python基礎爬蟲

import requests
import re

# 獲取對象的url
url2 = 'http://www.dzu.edu.cn/'

# 僞裝成默認瀏覽器訪問
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)
# 因爲出現了亂碼  所以改變編碼方式
response.encoding = 'utf-8'

# print(response)
# 將返回的response轉換爲text
html = response.text
# 利用正則進行數據清洗
title = re.findall(r'<li><a href="(.*?)">書記信箱</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
# 數據永久化處理
for x in imgs:
	imgurl = 'http://www.dzu.edu.cn/%s'%x
	print(imgurl)
	# 進行二進制書寫
	fb = open('%d.jpg' %i, 'wb')
	# 返回迴應
	repose =  requests.get(imgurl)
	# 將回應轉化爲二進制
	data = repose.content
	fb.write(data)
	i = i+1;