python获取QQ空间前100篇blog的地址和标题的方法

python获取QQ空间前100篇blog的地址和标题的方法

相关地址均由firebug获得，本来想把QQ空间的日志全部下载下来，可是目前只能获取前100篇的文章，先发出个半成品

代码:
#! /usr/bin/env python  
#coding=utf-8  
import urllib2,urllib, os
from HTMLParser import HTMLParser

QQnum=1026239701
loginurl=http://g.cnc.qzone.qq.com/fcg-bin/cgi_emotion_list.fcg?uin=+QQnum+&loginUin=0&s=414636&num=3&g_tk=5381
blogurl=http://br.cnc.qzone.qq.com/cgi-bin/blognew/blog_output_toppage?uin=+QQnum+&vuin=0&property=GoRE&getall=1&styledm=cnc.qzonestyle.gtimg.cn&imgdm=

cnc.qzs.qq.com&bdm=b.cnc.qzone.qq.com&cate=&numperpage=100&maxlen=68&sorttype=0&pos=0&direct=1
blogpreurl=http://user.qzone.qq.com/+QQnum+/blog/

#返回页面
def visitUrl(url): 
    html=
    fd=urllib2.urlopen(url)
    html=fd.read()
    if html !=:
        fd.close()
        return html
#写入文件
def write2file(data1, data2):
    fp=open(blogtitlelist.txt, a)
    for eachline in data1:
        fp.write(eachline)
        fp.write( )
    fp.close()
       
#下载网页
def downloadurl(url, filename):
    downloadFolder = ./QQspacedown #指定保存网页的文件夹
    if not os.path.isdir( downloadFolder ):
        os.mkdir( downloadFolder )
    downfilename=downloadFolder+/+filename+.html
    op=open(downfilename, wb)
   
    fd=urllib2.urlopen(url)
    html=fd.read()
    if html !=:
        op.write(html)
        fd.close()
        op.close()
        return True
    fd.close()
    op.close()
    return False
#处理html
class Parser(HTMLParser):  
    def __init__(self):  
        self.targets={}
        self.is_span=
        HTMLParser.__init__(self)  
    def handle_starttag(self, tag, attrs):  
        if tag==span:
            for name, value in attrs:
                if name==id:
                    if value.startswith(blogtitle_):
                        self.is_span=1
                        index=value.find(_)
                        self.id=value[index+1:]
    def handle_endtag(self, tag):
        if tag==span:
            self.is_span=
    def handle_data(self, data):
        if self.is_span:
            self.targets[self.id]=data.strip()
    def getTargets(self):  
        return self.targets
if __name__==__main__:
    map={}
    titlelist=[]
    urllist=[]
    data=visitUrl(blogurl)
    myparser=Parser()
    myparser.feed(data)
    map=myparser.getTargets()
    for key, value in map.items():
        titlelist.append(value)
        urllist.append(blogpreurl+key)
    print urllist
    write2file(titlelist)
    print finished