Python + selenium + requests实现12306全自动抢票及验证码破解加自动点击功能

测试结果： 

整个买票流程可以再快一点，不过为了稳定起见，有些地方等待了一些时间

完整程序，拿去可用

整个程序分了三个模块：购票模块（主体）、验证码识别模块、余票查询模块

购票模块：

from selenium import webdriver
from selenium.webdriver.common.by import By 
from selenium.webdriver.support import expected_conditions as EC 
from selenium.common.exceptions import NoSuchElementException, StaleElementReferenceException, ElementNotVisibleException
import time
import requests
from urllib.parse import urlencode
from pyquery import PyQuery as pq
from check_ticket import Check
from verify import Code
import json
class Buy_Ticket():
  def __init__(self, start_station, end_station, date, username, password, purpose):
    self.num = 1
    self.start = start_station
    self.end = end_station
    self.date = date
    self.username = username
    self.password = password
    self.purpose = purpose
    self.login_url = 'https://kyfw.12306.cn/otn/login/init'
    self.ticket_url = 'https://kyfw.12306.cn/otn/leftTicket/init'
  def login(self):
    browser.get(self.login_url)
    try:
      input_name = browser.find_element_by_id('username')
      input_pd = browser.find_element_by_id('password')
      button = browser.find_element_by_id('loginSub')
      time.sleep(1)
      input_name.send_keys(self.username)
      input_pd.send_keys(self.password)
      c = Code(browser)    #调用验证码识别模块
      c.main()
      button.click()
      time.sleep(2)
      #等待页面跳转，如果验证码识别错误，就执行下面的while语句
      while browser.current_url == self.login_url + '#':
        c = Code(browser)
        c.main()
        button.click()
        time.sleep(2)
      #self.get_passenger()
      self.check()
    except NoSuchElementException:
      self.login()
  def check(self):
    #调用余票查询模块
    check = Check(self.date, self.start, self.end, self.purpose)
    start_end = check.look_up_station()
    self.num = check.get_info()
    #cookie的添加，json.dumps把以汉字形式呈现的起始、终点站转化成unicode编码，可在审查元素里查看cookie
    browser.add_cookie({'name':'_jc_save_fromStation', 'value':json.dumps(self.start).strip('"').replace('\\', '%') + '%2C' + start_end[0]})
    browser.add_cookie({'name':'_jc_save_toStation', 'value':json.dumps(self.end).strip('"').replace('\\', '%') + '%2C' + start_end[1]})
    browser.add_cookie({'name':'_jc_save_fromDate', 'value':self.date})
    browser.get(self.ticket_url)
    if self.purpose == '学生':
      btn = browser.find_element_by_id('sf2')
      time.sleep(1)
      btn.click()
    button = browser.find_element_by_id('query_ticket')
    time.sleep(1)
    button.click()
  def book_ticket(self):
    print('开始预订车票...')
    #先查找出所有车次对应的预订按钮，再根据余票查询模块返回的车次序号，点击相应的预订按钮
    button = browser.find_elements_by_class_name('btn72')
    button[self.num-1].click()
    time.sleep(3)
    button2 = browser.find_element_by_id('normalPassenger_0') #按实际情况，可自行修改，这里就选择的第一个常用联系人，
                                  #第二个是normalPassenger_1，依此类推
    button2.click()
    button3 = browser.find_element_by_id('submitOrder_id')
    time.sleep(1)
    button3.click()
    time.sleep(3) #等待页面加载完毕，不然后面可能会报错,等待时间自行决定
    try:
      button4 = browser.find_element_by_id('qr_submit_id')
      button4.click()
    except ElementNotVisibleException:
      button4 = browser.find_element_by_id('qr_submit_id')
      button4.click()
    print('车票预定成功！请在30分钟内完成付款！')
  def main(self):
    self.login()
    self.book_ticket()
if __name__ == '__main__':
  begin = time.time()
  browser = webdriver.Chrome()
  b = Buy_Ticket('上海', '重庆', '2018-09-18', '账号', '密码', 'ADULT') #账号、密码自行修改
  b.main()
  end = time.time()
  print('总耗时：%d秒' % int(end-begin))
  #browser.close()

