import urllib.request
import re
def openl(url):
r=urllib.request.Request(url)
r.add_header('User-Agent','Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:73.0) Gecko/20100101 Firefox/73.0')
am=urllib.request.urlopen(r)
h=am.read().decode('utf-8')
return h
def geti(h):
p=r'<img alt="张哲瀚" id="mbpho-img" class="js-favorite-blogimg" src="(.*?\.jpeg)'
i=re.findall(p,h)
for e in i:
f=e.split('/')[-1]
urllib.request.urlretrieve(e,f,None)#下载图片
if __name__=='__main__':
url='https://www.duitang.com/blog/?id=897699310'
geti(openl(url))
在这里插入代码片
python爬虫之正则表达式搜取信息
猜你喜欢
转载自blog.csdn.net/feiqipengcheng/article/details/104639660
今日推荐
周排行