pdf_parser/expert_resume/parse_expert_resume.py

from collections import defaultdict
import os
from IPython.display import display
import tika
import pandas as pd

tika.initVM()
from tika import parser

from parse_resume_utils import (
    extract_email,
    extract_phone,
    extract_zipcode,
    extract_case_numbers,
    extract_litigation_experience,
    extract_patents_issued,
)


def main(PATH):
    """
    Returns the required data in a dataframe format
    """
    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):
        print(idx, file)
        parse_content = parser.from_file(file)["content"].strip().replace("\n", "")
        data_dict["email"].append(extract_email(parse_content))
        data_dict["phone"].append(extract_phone(parse_content))
        data_dict["zipcode"].append(extract_zipcode(parse_content))
        data_dict["cases"].append(extract_case_numbers(parse_content))
        data_dict["litigation_experience"].append(
            extract_litigation_experience(parse_content)
        )
        data_dict["patents_issued"].append(extract_patents_issued(parse_content))

    return pd.DataFrame(data_dict)


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