爪巴虫 1.0版

无聊之中，写了一个爪巴虫
如你所见，这是一条不称职的爪巴虫
无奈，实力有限，时间有限，精力有限，只能写到这种程度了。
不过也算是我写的第一条爪巴虫
好歹可以算我python已经入门了，对伐，呵呵~

貌似效率好低，试了几次，把自己的电脑差点弄挂掉了~

待进一步完善中。。。。

import urllibtry:    from urllib.request import urlopenexcept ImportError:    from urllib2 import urlopenimport osimport sysfrom copy import deepcopyfrom string import replace;#judge if repeat?def Judge(dirname):    lenn=len(repeat);    for i in range(0,lenn):        if repeat[i]==dirname:            return True;    repeat.append(deepcopy(dirname));    return False;#不带参数，规范dirnamedef Change(dirname):    lenn=len(dirname);    g=lenn;    for i in range(0,lenn):        if dirname[i]=='?':            g=int(i)            break;    ans = dirname[0:g];    return ans;    #输入网址def getURL():    global URL;    URL=raw_input("enter the URL(no '/' end!!):");    #URL="http://blog.sina.com.cn";    curUrl=deepcopy(URL);    #输入保存路径def getPath():    global Path;    Path=raw_input("enter the path(no '\\' end):");    #Path="F:\\test"    os.chdir(Path);#if startwithdef startwith(test1,test2):    len1=len(test1);    len2=len(test2);    lenn=min(len1,len2);    for i in range(0,lenn):        if test1[i]!=test2[i]:            return False;    return True;#得到路径def getHref(text):    lent=len(text)    #print text[0:5];    for i in range(0,lent-5):        if text[i:i+5]=='href=':            if text[i+5]!='"' and text[i+5]!="'":                dirname=text[i+5];            else:                dirname="";            for j in range(i+6,lent):                if text[j]=='"' or text[j]=="'" or text[j]=='>':                    break;                else:                    dirname=dirname+text[j];            getNewUrl(dirname);            i=j;#得到新的路径def getNewUrl(dirname):    if Judge(dirname):        return False;    if startwith(dirname,"http://"):        if not startwith(dirname,URL):            return False;        dirname=dirname[len(URL):len(dirname)];    dirname=Change(dirname);    if not startwith(dirname,"/") and not startwith(dirname,"../") or dirname[1:]=="":        return False;    else:       prePath=dirname.split('/');       lenn=len(prePath[-1]);       for i in range(0,lenn):           if prePath[-1][i]=='.':               #print '\\'.join(prePath[0:-1:1]);               createPath('\\'.join(prePath[0:-1:1]));               curUrl=URL+dirname;               getCon(URL+dirname,prePath[-1]);               os.chdir(Path);               return False;       createPath('\\'.join(prePath));       #print URL+dirname;       getCon(URL+dirname);#写入文件def loadFile(Url,filename):    f=open(filename,'w');    data=urlopen(Url);    f.write(data.read());    f.close();    #创建路径def createPath(path):    if path == '':        return False;    else:        #print path;        pp=path.split('\\');        curP=deepcopy(Path);        for i in pp:            if i=="":                os.chdir(Path);                return False;            if not os.path.exists(curP+"\\"+i):                 os.mkdir(curP+"\\"+i);            else:                os.chdir(curP+"\\"+i);            curP=curP+"\\"+i;        os.chdir(curP);        #得到内容def getCon(Url,filename='index.html'):    #print Url;    try:        url=urlopen(Url);    except:        print "IOError";        return ;    loadFile(Url,filename);    while True:        data=url.readline();        if data=="":            break;        getHref(data);def unit():    global curUrl;    global repeat;    global Path;    global URL;    URL="";    repeat=list();        if __name__=='__main__':    unit();    getURL();    getPath();    getCon(URL);    print "robot finish the work now!!!";