Python – 擷取校內(人人網)的所有好友照片儲存到本地

涉及內容包括：

0.POST DATA到校內網

1.Regex

2.urllib2的使用

3.Cache機制

[TODO]

1.SMTP的使用：自動發郵件到指定郵箱

2.SQLITE的使用：把圖片儲存到資料庫

有問題或者建議，歡迎聯絡：lihe21327@gmail.com

注意要更改Login的帳號和密碼。

只貼代碼：

#coding=utf-8from urllib import urlencodefrom time import sleepfrom random import randintimport sqlite3,cookielib,time,re,osimport urllib2,shutiladd_num = 0class RenrenRobot:    def __init__(self):        print '*********************************'        print '*Hi,This is Hark\'s Robot For RR*'        print '*********************************'        print 'Contact With me: lihe21327@gmail.com'        print 'Version: 0.1'        print ''        self.allCount = 0        self.newCount = 0        #Create Dir        self.strSpiderBasePath = r'c:\leehark_spider'                if os.path.exists(self.strSpiderBasePath) == False:            os.mkdir(self.strSpiderBasePath)            def Download(self,id):        # Fetching Your Friend's Recent Updated Pictures' URL whose id is '@param = id'        self.strBaseFilePath = (r'c:\leehark_spider\id_%s' % id)        if os.path.exists(self.strBaseFilePath) == False:            os.mkdir(self.strBaseFilePath)        strFriendURL = ('http://photo.renren.com/photo/%s/album/relatives' % id)        res = urllib2.urlopen(strFriendURL)        print res.geturl()        print res.getcode()        print res.info()        str = res.read()                strPattern = r'<li>.<a href="(http://photo.renren.com/photo/[^<>]*?)" class="picture">'        r = re.findall(strPattern,str,re.S|re.I)        if r == None:            return        fout = open('c:\\spider\\tmp.txt','wb')        for item in r:            photoURL = item            print 'Picture\'s URL: ' , photoURL            ret = urllib2.urlopen(photoURL)            strPicURLContent = ret.read()            strPicPattern = r'<img id="photo" src="(http://.*?)" title=".*?" style=".*?">'            rPic = re.findall(strPicPattern,strPicURLContent,re.S|re.I)            for subItem in rPic:                self.allCount+=1                # Construct FilePath                strItem = subItem.replace('/','_')                strItem = strItem.replace(':','_')                strItem = strItem.replace('&','_')                strItem = strItem.replace('\\','_')                strFilePath = self.strBaseFilePath+'\\'+strItem                                if os.path.exists(strFilePath):                    # Hit the Old one                    print 'Fetched Already : ',subItem                    continue                # This is New Image,Fetch it                self.newCount+=1                print 'Fetching New Image :'                print subItem,' --> ',strFilePath                ret = urllib2.urlopen(subItem)                # Get Image Size                headers = ret.info().headers                length = 0                for header in headers:                    if header.find('Length') != -1:                        length = header.split(':')[-1].strip()                        length = int(length)                print 'Image length = ',length                # Copy Content To Disk                fd = open(strFilePath, 'wb')                 shutil.copyfileobj(ret,fd,0x10000)                 fd.close()                 ret.close()                # Do not overload download                time.sleep(1)                    def WalkFriends(self):        strFriendURL=r"http://friend.renren.com/myfriendlistx.do"        try:            res = urllib2.urlopen(strFriendURL)        except :            print '******',"visit MY FRIEND LIST *",'BIG ERROR ******'        else:            strFriendURLContent = res.read()            #print strFriendURLContent            strFriendPattern = r'{"id":([0-9]*?),"vip":'            rFriend = re.findall(strFriendPattern,strFriendURLContent,re.S|re.I)            for subItem in rFriend:                print 'Fetching : ',subItem                self.Download(subItem)                    def Login(self,username,pwd):        # Set Cookie Jar        cookie = cookielib.CookieJar()        cookie_file = urllib2.HTTPCookieProcessor(cookie)        opener = urllib2.build_opener(cookie_file)        urllib2.install_opener(opener)        # Construct Post Data        data = {            'email':username,            'password':pwd,            'origURL':'',            'domain':'renren.com',            'formName':'',            'method':'',            'isplogin':'true',            'submit':'登陸'            }        web_data = urlencode(data)        print 'web_data : ',web_data        header = {'User-Agent':'Mozilla/5.0 (Windows NT 5.1; rv:6.0.2) Gecko/20100101 Firefox/6.0.2'}        req=urllib2.Request(url='http://www.renren.com/PLogin.do',                    data = web_data,                    headers = header)        try:            result = urllib2.urlopen(req)        except :            print '******',username,'BIG ERROR ******'            return        else:            print result.geturl()            print result.getcode()            print result.info()            print 'Go to YOURPAGE'            self.WalkFriends()        print 'Picture Count : ',self.allCount        print 'New Count : ',self.newCount                        def main():    robot = RenrenRobot()    robot.Login('lihe21327@hotmail.com','******')if __name__ == '__main__':    main()