print(refer_exteraction(content))
        print(email_extraction(content))
        print((telephone_number_extraction(content)))


if __name__ == "__main__":
    HOME_DIR = os.path.expanduser("~")
    BASE_DIR = "Code/pdf_parser/pdfs"
    PATH = os.path.join(HOME_DIR, BASE_DIR)
    main(PATH)