用python脚本遍历下载网站文件夹

因为需要，希望能下载http://www.xxx.us/上的所有xls/txt/pdf/rtf类型的资料，并按照相同路径保存文档。当然可以直接网上下载一个批量下载工具来搞定，但对于有DIY癖好的人来讲，当然自己写喽。

#coding=utf-8
from bs4 import BeautifulSoup
import os, sys, urllib2,time,random
 
path = os.getcwd()                     
root_path = os.path.join(path,u'TempDownload')
if not os.path.isdir(root_path):
    os.mkdir(root_path)
 
 
def download_loop(url, dl_path):
    print url
    content = urllib2.urlopen(url)
    soup = BeautifulSoup(content)
    link = soup.find_all('a')
    for download in link:
        flink = download.get('href')
        if flink.find(".pdf",len(flink)-4) <> -1 or flink.find(".xls",len(flink)-4) <> -1 or flink.find(".txt",len(flink)-4) <> -1 or flink.find(".xlsx",len(flink)-5) <> -1 or flink.find(".rtf",len(flink)-4) <> -1:
          print '+'+flink
          content2 = urllib2.urlopen(url+flink).read()
          with open(dl_path+'/'+flink,'wb') as code:
             code.write(content2)
        temp = download.get_text()
        if flink.find("/",len(flink)-1) <> -1 and temp <> u'Parent Directory':
          directory=str(flink[:-1])
          file_path= os.path.join(dl_path,directory.replace("%20"," "))
          if not os.path.isdir(file_path):
            os.mkdir(file_path)
          print '-'+flink + ' || path is:' + str(dl_path)
          new_url=url+flink
          download_loop(new_url, file_path)


##    print u'download completed'
     
download_loop('http://www.xxx.us/', root_path)
print "~~~~~~~~~~~~~~~~~~~~~~~~~~END~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
raw_input("Press <Enter> To Quit!")