pdf_parser/expert_report/parse_expert_pdf.py

from parse_expert_pdf_utils import (
    case_number_extraction,
    expert_name_extraction,
    plaintiff_extraction,
    defendent_extraction,
    patent_extraction,
    on_behalf_of_extraction,
    acronym_extraction,
    hourly_compensation,
    date_extraction,
    address_extraction,
)
import tika
import os
from tika import parser

tika.initVM()
import warnings

warnings.filterwarnings("ignore")


def main(path):
    required_files = [file for file in os.listdir(path) if file.find(".pdf") != -1]
    for idx, file in enumerate(required_files):
        print(idx, file)
        parsed_pdf = parser.from_file(file)
        # print(parsed_pdf.keys())

        content = parsed_pdf["content"].strip().replace("\n", "")
        # print(content)
        date = date_extraction(content)
        print(date)
        address = address_extraction(content)
        print(address)


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