爬虫笔记22:12306购票（input标签的type=‘‘hidden‘‘,而输入的值是以代号的形式确定、xpath过滤datatran属性的tr标签）

一、当输入框，也就是input标签的type=’‘hidden’’,而输入的值是以代号的形式确定的

<input id="fromStation" type="hidden" value="BJP" name="leftTicketDTO.from_station">

解决方法：
（1）type=’‘hidden’’，用driver.execute_script(‘arguments[0].value="%s"’%from_station_code,from_station_input)解决
（2）输入值由代号决定，提前准备好代号表（key-value），即stations.csv文件

import csv
from selenium import webdriver
import time
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC


driver = webdriver.Chrome(r'C:\Users\Administrator\Desktop\chromedriver_win32\chromedriver.exe')

# 面向对象来实现 
class TrainSpider(object):
    login_url = 'https://kyfw.12306.cn/otn/resources/login.html' # 登录的url
    personal_url = 'https://kyfw.12306.cn/otn/view/index.html' # 个人中心的url
    left_ticket_url = 'https://kyfw.12306.cn/otn/leftTicket/init?linktypeid=dc' # 车次以及余票查询

    def __init__(self,from_station,to_station,train_data):

        self.from_station = from_station
        self.to_station = to_station
        self.train_data = train_data
        self. station_codes = {}
        self.init_station_code()

    # 初始化站点
    def init_station_code(self):

        with open('stations.csv', 'r', encoding='utf-8') as file_obj:
            reader = csv.DictReader(file_obj)
            for line in reader:
                name = line['name']
                code = line['code']
                self.station_codes[name] = code

    # 登录
    def login(self):
        driver.get(self.login_url)
        
        WebDriverWait(driver, 1000).until(EC.url_contains(self.personal_url))

        print('登录成功！')

    #车次以及余票查询
    def search_left_ticket(self):
        # X掉弹框
        driver.get(self.left_ticket_url)
        driver.implicitly_wait(3)
        driver.find_element_by_id('gb_closeDefaultWarningWindowDialog_id').click()

        # 设置出发地 type="hidden" 1 先找到标签 2 在获取值 3 把值设置进去
        from_station_input = driver.find_element_by_id('fromStation')
        from_station_code = self.station_codes[self.from_station]
        driver.execute_script('arguments[0].value="%s"'%from_station_code,from_station_input)

        # 设置目的地
        to_station_input = driver.find_element_by_id('toStation')
        to_station_code = self.station_codes[self.to_station]
        driver.execute_script('arguments[0].value="%s"' % to_station_code, to_station_input)

        # 设置时间
        train_date_input = driver.find_element_by_id('train_date')
        driver.execute_script('arguments[0].value="%s"' % self.train_data, train_date_input)

        time.sleep(3)

        # 点击查询按钮(查票)
        search_btn = driver.find_element_by_id('query_ticket')
        # 按钮不能够被点击时
        driver.execute_script('arguments[0].click()', search_btn)
        

    # 封装了我们基本的功能
    def run(self):
        # 登录
        self.login()
        # 车次以及余票查询
        self.search_left_ticket()

def main():
    spider = TrainSpider('北京','长沙','2021-06-04')# 日期格式需要注意2021-05-19
    spider.run()

if __name__ == '__main__':
    main()

结果：（虽然出发地、目的地没有显示出来北京、长沙，但实际上它的值已设置好对应的代号值，查询车次结果也显示出来了）

二、车次信息的过滤
我们发现每一个有id的tr标签都对应一个车次；而datatran属性的tr标签没有对应的信息，所以我们就要把它从tr标签中过滤掉。

解决方法：
（1）定位到tr标签：driver.find_elements_by_xpath(’//tbody[@id=“queryLeftTable”]/tr’)
（2）过滤datatran属性的tr标签：[not(@datatran)]

也就是：

# 获取车次列表 过滤没有用的tr标签 datatran属性
 train_trs = driver.find_elements_by_xpath('//tbody[@id="queryLeftTable"]/tr[not(@datatran)]')

三、多个乘客要订票的逻辑实现
看下面的完整代码缕缕

import csv
from selenium import webdriver
import time
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import NoSuchElementException
from selenium.webdriver.support.ui import Select

driver = webdriver.Chrome(r'C:\Users\Administrator\Desktop\chromedriver_win32\chromedriver.exe')

# 面向对象来实现 
class TrainSpider(object):
    login_url = 'https://kyfw.12306.cn/otn/resources/login.html' # 登录的url
    personal_url = 'https://kyfw.12306.cn/otn/view/index.html' # 个人中心的url
    left_ticket_url = 'https://kyfw.12306.cn/otn/leftTicket/init?linktypeid=dc' # 车次以及余票查询
    confirm_passenger_url = 'https://kyfw.12306.cn/otn/confirmPassenger/initDc' # 乘客信息
    def __init__(self,from_station,to_station,train_data,trains,passengers):
        '''
        from_station: 出发地
        to_station: 目的地
        train_data: 出发日期
        trains: 车次以及席位 {"G69":['O','M']}
        passengers: 乘客 ['克拉拉','具虎东']
        '''
        self.from_station = from_station
        self.to_station = to_station
        self.train_data = train_data
        self.trains = trains
        self.passengers = passengers
        self.selected_number = None
        self. station_codes = {}
        self.init_station_code()

