爬取火车经停站

准备

• 导入相关包

import requests
import xlwt
import xlrd
from bs4 import BeautifulSoup

自定义函数

• 获取学生车次号

def getInfo(filename):
    dx = xlrd.open_workbook(filename, encoding_override='utf-8')
    sheet1 = dx.sheet_by_index(0)       # 获取第一张工作表
    trips = sheet1.col_values(12)       # 第13列为车次信息

    return trips                        # 返回车次列表

• 根据车次号获取HTML代码

def getHtml(trip):
    headers = {
                'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.87 Safari/537.36'
            }

    url = 'https://trains.ctrip.com/trainbooking/TrainSchedule/' + trip

    response = requests.get(url, headers)

    html = response.text

    return html

• 解析HTML得到经停站

def getTrips(html):
    soup = BeautifulSoup(html, 'lxml')
    aList = soup.select('td>a')     # td节点下的a结点
    strTrip = ''

    for trip in aList:
        strTrip += trip.string + '  '

    return strTrip

• 写入Excel

def writeInfo(filename,resultTrips):
    'resultTrips为每趟车次的停经站的车次字符串列表 '
    dx = xlrd.open_workbook(filename, encoding_override='utf-8')
    sheet1 = dx.sheet_by_index(0)    
    names = sheet1.col_values(4)    # 得到学生姓名
    trips = sheet1.col_values(12)   # 得到车次
    index = len(names)  # 获取需要写入数据的行数
    workbook = xlwt.Workbook()  # 新建一个工作簿
    sheet = workbook.add_sheet('dx1701')  # 在工作簿中新建一个表格
    for i in range(0, index):
        sheet.write(i, 0, names[i])          # 向表格中写入姓名
        sheet.write(i, 1, trips[i])          # 向表格中写入车次
        sheet.write(i, 2, resultTrips[i])    # 向表格写入停经站
    workbook.save('trips.xls')  # 保存工作簿
    print("xls格式表格写入数据成功！")

运行

• 主函数

if __name__ == "__main__":
    filename = 'idcard.xlsx'
    trips = getInfo(filename)
    resultTrips = []
    for trip in trips:
        html = getHtml(trip)
        strTrip = getTrips(html)
        if not strTrip:
            resultTrips.append('没有找到该车次')
            continue
        resultTrips.append(strTrip)
    writeInfo(filename, resultTrips)