用python制作火车站列车进站时刻表

最近需要查看火车站列车进站时刻

 

效果图

 

 

一、搜集数据

http://search.huochepiao.com/chezhan/wuxi

 

只有始发站和终点站信息，并没有到无锡站时间，只能根据每个车次获取

车次	出站 - 到站	类型	开车时间	到站时间	运行时间	里程
D306/D307	无锡   西安北	动车组	00:02	10:03	10小时4分	1355
K5562	无锡   亳州	快速	00:20	11:21	11小时5分	571
K5601/K5604	无锡   宁波	快速	00:25	07:06	6小时46分	203
K8372	无锡   徐州	快速	00:26	08:42	8小时20分	563
T136	无锡   济南	特快	00:32	10:14	9小时46分	842
K8386/K8387	无锡   阜阳	快速	00:51	08:48	8小时0分	571

from django.http import HttpResponse
from django.http.response import JsonResponse
from django.shortcuts import render
from coviddata.models import traintime
import urllib.request
import requests
import re
from bs4 import BeautifulSoup
import datetime
from distutils.filelist import findall
# 数据库操作
def getTrainData():
    # 初始化
    trainid=""
    htmlcontext= ""
    list = traintime.objects.all()
    #list = traintime.objects.order_by('trainid')[0:1]
    for var in list:
        trainid = var.trainid + ""
        webname="http://search.huochepiao.com/checi/"+trainid
        response = requests.get(webname)
        # 类文件对象支持 文件对象的操作方法，如read()方法读取文件全部内容，返回字符串
        htmlcontext = response.content
        htmlcontext = str(htmlcontext, 'gbk')
        soup = BeautifulSoup(htmlcontext, "html.parser")
        for tag in soup.find_all('a', href='http://search.huochepiao.com/chezhan/wuxi'):
            parent=tag.parent.parent
            tds=parent.find_all('td')
            var.arrivetime = tds[3].get_text()
        tag=soup.find('td',text='始发站')
        parent = tag.parent.parent
        tds = parent.find_all('td')
        var.startstation = tds[8].get_text()
        var.endstation=tds[10].get_text()
        var.save()

利用requests逐个获取车次信息

利用soup找到到达无锡站时间

利用model traintime 保存到数据库

 

二、展示数据

# -*- coding: utf-8 -*-
from django.http import HttpResponse
from django.http.response import JsonResponse
from django.shortcuts import render
from coviddata.models import traintime
import urllib.request
import requests
import re
from bs4 import BeautifulSoup
import datetime
from distutils.filelist import findall
def gettrainlist(request):
    request.encoding = 'utf-8'
    htmlcontext=""
    context = {}
    start_time = datetime.time(0, 0, 0)
    end_time = datetime.time(23, 59, 59)
    #根据四个班次分时刻显示
    if 'q' in request.GET and request.GET['q']:
        name=request.GET['q']
        url=name
        if (name=="1"):
            start_time = datetime.time(0,0,0)
            end_time = datetime.time(5,59,59)
        elif (name=="2"):
            start_time = datetime.time(6, 0, 0)
            end_time = datetime.time(11, 59, 59)
        elif (name == "3"):
            start_time = datetime.time(12, 0, 0)
            end_time = datetime.time(17, 59, 59)
        elif (name == "4"):
            start_time = datetime.time(18, 0, 0)
            end_time = datetime.time(23, 59, 59)
        else:
            start_time = datetime.time(18, 0, 0)
            end_time = datetime.time(23, 59, 59)
    else:
        start_time = datetime.time(0, 0, 0)
        end_time = datetime.time(23, 59, 59)
        #list = communitydata.objects.filter(districtname__icontains=name)
    list = traintime.objects.filter(arrivetime__range=(start_time, end_time)).order_by('arrivetime')
    context['trainlist'] = list
    return render(request, 'trainlist.html', context)