爬取12306全国各车站信息以及输入信息查询车次

最新推荐文章于 2024-05-25 23:37:51 发布

努力学习各种软件

最新推荐文章于 2024-05-25 23:37:51 发布

阅读量474

点赞数 1

分类专栏：爬虫案例文章标签： python 爬虫

本文链接：https://blog.csdn.net/m0_57265868/article/details/136625747

版权

爬虫案例专栏收录该内容

27 篇文章 5 订阅

订阅专栏

1.查询全国各车站信息并保存为json格式

mport time
import json
import requests
from requests.exceptions import RequestException


def getResponse(url):
    try:
        headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",}
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response
        return None
    except RequestException:
        return None


if __name__ == "__main__":
    url = "https://kyfw.12306.cn/otn/resources/js/framework/station_name.js"
    data = getResponse(url)
    if data is not None:
        dict_data = {}
        text = data.text
        str_split = text.split('@')
        for chars in str_split[1:]:
            station = chars.split('|')
            dict_data[station[1]] = station[2]
        # print (dict_data['深圳北'])
        with open("stations.json", 'w', encoding='utf-8') as fp:
            json.dump(dict_data, fp, ensure_ascii=False)

2.爬取车次信息

import pandas as pd
import requests
import json
'''
f = open('city.json',mode='r',encoding='utf-8')
text = f.read()
city_json = json.loads(text)



'''

url = 'https://kyfw.12306.cn/otn/leftTicket/query?'

data = {
    'leftTicketDTO.train_date': '2023-12-09',
    'leftTicketDTO.from_station': 'BJP',
    'leftTicketDTO.to_station': 'CDW',
    'purpose_codes': 'ADULT'
}

headers = {'User-Agent':
                'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36',
           'Cookie':
                'JSESSIONID=075AD1662DDC1E1B4BA1C32399779883; BIGipServerpassport=921174282.50215.0000; guidesStatus=off; highContrastMode=defaltMode; cursorStatus=off; route=9036359bb8a8a461c164a04f8f50b252; BIGipServerotn=2045247754.50210.0000; _jc_save_fromStation=%u5317%u4EAC%2CBJP; _jc_save_toStation=%u6210%u90FD%2CCDW; _jc_save_fromDate=2023-12-09; _jc_save_toDate=2023-12-09; _jc_save_wfdc_flag=dc',
           'Referer':
                'https://kyfw.12306.cn/otn/leftTicket/init?linktypeid=dc&fs=%E5%8C%97%E4%BA%AC,BJP&ts=%E6%88%90%E9%83%BD,CDW&date=2023-12-09&flag=N,N,Y'



                           }

response = requests.get(url=url,params=data,headers=headers)
response.encoding = response.apparent_encoding  # 自动识别编码

result = response.json()['data']['result']
lis = []
for index in result:
    index_list = index.replace('有','Yes').replace('无','No').split('|')  # 字符串分割方法，分割返回的是列表数据
    num = index_list[3]    #车次
    if 'G' in num:
        start_time = index_list[8]  # 出发时间
        end_time = index_list[9]  # 到达时间
        use_time = index_list[10]  # 耗时
        Top = index_list[32]      # 特等座
        first = index_list[31]     # 一等座
        second = index_list[30]    # 二等座
        dit = {
            'num':num,
            'start':start_time,
            'end':end_time,
            'usetime':use_time,
            'Top':Top,
            'first':first,
            'second':second,
            'yz':'-',
            'wz':'-',
            'rw':'-',
            'yw':'-',


        }
    else:
        start_time = index_list[8]  # 出发时间
        end_time = index_list[9]  # 到达时间
        use_time = index_list[10]  # 耗时
        rw = index_list[23]  # 软卧
        yw = index_list[28]  # 硬卧
        yz = index_list[29]  # 硬座
        wz = index_list[26]  # 无座
        dit = {
            'num': num,
            'start': start_time,
            'end': end_time,
            'usetime': use_time,
            'Top': '-',
            'first': '-',
            'second': '-',
            'yz': yz,
            'wz': wz,
            'rw': rw,
            'yw': yw,

        }

    lis.append(dit)

content = pd.DataFrame(lis)
print(content)