selenium + 超级鹰 识别验证码自动登录

登录界面如下

爬虫代码

from selenium import webdriver
import time,random, re, os
from test_chaojiying import Chaojiying_Client    # 导入超级鹰工具类
from PIL import Image
driver = webdriver.Chrome()                             #启动谷歌浏览器
driver.implicitly_wait(10)                              # 隐式等待( 等页面元素加载完毕再开始爬虫)

driver.get('http://127.0.0.1:8999') 	# 使用本地django项目
# 通过xpath 定位到账号密码输入框  并使用send_keys 发送账号密码到输入框
driver.find_element_by_xpath('//*[@id="app"]/div/div[4]/div/form/div[1]/div[2]/div/div/input').send_keys('账号')
driver.find_element_by_xpath('//*[@id="app"]/div/div[4]/div/form/div[2]/div[2]/div/div/input').send_keys('密码')

driver.save_screenshot('one.png')           # 先截取整个屏幕
element = driver.find_element_by_xpath('//*[@id="app"]/div/div[4]/div/form/div[4]')    #通过xpath找到验证码图片
# print(element.location)                  # 打印元素坐标
# print(element.size)                      # 打印元素大小
left = element.location['x'] + 150
top = element.location['y']
right = element.location['x'] + (element.size['width']+220)
bottom = element.location['y'] + (element.size['height']+20)
im = Image.open('one.png')
im = im.crop((left, top, right, bottom))
now = time.strftime("%m-%d %H-%M",time.localtime())
imgName = str(now) + ".png"
im.save(imgName)                          # 经过坐标的过滤，将有验证码的图片保存至本地

chaojiying = Chaojiying_Client('用户名', ' 密码', '用户中心的软件ID')  
im = open(imgName, 'rb').read()                           #  本地图片与当前py是同级，如不同级请写路径
# print(chaojiying.PostPic(im, 1902))                      #1902是验证码类型中的常见4-6位英文数字
result_code = chaojiying.PostPic(im, 4004)                       #result: {'err_str': 'OK', 'pic_id': '2090615382056500023', 'err_no': 0, 'md5': '47298d1d39c7b28c1c0269d87b8f7c33', 'pic_str': '1336'}
code = result_code['pic_str']          # 取出验证码的识别结果
print(code)
# driver.find_element_by_xpath('//*[@id="app"]/div/div[4]/div/form/div[4]/div[2]/div/div/input').send_keys(code)     #发送验证码
# driver.find_element_by_xpath('//*[@id="app"]/div/div[4]/div/form/div[5]/button/div/div').click()                    #点击提交按钮

driver.close()            #关闭浏览器
           

通过selenium截取的验证码图片

超级鹰

test_chaojiying.py

import requests
from hashlib import md5
class Chaojiying_Client(object):
    def __init__(self, username, password, soft_id):
        self.username = username
        password =  password.encode('utf8')
        self.password = md5(password).hexdigest()
        self.soft_id = soft_id
        self.base_params = {
            'user': self.username,
            'pass2': self.password,
             'softid': self.soft_id,
        }
        self.headers = {
            'Connection': 'Keep-Alive',
            'User-Agent': 'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0)',
        }
    def PostPic(self, im, codetype):
        #m: 图片字节
        #codetype: 题目类型 参考 http://www.chaojiying.com/price.html

       params = {
           'codetype': codetype,
       }
       params.update(self.base_params)
       files = {'userfile': ('ccc.jpg', im)}
       r = requests.post('http://upload.chaojiying.net/Upload/Processing.php', data=params, files=files, headers=self.headers)
       return r.json()

   def ReportError(self, im_id):

	   # im_id:报错题目的图片ID
       params = {
           'id': im_id,
       }
       params.update(self.base_params)
       r = requests.post('http://upload.chaojiying.net/Upload/ReportError.php', data=params, headers=self.headers)
       return r.json()
           

gif动图

超级鹰验证码类型及单价

更多爬虫知识 点击这里

另附上一篇 免费识别验证码

点击这里