python12306下单步骤_python编程实现12306的一个小爬虫实例

下单步骤：

1. 登录账号，获取cookie和验证码

2. 输入出发地、目的地、乘车日期等信息，获取车次信息

3. 选择需要购买的车次和座位类型，获取乘客信息

4. 提交订单，获取订单信息

5. 确认订单，完成购票流程

以下是一个简单的Python爬虫实现12306购票的例子：

import requests
import json
from time import sleep

# 登录url
login_url = 'https://kyfw.12306.cn/passport/web/login'

# 用户名和密码
username = 'your_username'
password = 'your_password'

# 出发地、目的地、日期等信息
from_station = '北京'
to_station = '上海'
train_date = '2019-07-01'

# 车次类型和座位类型
train_type = 'G'
seat_type = '二等座'

# 乘客姓名和身份证号码
passenger_name = '张三'
passenger_id = '123456789012345678'

# 提交订单url
submit_order_url = 'https://kyfw.12306.cn/otn/leftTicket/submitOrderRequest'

# 检查订单url
check_order_url = 'https://kyfw.12306.cn/otn/confirmPassenger/checkOrderInfo'

# 确认订单url
confirm_order_url = 'https://kyfw.12306.cn/otn/confirmPassenger/confirmSingleForQueue'

# 获取验证码url
captcha_url = 'https://kyfw.12306.cn/passport/captcha/captcha-image64'

# 登录请求头
login_headers = {
    'Accept': 'application/json, text/javascript, */*; q=0.01',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Connection': 'keep-alive',
    'Content-Length': '44',
    'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
    'Host': 'kyfw.12306.cn',
    'Origin': 'https://kyfw.12306.cn',
    'Referer': 'https://kyfw.12306.cn/otn/resources/login.html',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.157 Safari/537.36',
    'X-Requested-With': 'XMLHttpRequest'
}

# 下单请求头
order_headers = {
    'Accept': 'application/json, text/javascript, */*; q=0.01',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Connection': 'keep-alive',
    'Content-Length': '220',
    'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
    'Host': 'kyfw.12306.cn',
    'Origin': 'https://kyfw.12306.cn',
    'Referer': 'https://kyfw.12306.cn/otn/leftTicket/init',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.157 Safari/537.36',
    'X-Requested-With': 'XMLHttpRequest'
}

# 获取验证码请求头
captcha_headers = {
    'Accept': 'image/webp,image/apng,image/*,*/*;q=0.8',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Connection': 'keep-alive',
    'Host': 'kyfw.12306.cn',
    'Referer': 'https://kyfw.12306.cn/otn/resources/login.html',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.157 Safari/537.36'
}

# 登录请求参数
login_data = {
    'username': username,
    'password': password,
    'appid': 'otn'
}

# 下单请求参数
order_data = {
    'secretStr': '',
    'train_date': train_date,
    'back_train_date': train_date,
    'tour_flag': 'dc',
    'purpose_codes': 'ADULT',
    'query_from_station_name': from_station,
    'query_to_station_name': to_station,
    'undefined': ''
}

def login():
    # 获取验证码
    captcha_response = session.get(captcha_url, headers=captcha_headers)
    captcha_json = json.loads(captcha_response.text)
    captcha_image_base64 = captcha_json['image']
    with open('captcha.jpg', 'wb') as f:
        f.write(base64.b64decode(captcha_image_base64))
    captcha_code = input('请输入验证码: ')

    # 登录
    login_data['answer'] = captcha_code
    response = session.post(login_url, data=login_data, headers=login_headers)
    result = json.loads(response.text)
    if result['result_code'] == 0:
        print('登录成功')
        return True
    else:
        print('登录失败')
        return False

def submit_order():
    # 提交订单
    order_data['secretStr'] = secretStr
    response = session.post(submit_order_url, data=order_data, headers=order_headers)
    result = json.loads(response.text)
    if result['status'] == True:
        print('提交订单成功')
        return True
    else:
        print('提交订单失败')
        return False

