Python使用（三）-----常用代码块

1. 确定文本编码

# coding=utf-8
def check_charset(file_path):
    import chardet
    with open(file_path, "rb") as f:
        data = f.read(4)
        charset = chardet.detect(data)['encoding']
    return charset

2. 拆分文件

# coding=utf-8
def split_file(file_path,num):
    with open(file_path, "r") as f:
        s = f.read();
        for i in range(num):
            with open(file_path+str(i+1), 'w',encoding='utf8') as ff:
                ff.write(s[int(len(s)/num*i): int(len(s)/num*(i+1))])
                print('第',str(i+1),'个文件写入完成')

3.列举文件夹下的文件

import os
src_dir='E:/temp'
target_dir='D:/download'
for root, dirs, files in os.walk(src_dir, topdown=True):
    for name in files:
#         create_empty(os.path.join(target_dir, name))
#         print('created '+name)
        print(os.path.join(root, name))
#     for name in dirs:
#         print(os.path.join(root, name))

4.创建空文件（如果已存在，不变动）

def create_empty(file_name):
    with open(file_name,"a") as f:
        pass

5.获取文件修改时间

def get_modify_date(file_name):
    times = os.path.getmtime(file_name)
    localtime = time.localtime(times)
#     print(time.strftime("%Y-%m-%d %H:%M:%S",localtime))
#     print(time.strftime("%Y-%m-%d",localtime)=='2022-09-12')
    return time.strftime("%Y-%m-%d",localtime)

6.复制文件

import shutil
shutil.copy(src_dir,target_dir)

7.字符串数据库与驼峰转换

[a.split('_')[0].lower() + ''.join([i.capitalize() for i in a.split('_')[1:]]) for a in ['BILLACCOUNT_CODE','BILLACCOUNT_NAME']]

8.mysql

import pymysql
import requests


data = []
conn = pymysql.connect(host="", port=3306, user='', passwd='', db='', charset='utf8')
cursor = conn.cursor(pymysql.cursors.DictCursor)
cat_param = []
for cat in data:
    print(cat)
    name = cat['cate_name']
    num = cat['cate_num']
    oid = cat['cate_id']
    cursor.executemany("INSERT INTO `favorite`.`t_fav_category` (`name`, `count`, `origin_id`, `create_time`) VALUES (%s,%s,%s,NOW())", 
                       [[name,num,oid]])
    new_id = cursor.lastrowid
    print('newid'+str(new_id))
    childs_arr = []
    for one in cat['childs']:
        one_catid = new_id
        one_origid = one['id']
        one_title = one['title']
        one_cover = one['cover']
        g = requests.get(one_cover)
        one_cover_data = g.content
        one_upname = one['upname']
        one_pubt = one['pubtime']
        one_favt = one['favtime']
        one_link = one['link']
        one_item = (one_catid,one_origid,one_title,one_cover,one_cover_data,one_upname,one_pubt,one_favt,one_link)
        childs_arr.append(one_item)
    cursor.executemany("INSERT INTO `favorite`.`t_fav_item`  \
                           (`cat_id`, `origin_id`, `title`, `cover`,cover_data, `up_name`, `pub_time`, `fav_time`, `link`, `create_time`) \
                       VALUES (%s,%s,%s,%s,%s,%s,%s,%s,%s,NOW())", 
                       childs_arr)
    # print(childs_arr)
conn.commit()
cursor.close()
conn.close()
# print(len(data))

9.requests

import requests

g = requests.get('http://i2.hdslb.com/bfs/archive/1d3805a8b91d049af93f43897267a7de1baa59e8.jpg')
with open('E:/work/20230402/a.jpg','wb') as f:
    f.write(g.content)

10.获取运行参数

# -*- coding: utf-8 -*-
import argparse

if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--a', type=int, default=5,help='这是帮助信息')
    parser.add_argument('--b', type=float, default=0.1)
    parser.add_argument('--c', type=str, default="abc")
    parser.add_argument('--d', type=bool, default=True)
    opt = parser.parse_args()
    print(opt.a,opt.b,opt.c,opt.d)

参考：真正解决Windows下UnicodeDecodeError: ‘gbk‘ codec can‘t decode byte 0xff in position 0错误的方法_mighty13的博客-CSDN博客