验证码识别模块：

import requests
from PIL import Image
from selenium.webdriver import ActionChains
import time
from io import BytesIO
class Code():
  def __init__(self, browser):
    self.browser = browser
    self.verify_url = 'http://littlebigluo.qicp.net:47720/'   #验证码识别网址，返回识别结果
    #确定验证码的位置
  def get_position(self):
    time.sleep(3)
    element = self.browser.find_element_by_class_name('touclick-img-par')
    time.sleep(2)
    location = element.location
    size = element.size
    position= (location['x'], location['y'], location['x'] + size['width'], location['y'] + size['height'])
    return position
    #截取整个网页页面
  def get_screenshot(self):
    screenshot = self.browser.get_screenshot_as_png()
    screenshot = Image.open(BytesIO(screenshot))
    return screenshot
    #从截取的网页，裁剪出验证码图片，并保存到本地
  def get_touclick_img(self, name = 'captcha.png'):
    position = self.get_position()
    print('验证码的位置:', position)
    screenshot = self.get_screenshot()
    captcha = screenshot.crop(position)
    captcha.save('captcha.png')
    #验证码解析
  def parse_img(self):
    files = {'file': open('captcha.png', 'rb')}       #打开保存到本地的验证码图片
    response = requests.post(self.verify_url, files=files)
    num = response.text.split('<B>')[1].split('<')[0]
    print('验证码识别成功！图片位置：%s' % num)
    try:
      if int(num):
        return [int(num)]
    except ValueError:
      num = list(map(int,num.split()))
      return num
    #识别结果num都以列表形式返回，方便后续验证码的点击
    #实现验证码自动点击
  def move(self):
    num = self.parse_img()
    try:
      element = self.browser.find_element_by_class_name('touclick-img-par')
      for i in num:
        if i <= 4:
          ActionChains(self.browser).move_to_element_with_offset(element,40+72*(i-1),73).click().perform()
        else :
          i -= 4
          ActionChains(self.browser).move_to_element_with_offset(element,40+72*(i-1),145).click().perform()
    except:
      print('元素不可选！')
  def main(self):
    self.get_touclick_img()
    self.move()

余票查询模块：

import requests
from urllib.parse import urlencode
class Check():
  def __init__(self, date, start, end, purpose):
    self.base_url = 'https://kyfw.12306.cn/otn/leftTicket/queryA?'
    self.url = 'https://kyfw.12306.cn/otn/resources/js/framework/station_name.js?station_version=1.9018'
    self.date = date
    self.start_station = start
    self.end_station = end
    if purpose == '学生':
      self.purpose = '0X00'
    else:
      self.purpose = purpose
    #查找出车站的英文简称，用于构造cookie、完整的余票查询链接
  def look_up_station(self):
    response1 = requests.get(self.url)
    a = response1.text.split('@')
    a.pop(0)
    for each in a:
      i = each.split('|')
      if self.start_station == i[1]:
        self.start_station = i[2]
      elif self.end_station == i[1]:
        self.end_station = i[2]
    return [self.start_station, self.end_station]
  def get_info(self):
    start_end = self.look_up_station()
    #构造请求参数
    data = {
    'leftTicketDTO.train_date':self.date,
    'leftTicketDTO.from_station':start_end[0],
    'leftTicketDTO.to_station':start_end[1],
    'purpose_codes':self.purpose
    }
    url = self.base_url + urlencode(data)
    response = requests.get(url)
    json = response.json()
    maps = json['data']['map']
    count = 0    #用于对车次编号       
    for each in json['data']['result']:
      count += 1
      s = each.split('|')[3:]
      info = {
      'train':s[0],
      'start_end':maps[s[3]] + '-' + maps[s[4]],
      'time':s[5] + '-' + s[6],
      '历时':s[7],
      '一等座':s[-5],
      '二等座':s[-6]
      }
      try:
        #余票的结果有3种：有、一个具体的数字(如：18、6等)、无，判断如果余票是有或者一个具体的数字就直接输出对应的车次信息，然后返回
        if info['二等座'] == '有' or int(info['二等座']):   
          print('[%d]' % count, info)
          return count
      except ValueError:
        continue

总结