    # 初始化站点
    def init_station_code(self):

        with open('stations.csv', 'r', encoding='utf-8') as file_obj:
            reader = csv.DictReader(file_obj)
            for line in reader:
                name = line['name']
                code = line['code']
                self.station_codes[name] = code

    # 登录
    def login(self):
        driver.get(self.login_url)
        
        WebDriverWait(driver, 1000).until(EC.url_contains(self.personal_url))

        print('登录成功！')

    def search_left_ticket(self):
        # X掉弹框
        driver.get(self.left_ticket_url)
        driver.implicitly_wait(3)
        driver.find_element_by_id('gb_closeDefaultWarningWindowDialog_id').click()

        # 设置出发地 type="hidden" 1 先找到标签 2 在获取值 3 把值设置进去
        from_station_input = driver.find_element_by_id('fromStation')
        from_station_code = self.station_codes[self.from_station]
        driver.execute_script('arguments[0].value="%s"'%from_station_code,from_station_input)


        # 设置目的地
        to_station_input = driver.find_element_by_id('toStation')
        to_station_code = self.station_codes[self.to_station]
        driver.execute_script('arguments[0].value="%s"' % to_station_code, to_station_input)


        # 设置时间
        train_date_input = driver.find_element_by_id('train_date')
        driver.execute_script('arguments[0].value="%s"' % self.train_data, train_date_input)

        time.sleep(3)

        # 点击查询按钮(查票)
        search_btn = driver.find_element_by_id('query_ticket')
        # 按钮不能够被点击时
        driver.execute_script('arguments[0].click()', search_btn)

        # 解析车次信息
        WebDriverWait(driver, 1000).until(EC.presence_of_element_located((By.XPATH,'//tbody[@id="queryLeftTable"]/tr')))

        # 获取车次列表 过滤没有用的tr标签 datatran
        train_trs = driver.find_elements_by_xpath('//tbody[@id="queryLeftTable"]/tr[not(@datatran)]')

        is_searched = False
        for train_tr in train_trs:
            infos = train_tr.text.replace('\n',' ').split(' ')
            # print(infos)
            number = infos[0] # 车次
            # 判断
            if number in self.trains:   #key in dict:
                seat_types = self.trains[number] # ['O','M']，即：要订的席位
                for seat_type in seat_types:
                    if seat_type == 'O':
                        count = infos[9] # 二等座
                        if count == '有' or count.isdigit():
                            # 点击预定
                            is_searched = True
                            break
                    elif seat_type == 'M':
                        count = infos[8] # 一等座
                        if count == '有' or count.isdigit():
                            is_searched = True
                            break
                if is_searched:
                    time.sleep(2)
                    self.selected_number = number
                    order_btn = train_tr.find_element_by_xpath(".//a[@class='btn72']")
                    order_btn.click()
                    break   #如果没有break，就不会退出无限循序,将继续点击预定，报错。                        

    #确认乘客信息和席位
    def confirm_passengers(self):
        WebDriverWait(driver, 1000).until(EC.url_contains(self.confirm_passenger_url))

        # 确认需要购票的乘客
        passenger_labels = driver.find_elements_by_xpath("//ul[@id='normal_passenger_id']/li/label")
        for passenger_label in passenger_labels:
            name = passenger_label.text
            # print(name)
            if name in self.passengers:
                passenger_label.click()

        # 确认购买的席位
        seat_select = Select(driver.find_element_by_id('seatType_1'))
        seat_types = self.trains[self.selected_number]  # ['O','M']，即：要订的席位
        for seat_type in seat_types:
            try:
                seat_select.select_by_value(seat_type)
            except NoSuchElementException:
                continue
            else:   #如果try没有报错，执行了try之后再执行else
                break

        # 提交订单
        submit_btn = driver.find_element_by_id('submitOrder_id')
        submit_btn.click()

        # 等待核对信息窗口加载出来
        WebDriverWait(driver, 1000).until(EC.presence_of_element_located((By.CLASS_NAME, 'dhtmlx_window_active')))

        # 点击按钮
        s_btn = driver.find_element_by_id('qr_submit_id')
        s_btn.click()

    # 封装了我们基本的功能
    def run(self):
        # 登录
        self.login()
        # 车次以及余票查询
        self.search_left_ticket()
        # 确认乘客信息和席位
        self.confirm_passengers()

def main():
    spider = TrainSpider('北京','长沙','2021-06-04',{"G485":['O','M']},['赵晓龙'])# 日期格式需要注意2021-05-19
    spider.run()

if __name__ == '__main__':
    main()