nadya-p

from tika import parser
import os


def extract_text_from_pdfs_recursively(dir):
    for root, dirs, files in os.walk(dir):
        for file in files:
            path_to_pdf = os.path.join(root, file)
            [stem, ext] = os.path.splitext(path_to_pdf)
            if ext == '.pdf':

nadya-p

import json
import os


class Settings:
    _config_location = 'config.json'

    def __init__(self):
        if os.path.exists(self._config_location):
            self.__dict__ = json.load(open(self._config_location))