python 爬取静态网页

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/qq_38204686/article/details/79170059

# python 3.6.3
import re
from urllib import request
# '''网址'''  图片_百度百科  获取整个网页的代码
url = 'https://baike.baidu.com/item/%E5%9B%BE%E7%89%87/372416?fr=aladdin'
page = request.urlopen(url)
code = page.read()
code=code.decode('utf-8')

# 正则表达式  编译
pattern = 'src="(.+\.jpg)"'
reg = re.compile(pattern)

# 找到图片资源并下载到指定目录
imgs = reg.findall(code)
i = 0
for img in imgs:
    i = i + 1
    print(str(i)+img)
    request.urlretrieve(img,r'C:\Users\Administrator\Desktop\img\%s.jpg' %i)