soupR.py 代码例如以下

# -*- coding: cp936 -*-

import urllib

import urllib2

import os, re

from BeautifulSoup import BeautifulSoup

localDir = 'D:/test/'

URL = "http://cran.dataguru.cn/bin/windows/contrib/3.1/"

page = urllib2.urlopen(URL)

soup = BeautifulSoup(page)

page.close()

for a in soup.findAll('a'):

    if a is not None:

        text = a.text.strip()

        #if re.search('map',text):

        if text.startswith('map'):

            href = a.get('href')

            if href.endswith('.zip'):

                #print href

                localFile = localDir + text

                if os.path.exists(localFile):

                    print localFile,'is exists'

                else:

                    try:

                        # 依照url进行下载文件，并保存到本地文件夹

                        urllib.urlretrieve(URL+href,localFile)

                        print href,'is download'

                    except Exception,e:

                        continue