python爬虫之爬取百度网盘

爬虫之爬取百度网盘（python）

#coding: utf8"""author:haoningcreate time: 2015-8-15"""importre#正则表达式模块importurllib2#获取URLs的组件importtimefromQueueimportQueueimportthreading, errno, datetimeimportjsonimportrequests#Requests is an Apache2 Licensed HTTP libraryimportMySQLdb as mdbDB_HOST ='127.0.0.1'DB_USER ='root'DB_PASS =''#以下是正则匹配规则re_start = re.compile(r'start=(\d+)')#\d 表示0-9 任意一个数字 后面有+号 说明这个0-9单个数位出现一到多次 比如21312314re_uid = re.compile(r'query_uk=(\d+)')#查询编号re_urlid = re.compile(r'&urlid=(\d+)')#url编号ONEPAGE =20#一页数据量ONESHAREPAGE =20#一页分享连接量#缺少专辑列表URL_SHARE ='http://yun.baidu.com/pcloud/feed/getsharelist?auth_type=1&start={start}&limit=20&query_uk={uk}&urlid={id}'#获得分享列表"""{"feed_type":"share","category":6,"public":"1","shareid":"1541924625","data_id":"2418757107690953697","title":"\u5723\u8bde\u58c1\u7eb8\u5927\u6d3e\u9001","third":0,"clienttype":0,"filecount":1,"uk":1798788396,"username":"SONYcity03","feed_time":1418986714000,"desc":"","avatar_url":"http:\/\/himg.bdimg.com\/sys\/portrait\/item\/1b6bf333.jpg","dir_cnt":1,"filelist":[{"server_filename":"\u5723\u8bde\u58c1\u7eb8\u5927\u6d3e\u9001","category":6,"isdir":1,"size":1024,"fs_id":870907642649299,"path":"%2F%E5%9C%A3%E8%AF%9E%E5%A3%81%E7%BA%B8%E5%A4%A7%E6%B4%BE%E9%80%81","md5":"0","sign":"1221d7d56438970225926ad552423ff6a5d3dd33","time_stamp":1439542024}],"source_uid":"871590683","source_id":"1541924625","shorturl":"1dDndV6T","vCnt":34296,"dCnt":7527,"tCnt":5056,"like_status":0,"like_count":60,"comment_count":19},public:公开分享title:文件名称uk:用户编号"""URL_FOLLOW ='http://yun.baidu.com/pcloud/friend/getfollowlist?query_uk={uk}&limit=20&start={start}&urlid={id}'#获得订阅列表"""{"type":-1,"follow_uname":"\u597d\u55e8\u597d\u55e8\u554a","avatar_url":"http:\/\/himg.bdimg.com\/sys\/portrait\/item\/979b832f.jpg","intro":"\u9700\u8981\u597d\u8d44\u6599\u52a0994798392","user_type":0,"is_vip":0,"follow_count":2,"fans_count":2276,"follow_time":1415614418,"pubshare_count":36,"follow_uk":2603342172,"album_count":0},follow_uname:订阅名称fans_count：粉丝数"""URL_FANS ='http://yun.baidu.com/pcloud/friend/getfanslist?query_uk={uk}&limit=20&start={start}&urlid={id}'# 获取关注列表"""{"type":-1,"fans_uname":"\u62e8\u52a8\u795e\u7684\u5fc3\u7eea","avatar_url":"http:\/\/himg.bdimg.com\/sys\/portrait\/item\/d5119a2b.jpg","intro":"","user_type":0,"is_vip":0,"follow_count":8,"fans_count":39,"follow_time":1439541512,"pubshare_count":15,"fans_uk":288332613,"album_count":0}avatar_url：头像fans_uname：用户名"""QNUM =1000hc_q = Queue(20)#请求队列hc_r = Queue(QNUM)#接收队列success =0failed =0defreq_worker(inx):#请求s = requests.Session()#请求对象whileTrue:req_item = hc_q.get()#获得请求项req_type = req_item[0]#请求类型，分享?订阅？粉丝？