python爬取图片简记

参考:https://blog.csdn.net/tanlangqie/article/details/79506543

# -*- coding:utf-8 -*-
import urllib
import urllib.request
import re

def getHtml(url):
    request = urllib.request.Request(url)
    response = urllib.request.urlopen(request)
    html = response.read()
    return html

def getImg(html):
    reg = 'data-original="(.+?\.jpg)"'     
    imgre = re.compile(reg)
    imglist = re.findall(imgre, html.decode('utf-8'))
    localpath='G:/photo/'
    x = 1
    for imgurl in imglist  :
        urllib.request.urlretrieve(imgurl,localpath+'%s.jpg' % x)  
        print('正在下载第%s张图片' % x)
        x+=1
        if x>20:                    
            break
    return None

html = getHtml("https://www.zhihu.com/question/27364360")
getImg(html)