python基础爬虫

import requests
import re

# 获取对象的url
url2 = 'http://www.dzu.edu.cn/'

# 伪装成默认浏览器访问
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:67.0) Gecko/20100101 Firefox/67.0",}

response = requests.get(url2, headers  =  headers)
# 因为出现了乱码  所以改变编码方式
response.encoding = 'utf-8'

# print(response)
# 将返回的response转换为text
html = response.text
# 利用正则进行数据清洗
title = re.findall(r'<li><a href="(.*?)">书记信箱</a></li>',html)
imgs = re.findall(r'<img src="(.*?)" alt="">', html)

# print(imgs)

# print(title)

# with open('%s.jpg' %imgs[0]) as f:
i = 0
# 数据永久化处理
for x in imgs:
	imgurl = 'http://www.dzu.edu.cn/%s'%x
	print(imgurl)
	# 进行二进制书写
	fb = open('%d.jpg' %i, 'wb')
	# 返回回应
	repose =  requests.get(imgurl)
	# 将回应转化为二进制
	data = repose.content
	fb.write(data)
	i = i+1;