pdf_parser/pdfs/pdf_parser.py

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

import pandas as pd
import tika
from tika import parser

tika.initVM()


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

    data = pd.DataFrame(data_dict)
    data.to_csv("required_data.csv")


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