参考:https://blog.csdn.net/tanlangqie/article/details/79506543
1 # -*- coding:utf-8 -*- 2 import urllib 3 import urllib.request 4 import re 5 6 def getHtml(url): 7 request = urllib.request.Request(url) 8 response = urllib.request.urlopen(request) 9 html = response.read() 10 return html 11 12 def getImg(html): 13 reg = 'data-original="(.+?.jpg)"' 14 imgre = re.compile(reg) 15 imglist = re.findall(imgre, html.decode('utf-8')) 16 localpath='G:/photo/' 17 x = 1 18 for imgurl in imglist : 19 urllib.request.urlretrieve(imgurl,localpath+'%s.jpg' % x) 20 print('正在下载第%s张图片' % x) 21 x+=1 22 if x>20: 23 break 24 return None 25 26 html = getHtml("https://www.zhihu.com/question/27364360") 27 getImg(html)