用python爬虫，对12306网站进行模拟登陆

from selenium import webdriver

from time import sleep

from PIL import Image

from selenium.webdriver import ActionChains

from Cjy import Chaojiying_Client

bro = webdriver.Chrome(executable_path='chromedriver.exe')

bro.get('https://kyfw.12306.cn/otn/login/init')

sleep(5)

截屏

bro.save_screenshot('main.png')

验证码所对应的标签

code_img_tag = bro.find_element_by_xpath('//*[@id="loginForm"]/div/ul[2]/li[4]/div/div/div[3]/img')

获取标签的起始坐标

location = code_img_tag.location

获取起始坐标的长和宽

size = code_img_tag.size

裁剪的区域范围

ragle = (int(location['x']),int(location['y']),int(location['x']+size['width']),int(location['y']+size['height']))

读取图片

i = Image.open('./main.png')

根据指定的大小进行裁剪

frame = i.crop(range)

将裁剪的图片进行保存

frame.save('code.png')

使用超级鹰进行识别

def get_text(imgPath,imgType):

chaojiying = Chaojiying_Client('123456','123456.','901485')

im = open('imgPath','rb').read()

return chaojiying.PostPic(im,imgType)['pic_str']

获取超级鹰返回的数据

result = get_text('./code.png',9004)

对超级鹰的数据进行处理

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)

在图片中找到相应的点，进行点击

for a in all_list:

x = a[0]

y = a[1]

#在这里找的坐标不是整张页面，而是验证码的图片

ActionChains(bro).move_to_element_with_offset(code_img_tag,x,y).click().perform()

sleep(1)

找到用户名对应的标签进行输入

bro.find_element_by_id('username').send_keys('123456')

sleep(1)

找到密码对应的标签进行输入

bro.find_element_by_id('password').send_keys('123456')

sleep(1)

找的登陆按钮，点击

bro.find_element_by_id('loginSub').click()

sleep(5)

bro.quit()