import requests from bs4 import BeautifulSoup#使用工具 import pandas as pd url='http://www.mafengwo.cn/search/q.php?q=泉州'#网站 headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)Chrome/69.0.3497.100 Safari/537.36'}#伪装爬虫 r = requests.get(url,timeout = 30,headers=headers) soup=BeautifulSoup(r.text,'lxml') x=[]#建一个列表 for list1 in soup.find_all('li',class_="clearfix"): x.append(list1.get_text()) print (x)
打开网站
点击右键查看源代码
找到要爬取的数据
用代码进行爬取
最终得到: