pdf_parser/expert_report/parse_expert_pdf.py

from collections import defaultdict
import os
import tika
from tika import parser
import pandas as pd
from parse_expert_pdf_utils import (
    plaintiff_extraction,
    defendent_extraction,
    expert_name_extraction,
    case_number_extraction,
    patent_extraction,
    hourly_compensation,
)


tika.initVM()


def main(path: str) -> pd.DataFrame:
    """
    The functions iterates through all the given files and gathers the data in the \
    form of a dataframe
    """
    data = defaultdict(list)
    required_files = [file for file in os.listdir(path) if file.find(".pdf") != -1]
    for file in required_files:
        print(file)
        content = parser.from_file(file)["content"]
        data["file"].append(file)
        data["full_name"].append(expert_name_extraction(content))
        data["hourly_pay"].append(hourly_compensation(content))
        data["plaintiff"].append(plaintiff_extraction(content))
        data["defendant"].append(defendent_extraction(content))
        data["case_number"].append(case_number_extraction(content))
        data["patents"].append(patent_extraction(content))

    data_expert = pd.DataFrame(data)
    data_expert.to_csv("required_data.csv")
    return data_expert


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