对12306车票数据的提取

前言

之前写了12306的爬虫，当时可以运行，最近发现不行，返回的数据不对，可能是cookie有问题（可能需要某些参数，我也不确定，但没有cookie，数据请求不到。。。），修改之后，成功。

对于返回的数据进行了提取，并再次发送请求，得到车票的其他数据。

1，获得火车的经过的站及相关数据。

2，获得火车的票价。

本来觉得应该写窗体的，自己实力不行，有待学习，以后再来完成。

开始

得到数据

发送请求

该写的都写上，cookie，headers之类的。直接给出代码

# a传入时间（2023--01-10）
# b,出发地的代号
# c 目的地代号,
url = f'https://kyfw.12306.cn/otn/leftTicket/queryZ?leftTicketDTO.train_date={a}&leftTicketDTO.from_station={b}&leftTicketDTO.to_station={c}&purpose_codes=ADULT'self.headers = {'Cookie': f'_jc_save_toStation={b}','User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36 Edg/108.0.1462.76',}r = requests.get(url=url, headers=self.headers)results = r.json()['data']['result']
#  result 就是数据
#  下面进行分析

解释

参数

需要提供的参数有

1，出发时间

2，出发地代号

3，目的地代号

参数的获取

    """
城市代码
url=https://kyfw.12306.cn/otn/resources/js/framework/station_name.js?station_version=1.9002
怎么获得
1，打开开发者工具（中文）
2，源代码
3，在js中"""

获取到我保存到csv文件中，也可以放到数据库中。

用pandas提取csv中的数据，即参数

返回的数据

返回的数据是以"|"进行分割的，如下

data="vdeVLhSURm4Q1RP66du87ohMRCQ3MLwq0kfa3TJCnHalBU63NmdSl3%2Bj0rKw2GIMFpDmXzicLXbe%0Arj7VwfiSslzB2E330A4AhBXW%2FSiLQW29lNCn2ZoamKWMVLFSt9f7vxwjtgMqvoqMpleoviO0aZOG%0AX75YLCGxZv%2Bj8obzGYdP%2FjDdI1CxxnTonzzXG7GI0pM0YEwsrGSYPgTnlXRAjzA6WrqZn%2BVHxaQF%0AgL0vdZ2sxItfSR2yGSAYacvObVlZXkCJoHAJjrCXT25HnBhsUCrO%2FRQ%2F97qKbBcN5F3JnPxWZZzw%0AfwVu%2F0DAqHBn69up|预订|76000G219505|G2195|ICW|AOH|ICW|CWQ|06:10|13:22|07:12|Y|dHywp8bnO4BIQNw1cH%2FaVsWHeAoP7nmv6%2FF4lR7Tvkkl2UtE|20230114|3|W2|01|14|1|0|||||||||||有|5|2||90M0O0|9MO|1|0||9178550002M095200005O057850021|0|||||1|0#0#0#0#z||"

用split进行分开，得到一个列表，里面有49个元素

data.split('|')

配合enumerate 函数找到有用的数据，经过多次分析，其中有20条数据是有用的

给出数据和对应的含义

"""
#t就是datatrain_no = t[2]   #火车参数che = t[3]  # 车次startcode = t[4] #出发地代号endcode = t[5]  # 目的地代号from_station_no = t[16] # 发车地代号to_station_no = t[17]  # 终点代号seat_types = t[35] # 座位类型starttime = t[8]  # 出发时间endtime = t[9] # 到站时间duration_time = t[10] 持续时间special_shop_seat = t[32] or t[25] or '--' # 商务座/特等座，二者数据所处位置不一样first_seat = t[31] or '--' # 一等座second_seat = t[30] or '--' # 二等座high_sleep = t[21] or '--' # 高级软卧soft_sleep = t[23] or '--' # 软卧dong_sleep = t[33] or '--' # 动卧hard_sleep = t[28] or '--' # 硬卧sort_seat = t[24] or '--' # 软座hart_seat = t[29] or '--' # 硬座no_seat = t[26] or '--' # 站票
"""

把数据用prettable进行展示中，并且把这些数据存到一个新的列表中，为后来的操作提供需要的参数。

# import prettable as pt
# tb=pt.PrettyTable()
# 列名如下，和注释可能不一样，不重要，数据一样的。
# 新增加了序号，好选择火车
tb.field_names = ['序号', '火车参数', '车次', '出发地代号', '终点代号', '出发地代码', '终点代码', '座位信息', '开始时', '结束时', '持续时间', '商务座/特等座','一等座', '二等座', '高级软卧', '软卧', '动卧', '软座', '硬卧', '软座' '硬座', '站票']
# 如图

