import requests
import re
url = 'http://tmall.chd.sdo.com/'
res= requests.get(url)
lt=re.findall('
(.*?)
',res.text,re.S)print(lt)
import requests
import re
url = 'http://tmall.chd.sdo.com/'
res= requests.get(url)
lt=re.findall('
爬取网页内容和简单,主要是看你想要里面的什么内容,然后通过xpath、bs4或者re去匹配即可
#-*- coding:utf-8 -*-
import requests
headers = {"User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.87 Safari/537.36"}
url = 'http://tmall.chd.sdo.com/'
res= requests.get(url,headers=headers)
print(res.content.decode('utf-8'))