python抓取网页图片并放到指定文件夹

python抓取网站图片并放到指定文件夹

# -*- coding=utf-8 -*-
import urllib2
import urllib
import socket
import os
import re
def docment():
    print u'把文件存在e:\python\图（请输入数字或字母）'
    h=raw_input()
    path=u'e:\python\图'+str(h)
    if not os.path.exists(path):
        os.makedirs(path)
    return path
def getallurl(html):
    reg=r"a href='(.*?\.htm)'"
    allurl= re.compile(reg)
    alllist = re.findall(allurl,html)
    return alllist
def gethtml(url):
    url=url
    req_header = {'user-agent':'mozilla/5.0 (windows; u; windows nt 6.1; en-us; rv:1.9.1.6) gecko/20091201 firefox/3.5.6'}
    req_timeout = 20
    html='cuowu'
    try:
        req = urllib2.request(url,none,req_header)
        resp = urllib2.urlopen(req,none,req_timeout)
        html = resp.read()
    except urllib2.urlerror as e:
        print e.message
    except socket.timeout as e:
        gethtml(url,fu)
    return html
def getimg(html,path):
    reg = r'img class=img_show border=0 src=(.*?\.jpg)'
    imgre= re.compile(reg)
    imglist = re.findall(imgre, html)
    if imglist:
        print 'ghasghg',path
        for imgurl in imglist:
            print imgurl
            content2=urllib2.urlopen(imgurl).read()
            with open(path+'/'+imgurl[-7:],'wb') as code:
                code.write(content2)
    else:
        return 0
def getallurl(html):
    reg=r"a href='(.*?\.htm)'"
    allurl= re.compile(reg)
    alllist = re.findall(allurl,html)
    return alllist
j=1
i=0
print u'请输入网址:'
ul=raw_input()
print u'开始下载'
print u'第'+str(j)+u'页'
html=gethtml(ul)
alllist=getallurl(html)
path=docment()
getimg(html,path)
while i<len(alllist):
    for lis in alllist:
        l=lis[i]
        url=r'http://www.umei.cc/p/gaoqing/rihan/'+lis
        i=i+1
        j=j+1
        html=gethtml(url)
        getimg(html,path)
        print u'第'+str(j)+u'页'
    else:
        print u'下载完毕'