简单爬取去哪儿网

去哪儿网

import requests
import pandas as p
from bs4 import BeautifulSoup as bs

def spider(url):
    req=requests.get(url)
    req.encoding='utf-8'
    return bs(req.text,'html.parser')

def pandaWork(lis1,lis2,lis3):
    data=p.DataFrame({'地区名称':lis1,'地址':lis2,'起步价格':lis3})
    w=p.ExcelWriter('去哪儿网.xlsx')
    data.to_excel(w,'去哪儿网')
    w.save()
lis1=[]
lis2=[]
lis3=[]

for i in range(5):
    url='https://piao.qunar.com/ticket/list.htm?keyword=%E6%9D%AD%E5%B7%9E&region=%E6%9D%AD%E5%B7%9E&from=mpshouye_hotcity&page='+str(i+1)
    pbj=spider(url)
    for i in pbj.find_all('div',class_="sight_item"):
        lis1.append(i.find('a',class_='name').text)
        lis2.append(i.find('div',class_="intro color999").text)
        lis3.append(i.find('span',class_="sight_item_price").text)
pandaWork(lis1,lis2,lis3)