python meizitu

import re
import urllib.request

# ------ 获取网页源代码的方法 ---
def getHtml(url):
    page = urllib.request.urlopen(url)
    html = page.read()
    return html

# ------ getHtml()内输入任意静态URL ------
html = getHtml("http://www.meizitu.com/a/5485.html")
# ------ 修改html对象内的字符编码为gbk或者UTF-8 ------
html = html.decode('gbk')

# ------ 获取所有图片地址的方法 ------

    # ------ 利用正则表达式匹配网页内容找到图片地址 ------
reg = r'(http://[^s]*/[0-9][0-9].jpg)'
mmurl = re.findall(reg,html)
    #reg = r'src="([.*S]*.jpg)" pic_ext="jpeg"'
    #reg = r'src="(..jpg)" pic_ext="jpeg"'
#    imgre = re.compile(reg)
#    imglist = re.findall(reg, html)
#    return imglist
#print(re.findall(reg, html))

x = 0
for imgurl in mmurl:
    opener = urllib.request.build_opener()
    opener.addheaders = [('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1941.0 Safari/537.36')]
    urllib.request.install_opener(opener)
    urllib.request.urlretrieve(imgurl, 'd://1/5485/%s.jpg' % x )
    x += 1

print("All Done!")