(九)selenium实现12306模拟登录

登陆的唯一困难在于验证码的识别，此处使用第三方平台超级鹰进行验证码识别。

from selenium import webdriver
import time
from PIL import Image
from selenium.webdriver import ActionChains
import requests
from hashlib import md5

from selenium.webdriver import Chrome
from selenium.webdriver import ChromeOptions

class Chaojiying_Client(object):
    """超级鹰源代码"""

    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()

# 检测规避
option = ChromeOptions()
option.add_experimental_option('excludeSwitches', ['enable-automation'])
driver = Chrome(options=option)

bro = webdriver.Chrome(executable_path='./chromedriver.exe')
# 最大化屏幕
bro.maximize_window()

# 发送请求
bro.get('https://kyfw.12306.cn/otn/resources/login.html')

# 找到账号的登陆的标签
btn = bro.find_elements_by_xpath('/html/body/div[2]/div[2]/ul/li[2]/a')[0]
btn.click()
time.sleep(2)

# 将当前页面截屏生成图片
bro.save_screenshot('12306.png')

# 定位到要截取的图片
pic = bro.find_element_by_xpath('/html/body/div[2]/div[2]/div[1]/div[2]/div[3]/div/div[4]/img')
# 得到当前图片的左上角坐标
location = pic.location
# 得到图片的长和宽
size = pic.size
# 得到图片左上角和右下角的坐标 截图准确度与电脑缩放布局有关 当前为125%
rangle = (location['x'] * 1.25, location['y'] * 1.25, (location['x'] + size['width']) * 1.25,
          (location['y'] + size['height']) * 1.25)

# 保存生成的验证码图片
i = Image.open('./12306.png')
code_img_name = 'code.png'  # 裁剪文件的文件名称
frame = i.crop(rangle)  # 根据指定区域进行裁剪
frame.save(code_img_name)

# 利用超级鹰识别验证码
chaojiying = Chaojiying_Client('Mrterrific', 'WQ2017617sxy', '    905993')
im = open('./code.png', 'rb').read()
result = chaojiying.PostPic(im, 9004)['pic_str']
all_list = []

if '|' in result:
    # 多个结果
    print(result)
    ret_list = result.split('|')  # 148,102|236,203
    for ret in ret_list:
        # 将一组坐标放入列表
        x_y = []
        x = ret.split(',')[0]
        y = ret.split(',')[0]
        x_y.append(x)
        x_y.append(y)
        all_list.append(x_y)
else:
    x_y = []
    x = result.split(',')[0]
    y = result.split(',')[0]
    x_y.append(x)
    x_y.append(y)
    all_list.append(x_y)

for ret in all_list:
    x = int(ret[0])
    y = int(ret[1])
    ActionChains(bro).move_to_element_with_offset(pic, x, y).click().perform()
    # 以图片对象为参考系 将鼠标移动到相对图片x,y处 点击图片
    time.sleep(0.5)

bro.find_element_by_id('J-userName').send_keys('xxxx')
bro.find_element_by_id('J-password').send_keys('ssss')
bro.find_element_by_id('J-login').click()
time.sleep(3)
bro.quit()