之前發了一帖: http://bbs.csdn.net/topics/391024843
版主給了回答,也能夠解析出來,但卻發現出來的結果與真實結果完全不一樣,比如伺服器返回給我的是: ip: 107.145.107.140, port: 26773
但我解析出來卻變成了: ip: 46.48.46.48, port: 63271
這樣就差的遠了, 我用PHP去擷取nodes資訊,然後將nodes資訊自己解析輸出一遍,順便把未解析資料發送給pthon解析一遍,然後兩邊對比,發現結果卻不一樣
PHP(使用了swoole):
set(array( 'worker_num' => WORKER_NUM, 'daemonize' => false, 'max_request' => MAX_REQUEST, 'dispatch_mode' => 2, 'debug_mode' => 1));$serv->on('Start', function($serv){ echo "DHT Server start...\n"; $nid = get_node_id(); $msg = array( 't' => entropy(2), 'y' => 'q', 'q' => 'find_node', 'a' => array( 'id' => $nid, 'target' => $nid ) ); $serv->sendto(gethostbyname('router.bittorrent.com'), 6881, encode($msg));});$serv->on('Receive', function($serv, $fd, $from_id, $data){ echo "New receive from ip: "; $msg = decode($data); $fdinfo = $serv->connection_info($fd); echo $fdinfo['remote_ip'] . "\n"; if($msg['y'] == 'r'){ if(array_key_exists('nodes', $msg['r'])) //$this->response_actions($msg, array($fdinfo['remote_ip'], $fdinfo['remote_port'])); $nodes = decode_nodes($msg['r']['nodes']); foreach($nodes as $node){ echo "nid: " . $node->nid . ", ip: " . $node->ip . ", port: " . $node->port . "\n"; } $serv->sendto('127.0.0.1', 6813, $data); }});function entropy($length=20){ $s = ''; for($i=0;$i<$length;$i++) $s .= chr(mt_rand(0, 255)); return $s; }function get_node_id(){ return sha1(entropy()); }function get_neighbor($target, $nid){ return substr($target, 0, 10) . substr($nid, 0, -10); }function encode($msg){ return Bencode::encode($msg); }function decode($msg){ return Bencode::decode($msg); }function decode_nodes($msg){ $n = array(); $length = strlen($msg); // 由於每個node都為26位, 若總長度不等於26的倍數則直接返回 if(($length % 26) != 0) return $n; $i = 0; while($i<$length){ //$s = substr($msg, $i, 26); //$d = unpack('a20nid/Lip/Sport', $s); //var_dump($d); //$d = unpack('a20nid/lip/sport', $s); //var_dump($d); //$n[] = new Node($d['nid'], long2ip($d['ip']), $d['port']); $nid = substr($msg, $i, 20); var_dump($nid); $ip = substr($msg, $i+20, 4); var_dump($ip); $ip = long2ip(unpack('L', $ip)[1]); $port = substr($msg, $i+24, 2); var_dump($port); $port = unpack('s', $port)[1]; var_dump($port); //$n[] = new Node($nid, $ip, $port); $i += 26; } return $n; }$serv->start();
python:
#!/usr/bin/env python#encoding: utf-8import socketfrom hashlib import sha1from random import randintfrom struct import unpackfrom socket import inet_ntoafrom threading import Timer, Threadfrom time import sleepfrom collections import dequefrom bencode import bencode, bdecodedef decode_nodes(nodes): n = [] length = len(nodes) if(length % 26) != 0: return n for i in range(0, length, 26): nid = nodes[i:i+20] ip = inet_ntoa(nodes[i+20:i+24]) ip2 = nodes[i+20:i+24] print ip2 port = unpack("!H", nodes[i+24:i+26])[0] port2 = nodes[i+24:i+26] print port2 print "decode_nodes: nid: %s, ip: %s, port: %s\n" % (nid, ip, port)class DHTServer(): def __init__(self): self.ufd = socket.socket(socket.AF_INET, socket.SOCK_DGRAM, socket.IPPROTO_UDP) self.ufd.bind(("0.0.0.0", 6813)) def process_find_node_response(self, msg, address): nodes = decode_nodes(msg["r"]["nodes"]) for node in nodes: (nid, ip, port) = node print "find_node: nid: %s, ip: %s, port: %s\n" % (nid, ip, port) def run(self): while True: try: (data, address) = self.ufd.recvfrom(65536) msg = bdecode(data) self.on_message(msg, address) except Exception: pass def on_message(self, msg, address): try: if msg["y"] == "r": if msg["r"].has_key("nodes"): self.process_find_node_response(msg, address) except KeyError: passif __name__ == "__main__": # max_node_qsize bigger, bandwith bigger, spped higher dht = DHTServer() dht.run()
回複討論(解決方案)
你把執行 decode_nodes($msg) 時的 $msg 用
echo base64_encode($msg);
輸出出來看看
這個不是base64編碼,而是類似於:
未編碼: {"t":"aa", "y":"r", "r":{"id":"0123456789abcdefghij", "nodes":"def456..."}}
編碼後:d1:rd2:id20:0123456789abcdefghij5:nodes9:def456...e1:t2:aa1:y1:re
這樣的格式
而其中的nodeid、ip、port就是其中的nodes裡的
你把執行 decode_nodes($msg) 時的 $msg 用
echo base64_encode($msg);
輸出出來看看
這裡有份DHT協議說明: http://blog.csdn.net/xxxxxx91116/article/details/7970815
我又不做這個,沒興趣看協議文本
我給你的解碼格式是小端序的,如果你的資料是大端序的,那麼就查一下 pack 函數說明,換一下
如果你想讓我幫你檢查,那麼就請按我說的去做
4樓版主說的對,檢查大小端序的問題。
或者用tcpdump實際的位元據是什麼樣的。
現在已經能夠正確擷取IP地址,但是連接埠依然無解,也的確是使用大端序,但PHP只有這幾種格式,每個都試過,就是不正確,鬱悶了。。。
那有什麼辦法呢?讓你貼出資料你又不肯,只能這樣了
啊,沒有不肯啊,是這樣的:
比如伺服器發了一段資料過來,ip是:188.19.238.146,連接埠是:6881,然後我截取連接埠位的2位元組資料為:?
接著就是解碼,將網路位元組序轉換為連接埠號碼:unpack("n", $port),但是轉換出來卻變成了57763,用unpack("s", $port)變成了-23583,用unpack("S", $port)變成了41953
讓你把你收到的資料用 base64_encode 編碼後給我,怎麼就那麼難呢?
讓你把你收到的資料用 base64_encode 編碼後給我,怎麼就那麼難呢?
抱歉,是這樣的資料:
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
python 中有
n = [] length = len(nodes) if(length % 26) != 0: return n
而你給的資料(解碼後)長度是 474
模 26 為 6
請確認你給的資料是正確的
python 中有
n = [] length = len(nodes) if(length % 26) != 0: return n
而你給的資料(解碼後)長度是 474
模 26 為 6
請確認你給的資料是正確的
哦,抱歉,是這樣的,剛才給出的是擷取到的未經處理資料,而之後那裡 % 26那個是通過bencode解碼後的nodes資料,不好意思,忘了把這份資料也弄出來。。。
這份是未經處理資料,包含了擷取到的所有,比如:y = r 之類的
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
這份是通過bencode解碼後的nodes資料,也就是在這個資料中分成每份26位元組,從26位元組中取出20位元組的nid,4位元組的ip,2位元組的連接埠:
