import urllib.request from bs4 import BeautifulSoup import re import os def getcontent(url): req=urllib.request.Request(url) req.add_header("User-Agent","Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.101 Safari/537.36") page=urllib.request.urlopen(req) html=page.read().decode('utf-8') return html def downimg(content): regex=re.compile(r'<img class="BDE_Image".*?src="([^"]*\.jpg)".*?>') imglist=regex.findall(content) try: os.mkdir("nnimg")#下载到本地之前,需要选择下载的路径,或者创建新的文件夹 except FileExistsError: pass os.chdir("nnimg")#改变工作路径 for each in imglist: print(each) filename=each.split("/")[-1] urllib.request.urlretrieve(each,filename,None)#直接将远程数据下载到本地 if __name__ =="__main__": url="http://tieba.baidu.com/p/3823765471" downimg(getcontent(url))