def check_order():
    # 检查订单
    passengerTicketStr = 'O,0,1,' + passenger_name + ',1,' + passenger_id + ',,N,' + seat_type + ',,'
    oldPassengerStr = passenger_name + ',1,' + passenger_id + ',1_'
    order_data['passengerTicketStr'] = passengerTicketStr
    order_data['oldPassengerStr'] = oldPassengerStr
    order_data['REPEAT_SUBMIT_TOKEN'] = repeat_submit_token
    response = session.post(check_order_url, data=order_data, headers=order_headers)
    result = json.loads(response.text)
    if result['data']['submitStatus'] == True:
        print('检查订单成功')
        return True
    else:
        print('检查订单失败')
        return False

def confirm_order():
    # 确认订单
    order_data['passengerTicketStr'] = passengerTicketStr
    order_data['oldPassengerStr'] = oldPassengerStr
    order_data['REPEAT_SUBMIT_TOKEN'] = repeat_submit_token
    order_data['key_check_isChange'] = key_check_isChange
    order_data['leftTicketStr'] = leftTicketStr
    response = session.post(confirm_order_url, data=order_data, headers=order_headers)
    result = json.loads(response.text)
    if result['data']['submitStatus'] == True:
        print('确认订单成功')
        return True
    else:
        print('确认订单失败')
        return False

if __name__ == '__main__':
    session = requests.session()

    # 登录
    while not login():
        pass

    # 查询车票
    query_url = 'https://kyfw.12306.cn/otn/leftTicket/queryZ'
    params = {
        'leftTicketDTO.train_date': train_date,
        'leftTicketDTO.from_station': from_station,
        'leftTicketDTO.to_station': to_station,
        'purpose_codes': 'ADULT'
    }
    response = session.get(query_url, params=params)
    result = json.loads(response.text)
    for data in result['data']:
        if data['queryLeftNewDTO']['station_train_code'].startswith(train_type):
            print(data['queryLeftNewDTO']['station_train_code'], data['queryLeftNewDTO'][seat_type + '_num'])
            if data['queryLeftNewDTO'][seat_type + '_num'] != '无' and data['queryLeftNewDTO'][seat_type + '_num'] != '--':
                secretStr = data['secretStr']
                leftTicketStr = data['queryLeftNewDTO']['ypInfoDetail']
                start_train_date = data['queryLeftNewDTO']['start_train_date']
                train_no = data['queryLeftNewDTO']['train_no']
                train_location = data['queryLeftNewDTO']['location_code']
                break

    # 获取乘客信息
    passenger_url = 'https://kyfw.12306.cn/otn/confirmPassenger/getPassengerDTOs'
    data = {
        '_json_att': '',
        'REPEAT_SUBMIT_TOKEN': ''
    }
    response = session.post(passenger_url, data=data, headers=order_headers)
    result = json.loads(response.text)
    for passenger in result['data']['normal_passengers']:
        if passenger['passenger_name'] == passenger_name and passenger['passenger_id_no'] == passenger_id:
            passengerTicketStr = 'O,0,1,' + passenger_name + ',1,' + passenger_id + ',,N,' + seat_type + ',,'
            oldPassengerStr = passenger_name + ',1,' + passenger_id + ',1_'

    # 获取REPEAT_SUBMIT_TOKEN和key_check_isChange
    init_dc_url = 'https://kyfw.12306.cn/otn/confirmPassenger/initDc'
    data = {
        '_json_att': ''
    }
    response = session.post(init_dc_url, data=data, headers=order_headers)
    repeat_submit_token = re.findall(r"var globalRepeatSubmitToken = '(.*?)';", response.text)[0]
    key_check_isChange = re.findall(r"key_check_isChange':'(.*?)',", response.text)[0]

    # 下单
    if submit_order():
        # 延时5秒
        sleep(5)

        # 检查订单
        if check_order():
            # 确认订单
            if confirm_order():
                print('购票成功')

需要注意的是，12306的接口随时可能会变化，代码中的某些参数可能需要修改才能正常运行。此外，代码中的验证码是手动输入的，如果需要自动识别验证码，可以使用一些第三方验证码识别库。