pdf_title_image/tools.py

''' helper methods
'''
import pandas as pd
import numpy as np
import re
from Timer import timer
import json
import os
import requests
from pprint import pprint


class BaseMethods():
    ''' base methods class
    '''
    def __init__(self) -> None:
        pass

    def pandas_read_xls(self, file_path:str, sheetname:str="Sheet1"):
        ''' 读取xls文件方法
        '''
        return pd.read_excel(file_path,sheet_name=sheetname)

    def json_read(self, file_path:str):
        ''' 读取json文件方法
        '''
        with open(file_path, "r", encoding='utf-8') as fp:
            return json.load(fp)
        
    def save_file(self, save_data:list, save_path:str, file_format:str):
        ''' 保存文件
        '''
        print(len(save_data))
        if file_format == "json":
            with open(save_path,'w',encoding='utf-8') as sf:
                sf.write(json.dumps(save_data,ensure_ascii=False))
        elif file_format == "xlsx" or file_format == "xls":
            with pd.ExcelWriter(save_path) as fp:
                save_data.to_excel(fp, sheet_name="Sheet1")
        elif file_format == 'txt':
            with open(save_path, 'w', encoding='utf-8') as tx:
                for data in save_data:
                    tx.write(data+"\n")
    
    def traverse_file(self, dirpath:str):
        '''
        遍历文件夹下文件
        '''
        filename = tuple()
        for root, dir, files in os.walk(dirpath):
            for name in files:
                filename = filename.__add__((name,))
        return filename



    

if __name__ == "__main__":
    pass