网页资源下载器

import urllib
import urllib2
import re
import socket

#######################You may change here###############
baseurl = '##########'  #请自行添加下载网页地址
format = '(pdf|txt|cc|ppt|pptx)' #下载格式，可自行添加
#########################################################

def downfunc(blocknum, blocksize, totalsize):
'''回调函数
@blocknum:  已经下载的数据块
@blocksize: 数据块的大小
@totalsize: 下载文件的大小
'''
percent = 100.0 * blocknum * blocksize / totalsize
if percent > 100:
percent = 100
print "下载完成^^~"
else:
print "已下载%.2f%%......"% percent

def download(downurl, localFileName=None):
#m = re.search('(\w+.pdf)',downurl)
m = re.search('(\w+.%s)' % format,downurl)
if localFileName == None:
localFileName = m.group(0)

print ("正在下载" + localFileName)

try:
urllib.urlretrieve(downurl, localFileName,downfunc)
except socket.timeout:
print "下载超时"

socket.setdefaulttimeout(30)

#打开页面
page = urllib2.urlopen(baseurl)

# 读取包含HTML源码内容的页面信息
page_inform = page.read()

# 获取资源列表
#list_of_res = re.findall(r'href=.*"(.*\.pdf)', page_inform)
list_of_res = re.findall(r'href=.*"(.*\.%s)' % format, page_inform)

# 去除重复的资源
list_of_res = list(set(list_of_res))

# 根据资源列表逐个下载
for res in list_of_res:
downurl = res[0]
if downurl[0:4] != 'http':
downurl = baseurl+downurl
download(downurl)