python爬取网页（简易）

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/weixin_39641975/article/details/78701950

爬取的照片信息

from urllib import request
import re

def getResponse(url):
 url_request =  request.Request(url)
 url_response = request.urlopen(url_request)
 
 return url_response
 
def getjpg(data):
 jpglist =  re.findall(r'src="http.+?.jpg"',data)
 return jpglist
 
http_response = getResponse("http://dzh.mop.com/")

data = http_response.read().decode('utf-8')
L = getjpg(data)

global n
n = 1
for jpginfo in L:
 print(n,'------',jpginfo)
 n=n+1

爬取网页信息

import urllib.request

url = "http://www.douban.com/"

request =  urllib.request.Request(url)

response =  urllib.request.urlopen(request)

data =  response.read()

data = data.decode('utf-8')

print(data)

print(type(response))
print(response.geturl())
print(response.info())
print(response.getcode())