基于PHP的百度云网盘搜索引擎PHP版源码.zip

# -*- coding: utf-8 -*- import urllib2,re,argparse,json,time import MySQLdb as mdb import metautils,traceback,Queue,socket DB_HOST='127.0.0.1' DB_PORT='3306' DB_USER='root' # MySQL密码 DB_PASS='' # 数据库名称 DB_NAME='pan' SPIDER_INTERVAL=1 ERR_NO=0#正常 ERR_REFUSE=1#爬虫爬取速度过快，被拒绝 ERR_EX=2#未知错误 def getHtml(url,ref=None,reget=5): try: request = urllib2.Request(url) request.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36') if ref: request.add_header('Referer',ref) page = urllib2.urlopen(request,timeout=10) html = page.read() except: if reget>=1: #如果getHtml失败，则再次尝试5次 print 'getHtml error,reget...%d'%(6-reget) time.sleep(2) return getHtml(url,ref,reget-1) else: print 'request url:'+url print 'failed to fetch html' exit() else: return html class Db(object): def __init__(self): self.dbconn=None self.dbcurr=None def check_conn(self): try: self.dbconn.ping() except: return False else: return True def conn(self): self.dbconn=mdb.connect(DB_HOST, DB_USER, DB_PASS,DB_NAME, charset='utf8') self.dbconn.autocommit(False) self.dbcurr = self.dbconn.cursor() def fetchone(self): return self.dbcurr.fetchone() def fetchall(self): return self.dbcurr.fetchall() def execute(self, sql, args=None,falg=False): if not self.dbconn: #第一次链接数据库 self.conn() try: if args: rs=self.dbcurr.execute(sql,args) else: rs=self.dbcurr.execute(sql) return rs except Exception, e: if self.check_conn(): print 'execute error' traceback.print_exc() else: print 'reconnect mysql' self.conn() if args: rs=self.dbcurr.execute(sql,args) else: rs=self.dbcurr.execute(sql) return rs def commit(self): self.dbconn.commit() def rollback(self): self.dbconn.rollback() def close(self): self.dbconn.close() self.dbcurr.close() def last_row_id(self): return self.dbcurr.lastrowid class BaiduPanSpider(object): def __init__(self): self.db=Db() self.files=[] self.got_files_count=0 self.got_follow_count=0 self.while_count=0 self.spider_queue=Queue.Queue(maxsize=20) self.status='stop' self.errno=ERR_NO self.file_type_t={'video':0,'image':1,'document':2,'music':3,'package':4,'software':5,'torrent':6,'other':-1} def getShareUser(self,uk): url='http://yun.baidu.com/share/count?uk=%d&channel=chunlei&clienttype=0&web=1'%uk follows_json=json.loads(getHtml(url,uk)) if follows_json['errno']!=0: if follows_json['errno']==-55: self.errno=ERR_REFUSE else: self.errno=ERR_EX return False return { 'pubshare_cnt':follows_json['pubshare_cnt'], 'fans':follows_json['fans'], 'follow':follows_json['follow'], 'album':follows_json['follows_json'] } def getHotUser(self): url='http://yun.baidu.com/pcloud/friend/gethotuserlist?type=1&from=feed&start=0&limit=24&channel=chunlei&clienttype=0&web=1' follows_json=json.loads(getHtml(url)) if follows_json['errno']!=0: print u'failed to fetch hot users' return False returns=[] count=0 for item in follows_json['hotuser_list']: count=count+1 hot_uname=item['hot_uname'].encode('utf-8') hot_uk=item['hot_uk'] avatar_url=item['avatar_url'].encode('utf-8') intro=item['intro'].encode('utf-8') follow_count=item['follow_count'] fans_count=item['fans_count'] pubshare_count=item['pubshare_count'] album_count=item['album_count'] returns.append({'hot_uname':hot_uname,'hot_uk':hot_uk,'avatar_url':avatar_url,'intro':intro,'follow_count':follow_count,'fans_count':fans_count,'pubshare_count':pubshare_count,'album_count':album_count}) if count==0: print "got no hot users" return False else: print "success to fetched hot users: %d"%count return returns def getFans(self,uk,start=0,limit=24): #query_uk:用户ID #limit:每一页最多显示数量 #start:当前页数 follows_url='http://yun.baidu.com/pcloud/friend/getfanslist?query_uk=%d&limit=%d&start=%d'%(uk,limit,start) follows_json=json.loads(getHtml(follows_url,uk)) if follows_json['errno']!