http://blog.csdn.net/infoworld/article/details/19547723

以下代码是基于infoworld的csdn备份python代码修改的cnblogs博客备份，但是和infoworld的界面不匹配，只能够用在python里面。python确实有意思，开发很快，怪不得这么流行。

#! encoding=utf-8

#cnblogs博客备份，使用方法：修改最下面的url和output，然后执行就可以了。

import urllib2
import re
import os
import sys
# from HTMLParser import HTMLParser
import html5lib
# from xml.etree.ElementTree import ElementTree
from urlparse import urlparse
import xml
import codecs
import traceback
import time

# class MyHTMLParser(HTMLParser):

#     def handle_starttag(self, tag, attrs):
#         # if tag.lower() == "img":
#             print "Encountered the beginning of a %s tag,attrs size %d" % (tag ,len(attrs))
#             for x in attrs:
#                 print "name %s,value %s" % (x[0],x[1])
#     def handle_endtag(self, tag):
#         print "Encountered the end of a %s tag" % tag

#     def handle_startendtag(self, tag, attrs):
#         print "Encountered the beginning of a %s tag,attrs size %d" % (tag ,len(attrs))
#         for x in attrs:
#             print "name %s,value %s" % (x[0],x[1])

# 资源尝试次数
gTestTime = 5

def DownloadFile(url,output):
    responseText = None
    dirssPath = None
    try:
        res = urlparse(url)
        url = res.scheme+"://"+res.netloc+res.path
        path = res.path
        index = path.rfind('/')
        dirss = "/"
        if index != -1:
            dirss =  output + "/" + res.netloc.encode("utf-8") + path[0:index].encode("utf-8")
            dirssPath = output + "/" + res.netloc.encode("utf-8") + path.encode("utf-8")
            dirss_ansi = dirss.decode('utf-8')
            if not os.path.exists(dirss_ansi):
                os.makedirs(dirss_ansi)
        global gTestTime
        count = gTestTime    
        while True:
            if count < 0:
                break
            count = count - 1
            header={"User-Agent": "Mozilla-Firefox5.0"}
            if not url.startswith("http://"):
                break
            try:
                # print "url: %s:%d" % (url,count)
                time.sleep(0.5)
                request = urllib2.Request(url,None,header)
                response = urllib2.urlopen(request)
                dirssPath_ansi = dirssPath.decode("utf-8")
                if not os.path.exists(dirssPath_ansi):
                    resourceFile = open(dirssPath_ansi,"wb")
                    responseText = response.read()
                    if url.endswith(".js"):
                        responseText = responseText.replace("http://","")
                        responseText = responseText.replace("https://","")
                    resourceFile.write(responseText)
                    resourceFile.close()
                break         
            except Exception,e:
                print "DownloadFile: %s:%s:%d" % (e,url,count)
                # pass
                # exstr = traceback.format_exc()
                # print exstr

    except Exception,e:
            pass
            # exstr = traceback.format_exc()
            # print exstr
    
    return (responseText,url,output)

def ReadCss(css):
    # print "ReadCss"
    mode = 'url\(\"?([^)]+)\"?\)'
    pattern = re.compile(mode)
    try:
        text = css[0]
        if css[0] == None:
            return
        strMatch = pattern.findall(text)
        size = len(strMatch)
        # print "size: ",size
        for i in range(0,size,1):
            one = strMatch[i]
            newurl = GetConcatUrl(css[1],one)
            DownloadFile(newurl,css[2])
    except Exception,e:
            pass
            # exstr = traceback.format_exc()
            # print exstr 

def Download(url,output):
    # try:
    header={"User-Agent": "Mozilla-Firefox5.0"}
    namespace = "{http://www.w3.org/1999/xhtml}"
    request = urllib2.Request(url,None,header)
    response = urllib2.urlopen(request)

    data = http://www.mamicode.com/response.read()>