pdf_parser/complaints/test.py

import re
import tika
from tika import parser

tika.initVM()


if __name__ == "__main__":
    data = (
        parser.from_file(
            "/home/ftech/Desktop/harsh_parikh_codes/PDF_Scrapper/Complaint/document.pdf"
        )["content"]
        .strip()
        .replace("\n", "")
    )
    print(data)
    # pattern = r"OF\s\w+(\s.*?\,).*?Plaintiff"
    # print(re.search(pattern, data).groups()[0])
    # pattern = r"Plaintiff[s]?.*v[s]?\.(.*)Defendant\."
    # re.search(pattern, data).group()