Heim >Backend-Entwicklung >PHP-Tutorial >还是关于PHP的二进制流问题
还是关于PHP的二进制流问题
- WBOYOriginal
- 2016-06-23 13:35:411222Durchsuche
之前发了一帖: http://bbs.csdn.net/topics/391024843
版主给了回答,也能够解析出来,但却发现出来的结果与真实结果完全不一样,比如服务器返回给我的是: ip: 107.145.107.140, port: 26773
但我解析出来却变成了: ip: 46.48.46.48, port: 63271
这样就差的远了, 我用PHP去获取nodes信息,然后将nodes信息自己解析输出一遍,顺便把未解析数据发送给pthon解析一遍,然后两边对比,发现结果却不一样
PHP(使用了swoole):
<?php$serv = new swoole_server('0.0.0.0', 6882, SWOOLE_PROCESS, SWOOLE_SOCK_UDP);$serv->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); // 由于每个node都为26位, 若总长度不等于26的倍数则直接返回 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()
回复讨论(解决方案)
你把执行 decode_nodes($msg) 时的 $msg 用
echo base64_encode($msg);
输出出来看看
这个不是base64编码,而是类似于:
未编码: {"t":"aa", "y":"r", "r":{"id":"0123456789abcdefghij", "nodes":"def456..."}}
编码后:d1:rd2:id20:0123456789abcdefghij5:nodes9:def456...e1:t2:aa1:y1:re
这样的格式
而其中的nodeid、ip、port就是其中的nodes里的
你把执行 decode_nodes($msg) 时的 $msg 用
echo base64_encode($msg);
输出出来看看
这里有份DHT协议说明: http://blog.csdn.net/xxxxxx91116/article/details/7970815
我又不做这个，没兴趣看协议文本
我给你的解码格式是小端序的，如果你的数据是大端序的，那么就查一下 pack 函数说明，换一下
如果你想让我帮你检查，那么就请按我说的去做
4楼版主说的对，检查大小端序的问题。
或者用tcpdump实际的二进制数据是什么样的。
现在已经能够正确获取IP地址，但是端口依然无解，也的确是使用大端序，但PHP只有这几种格式，每个都试过，就是不正确，郁闷了。。。
那有什么办法呢？让你贴出数据你又不肯，只能这样了
啊，没有不肯啊，是这样的：
比如服务器发了一段数据过来，ip是：188.19.238.146，端口是：6881，然后我截取端口位的2字节数据为：?
接着就是解码，将网络字节序转换为端口号：unpack("n", $port)，但是转换出来却变成了57763，用unpack("s", $port)变成了-23583，用unpack("S", $port)变成了41953
让你把你收到的数据用 base64_encode 编码后给我，怎么就那么难呢？
让你把你收到的数据用 base64_encode 编码后给我，怎么就那么难呢？
抱歉，是这样的数据：
ZDE6cmQyOmlkMjA6daCpq0ZCdc6JP5An4ac4g4tlvPg1Om5vZGVzNDE2Oj4jyz4WVIOIxzAe2MXW4TWcH8dddZ6SRDktJ+7silGRA0YlQqlqucmPix2E6MZCvQ2ZY90lCzORZu5ZytoyWpBtKzh4PVNLMrz+Vo4exiqGYEUq3sV501VNWQ5XcqsXfXftr47cYrvZHsF4DCDFWnMcgC2Aq/DHVz00Wbxfm9qPqlsdaJ4um4dXnVtZ6BLCGgy42Pw3zVOnROrqVgpFb1J5g+BAxB2NOUMBBW7FQCyycNBojCpaDATl59Ekq4HpaHqD1gW057xisIRLgEp9f9VZvdr60s6C3CBNCX/OvoTfeJyY40k3SdswZ1lTimGVQRb7T7/VTO1rgXkZFTpuvAYbPCJaWUpbXcILoZh8A8H/qzKyirIM0v8lycJgFFdeiZR7bq+aPmxHVL1Scc6M3YMH17kiA8lK3l06cqN65EvX3/CuWJ4uw+fDhqSjVCkrwlpdQYO8k8mjkZhdVAaHCBUDxw9ESlvAXxuYGuFHYq2GV1BOhSYgmPJSaOzkghl0kq9lCiQvWUhr/ewsm/X/90CEXsTS45jet3HqWuZ2KcjVZTE6dDI6e8cxOnkxOnJl
python 中有
n = [] length = len(nodes) if(length % 26) != 0: return n而你给的数据（解码后）长度是 474
模 26 为 6
请确认你给的数据是正确的
python 中有
n = [] length = len(nodes) if(length % 26) != 0: return n而你给的数据（解码后）长度是 474
