无标题文章

下面的代码需要掌握基础的Python知识即可理解,very easy !

代码引用

# coding = utf-8
import urllib
import re

def getHtml(url):
    page = urllib.urlopen(url)
    html = page.read()
    return html

def getImg(html):
    reg = r'src="(.+?)" alt' """正则表达式 过滤图片链接"""
    imgre = re.compile(reg)
    imglist = re.findall(imgre, html)
    print imglist
    x = 0
    for imgurl in imglist:
        imgurl = 'https:'+imgurl """拼接完整URL"""
        print imgurl
        urllib.urlretrieve(imgurl, '/Users/.../Desktop/img/%s' %x)
        x = x+1


html = getHtml("http://www.jianshu.com/")
# print html
print getImg(html)