pdf_parser/expert/parse_expert_pdf.py

from parse_expert_pdf_utils import (
    case_number_extraction,
    expert_name_extraction,
)
import tika
from tika import parser
import re
import warnings
warnings.filterwarnings('ignore')


def main():
    tika.initVM()
    path = "/home/omkardesai/Code/pdf_parser/pdfs/expert_parse_pdf.pdf"
    parsed_pdf = parser.from_file(path)
    print(parsed_pdf.keys())
    # for mykeys, myvalues in parsed_pdf['metadata'].items():
    #     print(f"{mykeys}")
    #     print(f"{myvalues}")

    content = parsed_pdf['content']
    # print(content)
    case_number = case_number_extraction(content)
    print(case_number)
    expert_name = expert_name_extraction(content)
    print(expert_name)


if __name__ == "__main__":
    main()