Python之12306查询

#模拟浏览器向服务器发送请求
import requests
import re
import urllib.parse      #编码
#请求URL，由于该URL请求方式为get
def send_request():
    url = 'https://kyfw.12306.cn/otn/leftTicket/query?leftTicketDTO.train_date=2020-08-19&leftTicketDTO.from_station=IZQ&leftTicketDTO.to_station=XMS&purpose_codes=ADULT'
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.87 Safari/537.36',
               'Cookie': '_uab_collina=159747365464705128119335; JSESSIONID=F6D9AC296707C339E6D146DD6A117C7F; RAIL_DEVICEID=OVFcs8ehj4U3E5U4tYg0O6EpBczEdyW1VGlfjVVGzJ12tjkYPQIyb2R0Xiwe_5YFS8B6_sOzmHW6XUvH1Rn1LFY4WdlhmQA1SXPB1sqhzBU1JoaM3FNhyPt9engE3FFrJw0cTH3ymzmmTsImxnxZ8JtGDjMGVkpR; RAIL_EXPIRATION=1597745363482; _jc_save_fromStation=%u5E7F%u5DDE%u5357%2CIZQ; _jc_save_toStation=%u53A6%u95E8%2CXMS; _jc_save_wfdc_flag=dc; BIGipServerotn=2581004554.24610.0000; BIGipServerpassport=904397066.50215.0000; route=495c805987d0f5c8c84b14f60212447d; _jc_save_fromDate=2020-08-19; _jc_save_toDate=2020-08-18'}
    resp = requests.get(url,headers=headers)
    resp.encoding='utf-8'
    # print(resp.text)
    return resp
#提取数据
def parse_json(resp,city):
    json_ticket = resp.json()     #将响应结果转成json
    data_list = json_ticket["data"]["result"] #提取车次的列表
    #遍历每一个车次信息
    # d = data_list[0].split('|')
    lst = []
    for item in data_list:
        d = item.split('|')
        lst.append([d[3],city[d[6]],city[d[7]],d[31],d[30],d[13]])
    return lst
    '''3、车次
    4、车起始
    5、车终点
    6、查询起始点
    7、查询车终点
    8、出发时间
    9、到达时间
    10、历时
    21、高级软卧
    23、软卧一等座
    26、无座
    27、软座
    28、硬卧二等座
    29、硬座
    30、二等座、二等包座
    31、一等座
    32商务特等'''

def start():
    lst = parse_json(send_request(),get_city())
    for i in lst:
        if i[3]!='无'and i[3]!='':
            print(i)

#获取站点信息
def get_city():
    url = 'https://kyfw.12306.cn/otn/resources/js/framework/station_name.js?station_version=1.9152'
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.87 Safari/537.36'}
    resp = requests.get(url,headers=headers)
    resp.encoding='utf-8'
    stations = re.findall('([\u4e00-\u9fa5]+)\|([A-Z]+)',resp.text)     #[\u4e00-\u9fa5]表示全部中文汉字

    #将列表转成字典
    stations_data = dict(stations)
    station_d = {}
    for item in stations_data:
        station_d[stations_data[item]] = item
    return station_d

if __name__ == '__main__':
    start()