python3 使用 requests pytesseract PIL 实现识别网站验证码及模拟登陆

#!/usr/bin/python

# -*- coding: UTF-8 -*-

import requests

from PIL import Image

from pytesseract import image_to_string

from time import time

#爬虫

class reptilian:

def__init__(self, url):

self.url = url

self.req = requests.Session()

#文件保存本地

defgetFile(self, urlPath, fileName):

self.fileName = fileName

urlPath = self.url+urlPath

fileCon = self.req.get(urlPath)

file=open(self.fileName, 'wb')

file.write(fileCon.content)

file.close()

returnself

#识别验证码

defgetDist(self):

image = Image.open(self.fileName)

self.log_code = image_to_string(image)

returnself

#登陆

deflogin(self, login_url, login_data, timeout=8):

getUrl = self.url + login_url

self.req.post(getUrl, login_data)

#目标网站

url = 'xxxx'

#登陆页

login_url = "xxxx"

#验证码url

code_url = "xxx"

#验证码保存名称

imgName = str(int(time())) + '.jpg'

#验证码保存位置

imgPath = 'xxx'

#登陆参数

login_data = {

"ue": "xxx",

"pd": "xxx",

"code": '',

}

#实例化

rep = reptilian(url)

#获取验证码

rep.getFile(code_url, imgPath + imgName)

#识别验证码

rep.getDist()

#获取验证码

login_data['code'] = rep.log_code

#登陆

rep.login(login_url, login_data)