模 26 为 6
请确认你给的数据是正确的
哦，抱歉，是这样的，刚才给出的是获取到的原始数据，而之后那里 % 26那个是通过bencode解码后的nodes数据，不好意思，忘了把这份数据也弄出来。。。
这份是原始数据，包含了获取到的所有，比如：y = r 之类的
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
这份是通过bencode解码后的nodes数据，也就是在这个数据中分成每份26字节，从26字节中取出20字节的nid，4字节的ip，2字节的端口：
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
$s = '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';$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<?Æ rU<D¢4Îí½” [ip] => 177.183.234.200 [p] => 8080)Array( [n] => ?ü#î5<?Æ rU<D¢4Îí½” [ip] => 177.183.234.200 [p] => 8080)Array( [n] => ?ü#î5<?Æ rU<D¢4Îí½” [ip] => 177.183.234.200 [p] => 8080)Array( [n] => ?ÿLè§î(á<iå¾D’íH;Pv [ip] => 101.204.70.62 [p] => 6881)Array( [n] => ?ÿLè§î(á<iå¾D’íH;Pv [ip] => 101.204.70.62 [p] => 6881)Array( [n] => ?ÿLè§î(á<iå¾D’íH;Pv [ip] => 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)应该是没有问题的
$s = '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';$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<?Æ rU<D¢4Îí½” [ip] => 177.183.234.200 [p] => 8080)Array( [n] => ?ü#î5<?Æ rU<D¢4Îí½” [ip] => 177.183.234.200 [p] => 8080)Array( [n] => ?ü#î5<?Æ rU<D¢4Îí½” [ip] => 177.183.234.200 [p] => 8080)Array( [n] => ?ÿLè§î(á<iå¾D’íH;Pv [ip] => 101.204.70.62 [p] => 6881)Array( [n] => ?ÿLè§î(á<iå¾D’íH;Pv [ip] => 101.204.70.62 [p] => 6881)Array( [n] => ?ÿLè§î(á<iå¾D’íH;Pv [ip] => 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)应该是没有问题的
非常非常感谢，看来是我一开始截取的时候就截取错了，所以获取到的结果才会不对，真的太感谢了！
Stellungnahme：
Der Inhalt dieses Artikels wird freiwillig von Internetnutzern beigesteuert und das Urheberrecht liegt beim ursprünglichen Autor. Diese Website übernimmt keine entsprechende rechtliche Verantwortung. Wenn Sie Inhalte finden, bei denen der Verdacht eines Plagiats oder einer Rechtsverletzung besteht, wenden Sie sich bitte an admin@php.cn
Vorheriger Artikel：在Mac下配置php开发环境：Apache+php+MySqlNächster Artikel：小白，请指点以下程序怎么不是循环输出的，而且输出的中文还是乱码
In Verbindung stehende Artikel
Mehr sehen- So verwenden Sie cURL zum Implementieren von Get- und Post-Anfragen in PHP
- So verwenden Sie cURL zum Implementieren von Get- und Post-Anfragen in PHP
- So verwenden Sie cURL zum Implementieren von Get- und Post-Anfragen in PHP
- So verwenden Sie cURL zum Implementieren von Get- und Post-Anfragen in PHP
- Alle Ausdruckssymbole in regulären Ausdrücken (Zusammenfassung)