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
from tika import parser
import re
import warnings
warnings.filterwarnings('ignore')


def main():
    tika.initVM()
    path = "/home/ftech/Code/xc/pdf_parser/pdfs/2018008353_Mail_Decision.pdf" #2018008353_Mail_Decision.pdf"
    parsed_pdf = parser.from_file(path)
    print(parsed_pdf.keys())

    content = parsed_pdf['content'].strip().replace('\n', '')
    # print(content)
    # case_number = case_number_extraction(content)
    # print(case_number)
    # expert_name = expert_name_extraction(content)
    # print(expert_name)
    # plaintiff = plaintiff_extraction(content)
    # print(plaintiff)
    # defendent = defendent_extraction(content)
    # print(defendent)
    # patent = patent_extraction(content)
    # print(patent)
    # on_behalf_of = on_behalf_of_extraction(content)
    # print(on_behalf_of)
    # acronym = acronym_extraction(content)
    # print(acronym)
    # pay = hourly_compensation(content)
    # print(pay)
    date = date_extraction(content)
    print(date)
    address = address_extraction(content)
    print(address)

if __name__ == "__main__":
    main()