=0: print u'failed to fetch fens' return False total_count=follows_json['total_count'] returns=[] count=0 for item in follows_json['fans_list']: count=count+1 fans_uname=item['fans_uname'].encode('utf-8') fans_uk=item['fans_uk'] avatar_url=item['avatar_url'].encode('utf-8') intro=item['intro'].encode('utf-8') follow_count=item['follow_count'] fans_count=item['fans_count'] pubshare_count=item['pubshare_count'] album_count=item['album_count'] returns.append({'fans_uname':fans_uname,'fans_uk':fans_uk,'avatar_url':avatar_url,'intro':intro,'follow_count':follow_count,'fans_count':fans_count,'pubshare_count':pubshare_count,'album_count':album_count}) return (total_count,count,returns) def getFollows(self,uk,start=0,limit=24): follows_url='http://yun.baidu.com/pcloud/friend/getfollowlist?query_uk=%d&limit=%d&start=%d&bdstoken=d82467db8b1f5741daf1d965d1509181&channel=chunlei&clienttype=0&web=1'%(uk,limit,start) ref='http://yun.baidu.com/pcloud/friendpage?type=follow&uk=%d&self=1'%uk follows_json=json.loads(getHtml(follows_url,ref)) if follows_json['errno']!=0: print 'getFollows errno:%d'%follows_json['errno'] print 'request_url:'+follows_url if follows_json['errno']==-55: self.errno=ERR_REFUSE else: self.errno=ERR_EX return False total_count=follows_json['total_count'] returns=[] count=0 if(total_count>0): for item in follows_json['follow_list']: count=count+1 returns.append({ 'follow_uname':item['follow_uname'].encode('utf-8'), 'follow_uk':item['follow_uk'], 'avatar_url':item['avatar_url'].encode('utf-8'), 'intro':item['intro'].encode('utf-8'), 'follow_count':item['follow_count'], 'fans_count':item['fans_count'], 'pubshare_count':item['pubshare_count'], 'album_count':item['album_count'] }) return (total_count,count,returns) def getShareLists(self,uk,start=0,limit=60): sharelists_url='http://yun.baidu.com/pcloud/feed/getsharelist?category=0&auth_type=1&request_location=share_home&start=%d&limit=%d&query_uk=%d&channel=chunlei&clienttype=0&web=1'%(start,limit,uk) ref='http://yun.baidu.com/share/home?uk=%d&view=share'%uk sharelists_json=json.loads(getHtml(sharelists_url,ref)) if(sharelists_json['errno']!=0): print 'getShareLists errno:%d'%sharelists_json['errno'] print 'request_url:'+sharelists_url if sharelists_json['errno']==-55: self.errno=ERR_REFUSE else: self.errno=ERR_EX return False total_count=sharelists_json['total_count'] returns=[] count=0 if total_count>0: for item in sharelists_json['records']: count=count+1 feed_type=item['feed_type'] isdir=0 size=0 md5='' album_id='' shorturl='' if feed_type=='share': if item['filecount']==1: filelist=item['filelist'] isdir=filelist[0]['isdir'] size=filelist[0]['size'] md5=filelist[0]['md5'] else: isdir=1 elif feed_type=='album': album_id=item['album_id'] isdir=2 if item.has_key('shorturl'): shorturl=item['shorturl'] if feed_type=='share' or feed_type=='album': returns.append({ 'title':item['title'].encode('utf-8'), 'shorturl':shorturl, 'shareid':item['source_id'], 'feed_time':item['feed_time']//1000,#分享时间 'dCnt':item['dCnt'], 'isdir':isdir, 'size':size, 'md5':md5, 'uk':uk, 'feed_type':feed_type }) return (total_count,count,returns) def getAlbum(self,uk,start=0,limit=60): url='http://yun.baidu.com/pcloud/album/getlist?start=%d&limit=%d&query_uk=%d&channel=chunlei&clienttype=0&web=1&bdstoken=d82467db8b1f5741daf1d965d1509181'%(start,limit,uk) album_json=json.loa