数据太多，没对齐。。。

获取路途的站及相关数据

发送请求

# a 火车参数
# b 起点站的代号
# c 终点站代号
# d 时间url_1 = f'https://kyfw.12306.cn/otn/czxx/queryByTrainNo?train_no={a}&from_station_telecode={b}&to_station_telecode={c}&depart_date={d}'
resp = requests.get(url=url_1, headers=self.headers)
data = resp.json()['data']['data']

返回了数据，进行提取，用prettable来表示

tb.field_names = (['到站时间', '站点', '站数', '停留时间', '出站时间'])

没有多说的。唯一要说的就是代号，是火车发车的起点代号。

展示一下

获得票价

发送请求

#  a 火车参数
#  b 出发地代号
#  c 目的地代号
#  d  座位的类型
#  e 时间
#  注意代号的不同
url = f'https://kyfw.12306.cn/otn/leftTicket/queryTicketPrice?train_no={a}&from_station_no={b}&to_station_no={c}&seat_types={d}&train_date={e}'r = requests.get(url=url, headers=self.headers)

数据的分析

因为座位的不同，票价不一样，而导致座位类型不同，返回的数据也不同。

而座位的类型，d

        if d == '1341':tb.field_names = (['软卧价格', '硬卧价格', '硬座价格', '无座价格'])soft_sleep_price = r.json()['data']['A4']hard_sleep_price = r.json()['data']['A3']hart_seat_price = r.json()['data']['A1']no_seat_price = r.json()['data']['WZ']tb.add_row([soft_sleep_price, hard_sleep_price, hart_seat_price, no_seat_price])return tbif d == '1346':tb.field_names = (['高级软卧软卧价格', '硬卧价格', '硬座价格', '无座价格'])high_soft_sleep_price = r.json()['data']['A6']soft_sleep_price = r.json()['data']['A4']hard_sleep_price = r.json()['data']['A3']hard_seat_price = r.json()['data']['A1']tb.add_row([high_soft_sleep_price, soft_sleep_price, hard_sleep_price, hard_seat_price])return tbif d == '134':tb.field_names = (['软卧价格', '硬卧价格', '硬座价格'])soft_sleep_price = r.json()['data']['A4']hard_sleep_price = r.json()['data']['A3']hart_seat_price = r.json()['data']['A1']tb.add_row([soft_sleep_price, hard_sleep_price, hart_seat_price])return tbif d == '9MO' or 'OM9':tb.field_names = (['商务座价格', '一等座', '二等座'])special_price = r.json()['data']['A9']first_seat_price = r.json()['data']['M']second_seat = r.json()['data']['O']tb.add_row([special_price, first_seat_price, second_seat])return tbif d == 'MOO':tb.field_names = (['一等座', '二等座'])first_seat_price = r.json()['data']['M']second_seat = r.json()['data']['O']tb.add_row([first_seat_price, second_seat])return tbif d=='FOO':tb.field_names = (['动卧', '二等座','无座'])dong_sleep = r.json()['data']['F']second_seat = r.json()['data']['O']no_seat = r.json()['data']['O']tb.add_row([dong_sleep, second_seat,no_seat])return tbif d=='FO':tb.field_names = (['动卧', '二等座'])dong_sleep = r.json()['data']['F']second_seat = r.json()['data']['O']tb.add_row([dong_sleep, second_seat])return tbif d=='F':tb.field_names = (['动卧'])dong_sleep = r.json()['data']['F']tb.add_row([dong_sleep])return tbif d=='MOP':tb.field_names = (['特等座', '二等座','一等座'])special_seat = r.json()['data']['P']second_seat = r.json()['data']['O']first_seat = r.json()['data']['M']tb.add_row([special_seat, second_seat,first_seat])return tbif d=='IJO':tb.field_names = (['二等座', '软卧','硬卧'])soft_sleep = r.json()['data']['AI']second_seat = r.json()['data']['O']hard_sleep = r.json()['data']['AJ']tb.add_row([second_seat, soft_sleep,hard_sleep])return tb