P9LI9UagRY0oDfVScSnuyKZHmjRO68KLdlc/0sj1RqBFjSgN9VJxKe7IpkeaNE7rwot2Vz/SyPVGoEWNKA31UnEp7simR5o0TuvCi3ZXP/wj7jU8hMYdclU8RKIZNM7tvZSxt+rIH5A//CPuNTyExh1yVTxEohk0zu29lLG36sgfkD/8I+41PITGHXJVPESiGTTO7b2UsbfqyB+QP/9M6KfuKOE8aeW+E0SS7Ug7UHZlzEY+GuE//0zop+4o4Txp5b4TRJLtSDtQdmXMRj4a4T//TOin7ijhPGnlvhNEku1IO1B2ZcxGPhrhPk6NAzs25ZjxFKrQJrZEjbfkAhg8GYaAGuE+To0DOzblmPEUqtAmtkSNt+QCGDwZhoAa4T5OjQM7NuWY8RSq0Ca2RI235AIYPBmGgBrhPs9ltmz/1Jul2AA0wRDx0d4e2AFR4CzD2+A+z2W2bP/Um6XYADTBEPHR3h7YAVHgLMPb4D7PZbZs/9SbpdgANMEQ8dHeHtgBUeAsw9vgPajAE2YlZG+/uqPNCgQzuP6WjQ7fpv0NGuE=
$s = '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';$s = base64_decode($s);foreach(str_split($s, 26) as $s) { $r = unpack('a20n/Nip/np', $s); $r['ip'] = long2ip($r['ip']); print_r($r);}
Array( [n] => ?ÒÈõF E?(õRq)îȦG?4 [ip] => 78.235.194.139 [p] => 30295)Array( [n] => ?ÒÈõF E?(õRq)îȦG?4 [ip] => 78.235.194.139 [p] => 30295)Array( [n] => ?ÒÈõF E?(õRq)îȦG?4 [ip] => 78.235.194.139 [p] => 30295)Array( [n] => ?ü#î5 177.183.234.200 [p] => 8080)Array( [n] => ?ü#î5 177.183.234.200 [p] => 8080)Array( [n] => ?ü#î5 177.183.234.200 [p] => 8080)Array( [n] => ?ÿLè§î(á 101.204.70.62 [p] => 6881)Array( [n] => ?ÿLè§î(á 101.204.70.62 [p] => 6881)Array( [n] => ?ÿLè§î(á 101.204.70.62 [p] => 6881)Array( [n] => >N?;6å?ñª?&¶D?·ä [ip] => 60.25.134.128 [p] => 6881)Array( [n] => >N?;6å?ñª?&¶D?·ä [ip] => 60.25.134.128 [p] => 6881)Array( [n] => >N?;6å?ñª?&¶D?·ä [ip] => 60.25.134.128 [p] => 6881)Array( [n] => >Ïe¶lÿÔ?¥Ø4ÁñÑ?Ø [ip] => 81.224.44.195 [p] => 56288)Array( [n] => >Ïe¶lÿÔ?¥Ø4ÁñÑ?Ø [ip] => 81.224.44.195 [p] => 56288)Array( [n] => >Ïe¶lÿÔ?¥Ø4ÁñÑ?Ø [ip] => 81.224.44.195 [p] => 56288)Array( [n] => =¨Àf%do¿º£Í3¸??? [ip] => 223.166.253.13 [p] => 6881)
應該是沒有問題的
$s = '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';$s = base64_decode($s);foreach(str_split($s, 26) as $s) { $r = unpack('a20n/Nip/np', $s); $r['ip'] = long2ip($r['ip']); print_r($r);}
Array( [n] => ?ÒÈõF E?(õRq)îȦG?4 [ip] => 78.235.194.139 [p] => 30295)Array( [n] => ?ÒÈõF E?(õRq)îȦG?4 [ip] => 78.235.194.139 [p] => 30295)Array( [n] => ?ÒÈõF E?(õRq)îȦG?4 [ip] => 78.235.194.139 [p] => 30295)Array( [n] => ?ü#î5 177.183.234.200 [p] => 8080)Array( [n] => ?ü#î5 177.183.234.200 [p] => 8080)Array( [n] => ?ü#î5 177.183.234.200 [p] => 8080)Array( [n] => ?ÿLè§î(á 101.204.70.62 [p] => 6881)Array( [n] => ?ÿLè§î(á 101.204.70.62 [p] => 6881)Array( [n] => ?ÿLè§î(á 101.204.70.62 [p] => 6881)Array( [n] => >N?;6å?ñª?&¶D?·ä [ip] => 60.25.134.128 [p] => 6881)Array( [n] => >N?;6å?ñª?&¶D?·ä [ip] => 60.25.134.128 [p] => 6881)Array( [n] => >N?;6å?ñª?&¶D?·ä [ip] => 60.25.134.128 [p] => 6881)Array( [n] => >Ïe¶lÿÔ?¥Ø4ÁñÑ?Ø [ip] => 81.224.44.195 [p] => 56288)Array( [n] => >Ïe¶lÿÔ?¥Ø4ÁñÑ?Ø [ip] => 81.224.44.195 [p] => 56288)Array( [n] => >Ïe¶lÿÔ?¥Ø4ÁñÑ?Ø [ip] => 81.224.44.195 [p] => 56288)Array( [n] => =¨Àf%do¿º£Í3¸??? [ip] => 223.166.253.13 [p] => 6881)
應該是沒有問題的
非常非常感謝,看來是我一開始截取的時候就截取錯了,所以擷取到的結果才會不對,真的太感謝了!