soupR.py 代码如下# -*- coding: cp936 -*-
import urllib
import urllib2
import os, re
from BeautifulSoup import BeautifulSoup
localDir = 'D:/test/'
URL = "外链网址已屏蔽;
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:
# 按照url进行下载文件，并保存到本地目录
urllib.urlretrieve(URL+href,localFile)
print href,'is download'
except Exception,e:
continue

                    

#!/usr/bin/perl
use HTTP::Tiny;
use Data::Dumper;
my $contrib_url="http://mirrors.ustc.edu.cn/CRAN/web/packages/available_packages_by_name.html";
my $browser=HTTP::Tiny->new();
my $response=$browser->get("$contrib_url");
my $content=$response->{"content"};
my @lines=split/\n/,$content;
my $i=0;
foreach my $line(@lines){
        if($line=~m/href="([\w\d\.\/]+)"/){
                my $pkg_url=$1;
                $pkg_url=~s|\.\.\/\.\.|http://mirrors.ustc.edu.cn/CRAN|;
                $response=$browser->get("$pkg_url");
                $content=$response->{content};
                $content=~m/href="(.*tar.gz)"/;
                $down_link=$1;
                $down_link=~s|\.\.\/\.\.\/\.\.|http://mirrors.ustc.edu.cn/CRAN|;
                if($down_link=~m/\/([\w\d\._\-]+\.tar\.gz)$/){
                        $i++;
                        my $pkg_name=$1;
                        print "$i Downloading!!!\n";
                        system("wget -c $down_link -O $pkg_name");
                }
        }
}
~               









本文转自 tiger506 51CTO博客，原文链接：http://blog.51cto.com/tiger506/1608601，如需转载请自行联系原作者



        
        
                
    

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
本文转自mfrbuaa博客园博客，原文链接：http://www.cnblogs.com/mfrbuaa/p/5058021.html，如需转载请自行联系原作者

R语言设置CRAN使用清华大学镜像，命令如下：

options(repos=structure(c(CRAN="http://mirrors.tuna.tsinghua.edu.cn/CRAN/")))

soupR.py 代码如下

# -*- coding: cp936 -*-
import urllib
import urllib2
import os, re
from BeautifulSoup import BeautifulSoup

localDir = 'D:/test/'
URL = "http://mirrors.tuna.tsinghua.edu.cn/CRAN/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:
                        # 按照url进行下载文件，并保存到本地目录
                        urllib.urlretrieve(URL+href,localFile)
                        print href,'is download'
                    except Exception,e:
                        continue