d有很多种，应实际情况会发生不同的变化，我感觉没有遇到完，还有其他情况。。。

而且这样写，重复的代码实在太多，有待修改，有些情况应该还没遇到，还有其他座位类型。

展示一下，有待修改。

操作一下

视频

不知道怎么把视频传到csdn上，传到b站上了，顺便开始当up主，哈哈哈哈哈哈

视频

总结

有待修改，还要结合pyqt5，不然终究感觉少了什么

源码

import requests
import prettytable as pt
import pandas as pd
import datetimetb = pt.PrettyTable()def today(a: int):today = datetime.date.today()data = today + datetime.timedelta(days=a)return dataclass ottzs:def __init__(self):self.headers = Noneself.times = Nonedef get_time(self):a = {}for i in range(15):a[i] = today(i)a[15] = '-1'return adef choose_time(self):t = self.get_time()choose = int(input(f'需要输入需要查询的车票的时间,序号如下.\n请选择序号\n'f'序号----时间\n'f'0----{today(0)}\n'f'1----{today(1)}\n'f'2----{today(2)}\n'f'3----{today(3)}\n'f'4----{today(4)}\n'f'5----{today(5)}\n'f'6----{today(6)}\n'f'7----{today(7)}\n'f'8----{today(8)}\n'f'9----{today(9)}\n'f'10----{today(10)}\n'f'11----{today(11)}\n'f'12----{today(12)}\n'f'13----{today(13)}\n'f'14----{today(14)}\n'f'15-----退出\n''请输入序号:\n'))times = t[choose]return timesdef get_code(self, a):s = pd.read_csv(path, index_col='地点')result = s.loc[f'{a}']['代码']return result"""城市代码的url=https://kyfw.12306.cn/otn/resources/js/framework/station_name.js?station_version=1.9002"""def get_data(self, a, b, c):try:tb.field_names = ['序号 ', '火车参数     ', '车次   ', '出发地代号   ', '终点代号  ', '出发地代码  ', '终点代码  ', '座位信息 ', '开始时   ', '结束时  ', '  持续时间  ', '商务座/特等座   ','一等座   ', '二等座 ', '高级软卧   ', '软卧   ', '动卧  ', '软座   ', '硬卧   ', '软座 ' '硬座  ', '站票   ']url = f'https://kyfw.12306.cn/otn/leftTicket/queryZ?leftTicketDTO.train_date={a}&leftTicketDTO.from_station={b}&leftTicketDTO.to_station={c}&purpose_codes=ADULT'self.headers = {'Cookie': f'_jc_save_toStation={b}','User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36 Edg/108.0.1462.76',}r = requests.get(url=url, headers=self.headers)results = r.json()['data']['result']acc = []num = 0for i in results:t = i.split('|')train_no = t[2]che = t[3]startcode = t[4]endcode = t[5]from_station_no = t[16]to_station_no = t[17]seat_types = t[35]starttime = t[8]endtime = t[9]duration_time = t[10]special_shop_seat = t[32] or t[25] or '--'first_seat = t[31] or '--'second_seat = t[30] or '--'high_sleep = t[21] or '--'soft_sleep = t[23] or '--'dong_sleep = t[33] or '--'hard_sleep = t[28] or '--'sort_seat = t[24] or '--'hart_seat = t[29] or '--'no_seat = t[26] or '--'tb.add_row([num + 1, train_no, che, startcode, endcode, from_station_no, to_station_no, seat_types, starttime, endtime, duration_time, special_shop_seat, first_seat, second_seat, high_sleep, soft_sleep, dong_sleep, hard_sleep, sort_seat, hart_seat, no_seat])acc.append([num + 1, train_no, che, startcode, endcode, from_station_no, to_station_no, seat_types, starttime, endtime, duration_time, special_shop_seat, first_seat, second_seat, high_sleep, soft_sleep, dong_sleep, hard_sleep, sort_seat, hart_seat, no_seat])num += 1print(tb)return accexcept Exception as e:return edef price(self, a, b, c, d, e):url = f'https://kyfw.12306.cn/otn/leftTicket/queryTicketPrice?train_no={a}&from_station_no={b}&to_station_no={c}&seat_types={d}&train_date={e}'r = requests.get(url=url, headers=self.headers)if d == '1341':tb.field_names = (['软卧价格', '硬卧价格', '硬座价格', '无座价格'])soft_sleep_price = r.json()['data']['A4']hard_sleep_price = r.json()['data']['A3']hart_seat_price = r.json()['data']['A1']no_seat_price = r.json()['data']['WZ']tb.add_row([soft_sleep_price, hard_sleep_price, hart_seat_price, no_seat_price])return tbif d == '1346':tb.field_names = (['高级软卧软卧价格', '硬卧价格', '硬座价格', '无座价格'])high_soft_sleep_price = r.json()['data']['A6']soft_sleep_price = r.json()['data']['A4']hard_sleep_price = r.json()['data']['A3']hard_seat_price = r.json()['data']['A1']tb.add_row([high_soft_sleep_price, soft_sleep_price, hard_sleep_price, hard_seat_price])return tbif d == '134':tb.field_names = (['软卧价格', '硬卧价格', '硬座价格'])soft_sleep_price = r.json()['data']['A4']hard_sleep_price = r.json()['data']['A3']hart_seat_price = r.json()['data']['A1']tb.add_row([soft_sleep_price, hard_sleep_price, hart_seat_price])return tbif d == '9MO' or 'OM9':tb.field_names = (['商务座价格', '一等座', '二等座'])special_price = r.json()['data']['A9']first_seat_price = r.json()['data']['M']second_seat = r.json()['data']['O']tb.add_row([special_price, first_seat_price, second_seat])return tbif d == 'MOO':tb.field_names = (['一等座', '二等座'])first_seat_price = r.json()['data']['M']second_seat = r.json()['data']['O']tb.add_row([first_seat_price, second_seat])return tbif d=='FOO':tb.field_names = (['动卧', '二等座','无座'])dong_sleep = r.json()['data']['F']second_seat = r.json()['data']['O']no_seat = r.json()['data']['O']tb.add_row([dong_sleep, second_seat,no_seat])return tbif d=='FO':tb.field_names = (['动卧', '二等座'])dong_sleep = r.json()['data']['F']second_seat = r.json()['data']['O']tb.add_row([dong_sleep, second_seat])return tbif d=='F':tb.field_names = (['动卧'])dong_sleep = r.json()['data']['F']tb.add_row([dong_sleep])return tbif d=='MOP':tb.field_names = (['特等座', '二等座','一等座'])special_seat = r.json()['data']['P']second_seat = r.json()['data']['O']first_seat = r.json()['data']['M']tb.add_row([special_seat, second_seat,first_seat])return tbif d=='IJO':tb.field_names = (['二等座', '软卧','硬卧'])soft_sleep = r.json()['data']['AI']second_seat = r.json()['data']['O']hard_sleep = r.json()['data']['AJ']tb.add_row([second_seat, soft_sleep,hard_sleep])return tbdef road(self, a, b, c, d):tb.field_names = (['到站时间', '站点', '站数', '停留时间', '出站时间'])url_1 = f'https://kyfw.12306.cn/otn/czxx/queryByTrainNo?train_no={a}&from_station_telecode={b}&to_station_telecode={c}&depart_date={d}'resp = requests.get(url=url_1, headers=self.headers)data = resp.json()['data']['data']for i in data:arrive_time = i['arrive_time']station_name = i['station_name']station_no = i['station_no']stopover_time = i['stopover_time']start_time = i['start_time']tb.add_row([arrive_time, station_name, station_no, stopover_time, start_time])return tbdef success(self, e):while True:print('0,重新选择\n''1，查看价格\n''2，火车路程\n')f = input('请输入(-1退出):')if f == '-1':breakif f == '2':choose = int(input('请输入火车的序号:')) - 1xunhao = e[choose]j = self.road(xunhao[1],xunhao[3], xunhao[4], self.times)print(j)tb.clear()if f == '0':continueif f == '1':choose = int(input('请输入火车的序号:'))-1xunhao = e[choose]A=xunhao[1]B=xunhao[5]C=xunhao[6]D=xunhao[7]E = self.price(A, B, C, D, self.times)print(E)tb.clear()def main(self):while True:self.times = self.choose_time()if self.times == '-1':breaka = input('输入出发地:')b = input('输入终点:')c = self.get_code(a)d = self.get_code(b)e = self.get_data(self.times, c, d)tb.clear()if isinstance(e, list):self.success(e)else:print('没有返回数据!!!')choose = input('是否再次尝试\n1,是\n2,算了吧\n')if choose == '1':continueelse:break