url = req_item[1]#urlr = s.get(url)#通过url获得数据hc_r.put((r.text, url))#将获得数据文本和url放入接收队列print"req_worker#", inx, url #inx 线程编号； url 分析了的 urldefresponse_worker():#处理工作dbconn = mdb.connect(DB_HOST, DB_USER, DB_PASS,'baiduyun', charset='utf8')dbcurr = dbconn.cursor()dbcurr.execute('SET NAMES utf8')dbcurr.execute('set global wait_timeout=60000')#以上皆是数据库操作whileTrue:"""#正则备注match() 决定 RE 是否在字符串刚开始的位置匹配search() 扫描字符串，找到这个 RE 匹配的位置findall() 找到 RE 匹配的所有子串，并把它们作为一个列表返回finditer() 找到 RE 匹配的所有子串，并把它们作为一个迭代器返回百度页面链接：http://pan.baidu.com/share/link?shareid=3685432306&uk=1798788396&from=hotrecuk 其实用户id值"""metadata, effective_url = hc_r.get()#获得metadata（也就是前面的r.text）和有效的url#print "response_worker:", effective_urltry:tnow = int(time.time())#获得当前时间id = re_urlid.findall(effective_url)[0]#获得re_urlid用户编号start = re_start.findall(effective_url)[0]#获得start用户编号ifTrue:if'getfollowlist'ineffective_url:#type = 1，也就是订阅类follows = json.loads(metadata)#以将文本数据转化成json数据格式返回uid = re_uid.findall(effective_url)[0]#获得re_uid，查询编号if"total_count"infollows.keys()andfollows["total_count"]>0andstr(start) =="0":#获得订阅数量foriinrange((follows["total_count"]-1)/ONEPAGE):#开始一页一页获取有用信息try:dbcurr.execute('INSERT INTO urlids(uk, start, limited, type, status) VALUES(%s, %s, %s, 1, 0)'% (uid, str(ONEPAGE*(i+1)), str(ONEPAGE)))#存储url编号，订阅中有用户编号，start表示从多少条数据开始获取，初始status=0为未分析状态exceptException as ex:print"E1", str(ex)passif"follow_list"infollows.keys():#如果订阅者也订阅了，即拥有follow_listforiteminfollows["follow_list"]:try:dbcurr.execute('INSERT INTO user(userid, username, files, status, downloaded, lastaccess) VALUES(%s, "%s", 0, 0, 0, %s)'% (item['follow_uk'], item['follow_uname'], str(tnow)))#存储订阅这的用户编号，用户名，入库时间exceptException as ex:print"E13", str(ex)passelse:print"delete 1", uid, startdbcurr.execute('delete from urlids where uk=%s and type=1 and start>%s'% (uid, start))elif'getfanslist'ineffective_url:#type = 2,也就是粉丝列表fans = json.loads(metadata)uid = re_uid.findall(effective_url)[0]if"total_count"infans.keys()andfans["total_count"]>0andstr(start) =="0":foriinrange((fans["total_count"]-1)/ONEPAGE):try:dbcurr.execute('INSERT INTO urlids(uk, start, limited, type, status) VALUES(%s, %s, %s, 2, 0)'% (uid, str(ONEPAGE*(i+1)), str(ONEPAGE)))exceptException as ex:print"E2", str(ex)passif"fans_list"infans.keys():foriteminfans["fans_list"]:try:dbcurr.execute('INSERT INTO user(userid, username, files, status, downloaded, lastaccess) VALUES(%s, "%s", 0, 0, 0, %s)'% (item['fans_uk'], item['fans_uname'], str(tnow)))exceptException as ex:print"E23", str(ex)passelse:print"delete 2", uid, startdbcurr.execute('delete from urlids where uk=%s and type=2 and start>%s'% (uid, start))else:#type=0，也即是分享列表shares = json.loads(metadata)uid = re_uid.findall(effective_url)[0]if"total_count"inshares.keys()andshares["total_count"]>0andstr(start) =="0":foriinrange((shares["total_count"]-1)/ONESHAREPAGE):try:dbcurr.execute('INSERT INTO