1.首先实现使用selenium登陆12306
关于使用selenium实现12306登陆可以看我的另一篇文章 这里实现了使用selenium登陆12306,这次是基于上次的代码进行修改实现全自动购买车票的 实现全自动登陆12306链接。
2.根据上面实现登陆后,实现购买火车票还需两步
这里只进行了二等座的查询和购票,想要买其他的自己也可以进行修改 1.进行车票的查询 这里面需要注意的是在输入目的地和起始地时需要先click一下文本框browser.find_element_by_id(‘fromStationText’).click() 不然输入的地址无效 还有将日期的只读属性去掉。
- def search_railway_ticket(fromstation,tostation,train_date):
- # 火车票页面查询url
- search_url = 'https://kyfw.12306.cn/otn/leftTicket/init?linktypeid=dc'
- # 转到查询车次页面
- browser.get(search_url)
- time.sleep(2)
- #输入出发地
- WebDriverWait(browser, 1000).until(
- EC.presence_of_element_located((By.ID, 'fromStationText'))
- )
- #先点击一下
- browser.find_element_by_id('fromStationText').click()
- browser.find_element_by_id('fromStationText').send_keys(fromstation)
- browser.find_element_by_id('fromStationText').send_keys(Keys.ENTER)
- time.sleep(1)
- WebDriverWait(browser, 1000).until(
- EC.presence_of_element_located((By.ID, 'toStationText'))
- )
- #输入目的地
- browser.find_element_by_id('toStationText').click()
- browser.find_element_by_id('toStationText').send_keys(tostation)
- browser.find_element_by_id('toStationText').send_keys(Keys.ENTER)
- time.sleep(5)
- #将日期的只读属性去掉
- js = 'document.getElementById("train_date").removeAttribute("readonly")'
- browser.execute_script(js)
- #去掉原本的时间
- WebDriverWait(browser, 1000).until(
- EC.presence_of_element_located((By.ID, 'train_date'))
- )
- browser.find_element_by_id("train_date").clear()
- #输入出发时间
- browser.find_element_by_id('train_date').send_keys(train_date)
- # 等待查询按钮是否可用
- WebDriverWait(browser, 1000).until(
- EC.element_to_be_clickable((By.ID, 'query_ticket'))
- )
- searBtn = browser.find_element_by_id('query_ticket')
- searBtn.click()
- print('点击按钮')
购买火车票 在这个函数中需要注意的是最好把最后一步注释掉 browser.find_element_by_id(‘qr_submit_id’).click() 因为一天只能取消3次订单。
- def buy_ticket(fromstation,tostation,train_date,train_number,passenger):
-
- #查询火车票
- search_railway_ticket(fromstation,tostation,train_date)
- time.sleep(5)
- #获取每一个车次的信息
- tr_list = browser.find_elements_by_xpath('.//tbody[@id="queryLeftTable"]/tr[not(@datatran)]')
- for tr in tr_list:
- #获取车次号
- number = tr.find_element_by_class_name('number').text
- if number in train_number:
- #获取是否还有票
- left_ticket = tr.find_element_by_xpath('./td[4]').text
- if left_ticket =='有'or left_ticket.isdigit:
- print(f'{number}还有票')
- #点击预订
- orderBtn = tr.find_element_by_class_name('btn72')
- orderBtn.click()
- time.sleep(5)
- #获取12306中乘客的信息
- passenger_list = browser.find_elements_by_xpath('//*[@id="normal_passenger_id"]/li')
- for li in passenger_list:
- name = li.find_element_by_xpath('./label').text
- print(name)
- #配对12306人名
- if name == passenger:
- li.find_element_by_tag_name('input').click()
- #提交订单
- submit = browser.find_element_by_id('submitOrder_id')
- submit.click()
- WebDriverWait(browser, 1000).until(
- EC.element_to_be_clickable((By.ID, 'qr_submit_id'))
- )
- #一天只能取消3次 所以最好把最后一步注释了
- browser.find_element_by_id('qr_submit_id').click()
- print('已经提交订单')
- break
下面是源代码
测试的时候可以把#click_captcha()这个点击验证码的去掉自己手动点击,这样就不用扣超级鹰的积分(有钱的话当我没说),留下了贫穷的泪水。
- from selenium import webdriver
- from selenium.webdriver import Actionchains
- import time
- from PIL import Image
- import requests
- from hashlib import md5
- from selenium.webdriver import ChromeOptions
- #验证码识别处理
- from selenium.webdriver.common.keys import Keys
- from selenium.webdriver.common.by import By
- from selenium.webdriver.support.wait import WebDriverWait
- from selenium.webdriver.support import expected_conditions as EC
-
- 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()
-
- def login(username,password):
- # 填写账号密码
- browser.find_element_by_id('J-userName').send_keys(username)
- browser.find_element_by_id('J-password').send_keys(password)
-
- # 获取验证码
- get_captcha()
-
- # 填写验证码
- click_captcha()
-
- #点击登录
- time.sleep(4)
- browser.find_element_by_id('J-login').click()
- time.sleep(4)
-
- #滑动验证码
- slider()
-
- print('成功登陆')
- time.sleep(5)
-
- def slider():
- #滑动验证码
- WebDriverWait(browser, 1000).until(
- EC.presence_of_element_located((By.XPATH, '//*[@id="nc_1_n1z"]'))
- )
- span = browser.find_element_by_xpath('//*[@id="nc_1_n1z"]')
- # 对div_tag进行滑动操作
- action = Actionchains(browser)
- # 点击长按指定的标签
- action.click_and_hold(span).perform()
- action.drag_and_drop_by_offset(span, 400, 0).perform()
-
- def click_captcha():
- # 获取验证码需要的为点击位置
