使用python采集某网站的图片

因为无法直接使用遨游的图片保存工具，所以自己用python写了一个。保存文件和文件名生成参考了别人的代码，加上了用BeautifulSoup解析网页内容的部分。

#coding=utf-8

from BeautifulSoup import BeautifulSoup
import urllib
import urllib2
import httplib, urlparse   
import re   
import random 

save_path=u"d:\\temp\\"
save_title=u""


def gGetFileName(url):   
    if url==None:
        return None   
    if url=="" :
        return ""  
    arr=url.split("/")   
    return arr[len(arr)-1]

def gRandFilename(type):   
    fname = ''  
    for i in range(16):   
        fname = fname + chr(random.randint(65,90))   
        fname = fname + chr(random.randint(48,57))
    if type=="":
        type="jpg"
    if type==None:
        type="jpg"
    return fname + '.' + type

def gDownload(url):   
    try:   
        urlopen=urllib.URLopener()   
        fp = urlopen.open(url)   
        data = fp.read()   
        fp.close()   
        file=open(save_path + gRandFilename("jpeg"),'w+b')   
        file.write(data)   
        file.close()
        print 'download successfully:'+ url
    except IOError:   
        print "download error!"+ url

def geturl(url):
    page=urllib2.urlopen(url)
    soup=BeautifulSoup(page,fromEncoding="GBK")
    script=soup.findAll('input',type="image")
    for ele in script:
        img_src=ele['src']
        gDownload(img_src)

if __name__=="__main__":
    url="http://www.baidu.com/htm_data/16/1011/600682.html"
    geturl(url)