RPA流程开发通用函数梳理

注：基于艺赛旗设计器开发

1. 自定义添加日志

import time, os

# file_content：日志内容
def add_logs(file_content):
	time_name = time.strftime('%Y%m%d',time.localtime(time.time()))
	file_dir = '日志文件存放目录'
	file_name = '前缀' + str(time_name)
	path = file_dir.strip()
	isExists = os.path.exists(path)
	if not isExists:
		# 如果不存在则创建目录，存在就往文件中写日志
		os.makedirs(path)
	file_path = open(file_dir + file_name + '.log','a')
	file_path.write(file_content)
	file_path.close()

2. 自定义记录台账

import ubpa.iexcel as iexcel
import shutil

# path：台账模板文件路径
def makedir_account(path):
	t1 = time.strftime('%Y%m%d',time.localtime(time.time()))
	path1 = '台账存放目录' + t1
	if not os.path.exists(path1):
		# 如果不存在则创建
		os.makedirs(path1)
		iexcel.close_excel_apps()
		shutil.copy(path，path1)
		account = path1 + '台账文件名'
	if os.path.exists(path1):
		account = path1 + '台账文件名'
	return account

3. excel去除重复行

import pandas as pd

# path1为需去重的excel所在路径，path2为去重后文件内容保存路径
def duplicate(path1,path2):
	data = pd.DataFrame(pd.read_excel(path1,'Sheet1'))
	print(data)
	# 查看是否有重复行
	re_row = data.duplicated()
	print(re_row)
	# 去除重复行
	no_re_row = data.drop_duplicates()
	print(no_re_row)
	# 基于某列去除重复行
	wp = data.drop_duplicates(['列名'])
	# 将去除重复行后的数据输出到excel中
	no_re_row.to_excel(path2)

4. 解压7z压缩包

import os

# path：需解压的压缩包路径
def unzip(path):
	folder_name = '7z解压软件所在路径'
	# 定位到指定路径
	os.chdir(folder_name)
	z_path = path
	un_path, name = os.path.splitext(z_path)
	un_path = '"{}"'.format(un_path)
	cmd = '7z.exe x "{}" -o{} -aos -r'.format(z_path,un_path)
	os.system(cmd)

5.excel设置访问密码

import win32com.client

"""
excel文件设置访问密码
"""
def set_pwd_xlsx(dec_path, enc_path, pw_str):
    """
    param:dec_path:excel文件路径，enc_path:excel保存路径，pw_str:密码字符串
    """
    xcl = win32com.client.Dispatch("Excel.Application")
    wb = xcl.workbooks.open(dec_path, False, False)
    xcl.DisplayAlerts = True
    wb.SaveAs(enc_path, None, pw_str)
    wb.Close()
    xcl.Quit()

6.生成指定目录下文件路径

import os
"""
生成指定目录下所有文件路径
"""
def get_files_path(dir_name):
    # dir_name:目录路径
    stack = []
    result_xlsx = []
    stack.append(dir_name)
    # 栈空代表所有目录均已遍历
    while len(stack) != 0:
        temp_name = stack.pop()
        try:
            temp_name2 = os.listdir(temp_name)
            for ex in temp_name2:
                stack.append(temp_name + "\\" + ex)
        except:
            result_xlsx.append(temp_name.strip())
    return result_xlsx    

7.获取验证码

import re, pytesseract
from PIL import Image
"""
获取验证码
"""
def get_tesseract(img_path, lang=None):
    txt = None
    try:
        image = Image.open(img_path)
        txt = pytesseract.image_to_string(image, lang=lang)
        if txt:
            txt = re.sub('\D', '', txt)
            # logger.info(f'ocr识别函数验证码【{txt}】')
    except Exception as e:
        # logger.error(f'ocr识别函数：{e}')
    finally:
        return txt