urlids(uk, start, limited, type, status) VALUES(%s, %s, %s, 0, 0)'% (uid, str(ONESHAREPAGE*(i+1)), str(ONESHAREPAGE)))exceptException as ex:print"E3", str(ex)passif"records"inshares.keys():foriteminshares["records"]:try:dbcurr.execute('INSERT INTO share(userid, filename, shareid, status) VALUES(%s, "%s", %s, 0)'% (uid, item['title'], item['shareid']))#item['title']恰好是文件名称#返回的json信息：exceptException as ex:#print "E33", str(ex), itempasselse:print"delete 0", uid, startdbcurr.execute('delete from urlids where uk=%s and type=0 and start>%s'% (uid, str(start)))dbcurr.execute('delete from urlids where id=%s'% (id, ))dbconn.commit()exceptException as ex:print"E5", str(ex), iddbcurr.close()dbconn.close()#关闭数据库defworker():globalsuccess, faileddbconn = mdb.connect(DB_HOST, DB_USER, DB_PASS,'baiduyun', charset='utf8')dbcurr = dbconn.cursor()dbcurr.execute('SET NAMES utf8')dbcurr.execute('set global wait_timeout=60000')#以上是数据库相关设置whileTrue:#dbcurr.execute('select * from urlids where status=0 order by type limit 1')dbcurr.execute('select * from urlids where status=0 and type>0 limit 1')#type>0,为非分享列表d = dbcurr.fetchall()#每次取出一条数据出来#print difd:#如果数据存在id = d[0][0]#请求url编号uk = d[0][1]#用户编号start = d[0][2]limit = d[0][3]type = d[0][4]#哪种类型dbcurr.execute('update urlids set status=1 where id=%s'% (str(id),))#状态更新为1，已经访问过了url = ""iftype ==0:#分享url = URL_SHARE.format(uk=uk, start=start, id=id).encode('utf-8')#分享列表格式化#query_uk uk 查询编号#start#urlid id url编号eliftype ==1:#订阅url = URL_FOLLOW.format(uk=uk, start=start, id=id).encode('utf-8')#订阅列表格式化eliftype ==2:#粉丝url = URL_FANS.format(uk=uk, start=start, id=id).encode('utf-8')#关注列表格式化ifurl:hc_q.put((type, url))#如果url存在，则放入请求队列，type表示从哪里获得数据#通过以上的url就可以获得相应情况下的数据的json数据格式，如分享信息的，订阅信息的，粉丝信息的#print "processed", urlelse:#否则从订阅者或者粉丝的引出人中获得信息来存储，这个过程是爬虫树的下一层扩展dbcurr.execute('select * from user where status=0 limit 1000')d = dbcurr.fetchall()ifd:foritemind:try:dbcurr.execute('insert into urlids(uk, start, limited, type, status) values("%s", 0, %s, 0, 0)'% (item[1], str(ONESHAREPAGE)))#uk 查询号，其实是用户编号#start 从第1条数据出发获取信息#dbcurr.execute('insert into urlids(uk, start, limited, type, status) values("%s", 0, %s, 1, 0)'% (item[1], str(ONEPAGE)))dbcurr.execute('insert into urlids(uk, start, limited, type, status) values("%s", 0, %s, 2, 0)'% (item[1], str(ONEPAGE)))dbcurr.execute('update user set status=1 where userid=%s'% (item[1],))#做个标志，该条数据已经访问过了#跟新了分享，订阅，粉丝三部分数据exceptException as ex:print"E6", str(ex)else:time.sleep(1)dbconn.commit()dbcurr.close()dbconn.close()defmain():print'starting at:',now()foriteminrange(16):t = threading.Thread(target = req_worker, args = (item,))t.setDaemon(True)t.start()#请求线程开启，共开启16个线程s = threading.Thread(target = worker, args = ())s.setDaemon(True)s.start()#worker线程开启response_worker()#response_worker开始工作print'all Done at:', now()