- chaojiying = Chaojiying_Client('自己的用户名', '密码', '软件id') # 用户中心>>软件ID 生成一个替换 96001
- im = open('./captcha.png', 'rb').read() # 本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
- location = chaojiying.PostPic(im, 9004)['pic_str'] # 1902 验证码类型 官方网站>>价格体系 3.4+版 print 后要加()
- print(chaojiying.PostPic(im, 9004))
- # 将位置进行分割成 [ [ ], [ ], [ ] ]类型
- location_list = [i.split(',') for i in location.split('|')]
- for l in location_list:
- x = l[0]
- y = l[1]
- Actionchains(browser).move_to_element_with_offset(browser.find_element_by_class_name('login-pwd-code'), int(x),int(y)).click().perform()
- time.sleep(0.5)
-
- def get_captcha():
- # 获取网页的截图
- allscreen = browser.get_screenshot_as_file('allscreen.png')
- # 获取captcha
- captcha = browser.find_element_by_class_name('login-pwd-code')
- # 获取captcha的左上角位置
- location = captcha.location
- # 获取图片大小
- size = captcha.size
- # 裁取captcha
- rangle = (location['x'],location['y'],(location['x']+size['width']),(location['y']+size['height']))
- i = Image.open('./allscreen.png')
- captcha_img = './captcha.png'
- frame = i.crop(rangle)
- frame.save(captcha_img)
-
- def buy_ticket(fromstation,tostation,train_date,train_number,passenger):
-
- #查询火车票
- search_railway_ticket(fromstation,tostation,train_date)
- time.sleep(5)
- tr_list = browser.find_elements_by_xpath('.//tbody[@id="queryLeftTable"]/tr[not(@datatran)]')
- for tr in tr_list:
- number = tr.find_element_by_class_name('number').text
- if number in train_number:
- left_ticket = tr.find_element_by_xpath('./td[4]').text
- if left_ticket =='有'or left_ticket.isdigit:
- print(f'{number}还有票')
- orderBtn = tr.find_element_by_class_name('btn72')
- orderBtn.click()
- time.sleep(5)
- passenger_list = browser.find_elements_by_xpath('//*[@id="normal_passenger_id"]/li')
- for li in passenger_list:
- name = li.find_element_by_xpath('./label').text
- if name == passenger:
- li.find_element_by_tag_name('input').click()
- submit = browser.find_element_by_id('submitOrder_id')
- submit.click()
- WebDriverWait(browser, 1000).until(
- EC.element_to_be_clickable((By.ID, 'qr_submit_id'))
- )
- #一天只能取消3次 所以把最后一步注释了
- # browser.find_element_by_id('qr_submit_id').click()
- print('已经提交订单')
- break
-
- def search_railway_ticket(fromstation,tostation,train_date):
- # 火车票页面查询url
- search_url = 'https://kyfw.12306.cn/otn/leftTicket/init?linktypeid=dc'
- # 转到查询车次页面
- browser.get(search_url)
- time.sleep(2)
- #输入出发地
- WebDriverWait(browser, 1000).until(
- EC.presence_of_element_located((By.ID, 'fromStationText'))
- )
- #先点击一下
- browser.find_element_by_id('fromStationText').click()
- browser.find_element_by_id('fromStationText').send_keys(fromstation)
- browser.find_element_by_id('fromStationText').send_keys(Keys.ENTER)
- time.sleep(1)
- WebDriverWait(browser, 1000).until(
- EC.presence_of_element_located((By.ID, 'toStationText'))
- )
- #输入目的地
- browser.find_element_by_id('toStationText').click()
- browser.find_element_by_id('toStationText').send_keys(tostation)
- browser.find_element_by_id('toStationText').send_keys(Keys.ENTER)
- time.sleep(5)
- #将日期的只读属性去掉
- js = 'document.getElementById("train_date").removeAttribute("readonly")'
- browser.execute_script(js)
- #去掉原本的时间
- WebDriverWait(browser, 1000).until(
- EC.presence_of_element_located((By.ID, 'train_date'))
- )
- browser.find_element_by_id("train_date").clear()
- #输入出发时间
- browser.find_element_by_id('train_date').send_keys(train_date)
- # 等待查询按钮是否可用
- WebDriverWait(browser, 1000).until(
- EC.element_to_be_clickable((By.ID, 'query_ticket'))
- )
- searBtn = browser.find_element_by_id('query_ticket')
- searBtn.click()
- print('点击按钮')
-
- if __name__ == '__main__':
- option = ChromeOptions() # 实例化一个ChromeOptions对象
- option.add_experimental_option('excludeSwitches', ['enable-automation']) # 以键值对的形式加入参数
- option.add_experimental_option('useAutomationExtension', False)
-
- browser = webdriver.Chrome(options=option)
- # 获取响应
- browser.get('https://kyfw.12306.cn/otn/resources/login.html')
- script = 'Object.defineProperty(navigator,"webdriver",{get:()=>undefined,});'
- browser.execute_script(script)
- browser.maximize_window()
- time.sleep(1)
-
- # 点击账号登陆
- browser.find_element_by_class_name('login-hd-account').click()
- #登陆12306的账号密码
- login('用户名','密码')
- time.sleep(4)
- #例buy_ticket('南昌','抚州北','2020-12-15','D2241','xx')
- buy_ticket('起始地','目的地','出发日期','车次','姓名')
【编辑推荐】