爬虫 12306模拟登录（运用超级鹰 selenium)

调用了超级鹰（两个文件  ，从超级鹰导入文件）

#!/usr/bin/env python
# coding:utf-8

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):
        """
        im: 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()

注意电脑分辨率调为100%（这样图片位置才能正好 ）（或者里面的x,y 对应等比例缩放）

from PIL import Image
from selenium import webdriver
from chaojiying import Chaojiying_Client
from selenium.webdriver import ActionChains
from time import sleep
#返回验证码对应的数据
def getCode(imgPath,imgType):
    chaojiying = Chaojiying_Client('xlhchaojiying', 'xlhchaojiying', '900927')  # 用户中心>>软件ID 生成一个替换 96001
    im = open(imgPath, 'rb').read()  # 本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
    return chaojiying.PostPic(im,imgType)['pic_str']


bro = webdriver.Chrome(executable_path='chromedriver.exe')
url = 'https://kyfw.12306.cn/otn/login/init'
bro.get(url)
sleep(3)

#验证码进行截取且识别
bro.save_screenshot('main.png')

#确定截取的范围
img_ele= bro.find_element_by_xpath('//*[@id="loginForm"]/div/ul[2]/li[4]/div/div/div[3]/img')
#location表示的是验证码图片左上角的坐标
location = img_ele.location
print('location:',location)
#size返回的是图片的长和宽
size = img_ele.size
print('size:',size)
#rangle就是制定好的截取范围
rangle = (int(location['x']),int(location['y']),int(location['x']+size['width']),int(location['y']+size['height']))

#根据截取范围进行截图
i = Image.open('main.png')
#code_img_name截取下验证码图片的名称
code_img_name = 'code.png'
frame = i.crop(rangle)
frame.save(code_img_name)

#记录：code.png就是验证码图片  main.png就是当前登陆页面对应的图片
result = getCode('code.png',9004)
print(result)
#返回的单组坐标数据：242,84
#返回的多组坐标数据：242,84|12,54|44,66
#[[1,2],[3,4],[5,6]]
#[[1,2]]
all_list = []
if '|' in result:
    list_1 = result.split('|')
    count_1 = len(list_1)
    for i in range(count_1):
        xy_list = []
        x = int(list_1[i].split(',')[0])
        y = int(list_1[i].split(',')[1])
        xy_list.append(x)
        xy_list.append(y)
        all_list.append(xy_list)
else:
    x = int(result.split(',')[0])
    y = int(result.split(',')[1])
    xy_list = []
    xy_list.append(x)
    xy_list.append(y)
    all_list.append(xy_list)

print(all_list)

#基于selenium根据all_list进行定点的点击操作
for l in all_list:
    x = l[0]
    y = l[1]
    ActionChains(bro).move_to_element_with_offset(img_ele,x,y).click().perform()
    sleep(0.5)

bro.find_element_by_id('username').send_keys('yonghuming')
sleep(2)
bro.find_element_by_id('password').send_keys('changmima')
sleep(2)
bro.find_element_by_id('loginSub').click()
sleep(10)
bro.quit()