python下载文件（图片）源码，包含爬网内容（爬url），可保存cookie

#coding=utf-8
'''
Created on 2013-7-17

@author: zinan.zhang
'''

import re
import time
import httplib2
import urllib
from bs4 import BeautifulSoup

#路径
savePath = 'F://TDDOWNLOAD//aNO.4//'

#获取url
def url_xunhuan(url,list):
    return url + list

#下载图片的时候
time.sleep(0.5)#先sleep，再读取数据
"""根据url下载文件，文件名自动从url获取"""
def gDownload(url,savePath):
    #参数检查，现忽略
    fileName = gGetFileName(url)
    #fileName =gRandFilename('jpg')
    gDownloadWithFilename(url,savePath,fileName)
   
"""根据url获取文件名"""
def gGetFileName(url):
    if url==None: return None
    if url=="" : return ""
    arr=url.split("/")
    return arr[len(arr)-1]

"""根据url下载文件，文件名参数指定"""
def gDownloadWithFilename(url,savePath,file):
    #参数检查，现忽略
    try:
        urlopen=urllib.URLopener()
        fp = urlopen.open(url)
        data = fp.read()
        fp.close()
        file=open(savePath + file,'w+b')
        file.write(data)
        print "下载成功："+ url
        file.close()
    except IOError:
        print "下载失败:"+ url
       
#初始化页面，提取必要信息
def getPage(url):
    userAgent = 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko)'
    headers = {
       'User-Agent': userAgent,
       'Accept-Language':  'zh-CN,zh;q=0.8',
       'Accept': 'text/css,*/*;q=0.1',
       }
    http = httplib2.Http(".cache")
    _, content = http.request(url, 'GET',headers=headers)
    return content

#循环下载列表固定的  ---就是wallpaper,enterdesk等网站
def xuanhuan_down_list():
    list=[]
    url = 'http://tupian.enterdesk.com/2013/mxy/0311/4/'
    temp=10
    for i in range(temp):
        list.append(str(i)+'.jpg')
    for i in range(temp):
        url_list = url_xunhuan(url,list[i])
        gDownload(url_list,savePath)
        time.sleep(0.2)

#爬网获取url
def spider_url(url):
    page = getPage(url)
    dom = BeautifulSoup(page)
    srcs = [x['src'] for x in dom.findAll('img')]
    #成功获取url
    return srcs[0]
   
#循环下载列表随机的 ---就是ZOL桌面壁纸下载
def xuanhuan_down_suiji():
    try:
        temp=25
        i=88
        j=i
        while (i <= j+temp):
            #http://desk.zol.com.cn/showpic/1920x1200_30688_33.html
            url = 'http://desk.zol.com.cn/showpic/1920x1200_12'+str(i)+'_37.html'
            src_url = spider_url(url)
            gDownload(src_url,savePath)
            time.sleep(0.1)
            i+=1
    except IOError:
        print "url获取失败！"

if __name__ == "__main__":
    #gDownload(url,savePath)
    '''
    #批量下载序号固定的图片
    xuanhuan_down_list()
    '''
    '''
    #批量下载隐藏jpg路径的文件
    xuanhuan_down_suiji()
    '''
    #批量下载文件
   
   
   
    print '下载完成！'