{"id":1523,"date":"2018-07-16T20:18:37","date_gmt":"2018-07-16T12:18:37","guid":{"rendered":"https:\/\/damogame.cn:15443\/wordpress\/?p=1523"},"modified":"2018-07-16T20:18:37","modified_gmt":"2018-07-16T12:18:37","slug":"dht%e7%88%ac%e8%99%ab%ef%bc%9a18-4gb%e7%a7%8d%e5%ad%90%e5%88%86%e6%9e%90%e5%b0%8f%e8%ae%b0","status":"publish","type":"post","link":"https:\/\/i007.cc\/wordpress\/archives\/1523","title":{"rendered":"DHT\u722c\u866b\uff1a18.4GB\u79cd\u5b50\u5206\u6790\u5c0f\u8bb0"},"content":{"rendered":"<div class=\"title clearfix\">\n<h2>DHT\u722c\u866b\uff1a18.4GB\u79cd\u5b50\u5206\u6790\u5c0f\u8bb0<\/h2>\n<div class=\"property\"><span class=\"name\"><a title=\"\u7531 zrools \u53d1\u5e03\" href=\"http:\/\/www.freebuf.com\/author\/zrools\" rel=\"author\">zrools<\/a><\/span><span class=\"time\">2016-04-11<\/span><span class=\"rmb\"><img decoding=\"async\" title=\"\u73b0\u91d1\u5956\u52b1\" src=\"http:\/\/image.3001.net\/images\/new\/icon-m.jpg\" \/><\/span><span class=\"look\">\u5171<strong>1127915<\/strong>\u4eba\u56f4\u89c2 \uff0c\u53d1\u73b0\u00a0<strong>23<\/strong>\u00a0\u4e2a\u4e0d\u660e\u7269\u4f53<\/span><span class=\"tags\"><a href=\"http:\/\/www.freebuf.com\/articles\/database\">\u6570\u636e\u5b89\u5168<\/a><\/span><\/div>\n<\/div>\n<div id=\"contenttxt\">\n<h3><strong>\u672c\u6587\u539f\u521b\u4f5c\u8005\uff1azrools<\/strong><\/h3>\n<h2><a class=\"highslide-image\" href=\"http:\/\/image.3001.net\/images\/20160408\/14601042777151.png\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" src=\"http:\/\/image.3001.net\/images\/20160408\/14601042777151.png!small\" alt=\"unnamed.png\" width=\"640\" data-original=\"http:\/\/image.3001.net\/images\/20160408\/14601042777151.png!small\" \/><\/a><\/h2>\n<h2>0\u00d700 \u524d\u8a00<\/h2>\n<p><b>\u66fe\u7ecf\u6709\u79cd\u5b50\u5e1d\u8bf4\u8fc7\uff1a\u5982\u679c\u4f60\u6709\u4e00\u4e2a\u65e0\u804a\u7684\u60f3\u6cd5\uff0c\u90a3\u4e48\u5c31\u5728\u65e0\u804a\u7684\u65f6\u5019\u53bb\u5b9e\u73b0\u5b83\u5427\u3002<\/b><\/p>\n<p>\u8d77\u521d\u662f\u60f3\u62ff\u7f51\u4e0a\u6d41\u4f20\u6d77\u76d7\u6e7e\u90a3\u6279\u79cd\u5b50\u4f5c\u5206\u6790\uff0c\u540e\u6765\u60f3\u6765\u70b9\u201c\u65b0\u9c9c\u7684\u201d\u770b\u770b\u5468\u672b\u5927\u5bb6\u90fd\u5728\u4e0b\u4e9b\u5565\uff1b\u5f00\u59cb\u53ea\u662f\u5355\u7eaf\u7684\u60f3\u6293\u70b9\u4fe1\u606f\uff0c\u53d1\u73b0announce_peer\u8bf7\u6c42\u8fc7\u6765\u7684name\u5e76\u4e0d\u5168\uff0c\u53c8\u5f00\u59cb\u6574\u4e0b\u8f7d\u79cd\u5b50\uff0c\u540e\u6765\u5e72\u8106\u628a\u79cd\u5b50\u4fe1\u606f\u5bfc\u8fdb\u6570\u636e\u5e93\uff08\u57fa\u672c\u53ef\u4ee5\u505a\u4e00\u4e2a\u7b80\u5355\u7684BT\u641c\u7d22\u4e86\uff09\u3002<\/p>\n<p>\u56e0\u4e3a\u5177\u6709\u65f6\u6548\u6027\uff0c3\u5929\u6536\u96c6\u7684\u4fe1\u606f\u5e76\u4e0d\u5b8c\u5168\u5177\u6709\u4ee3\u8868\u6027\u3002<\/p>\n<h2>0\u00d701 \u76f8\u5173\u672f\u8bed<\/h2>\n<h3>1.1 P2P\u7f51\u7edc<\/h3>\n<p>\u5bf9\u7b49\u8ba1\u7b97\uff08Peer to Peer\uff0c\u7b80\u79f0p2p\uff09\u53ef\u4ee5\u7b80\u5355\u7684\u5b9a\u4e49\u6210\u901a\u8fc7\u76f4\u63a5\u4ea4\u6362\u6765\u5171\u4eab\u8ba1\u7b97\u673a\u8d44\u6e90\u548c\u670d\u52a1\uff0c\u800c\u5bf9\u7b49\u8ba1\u7b97\u6a21\u578b\u5e94\u7528\u5c42\u5f62\u6210\u7684\u7f51\u7edc\u901a\u5e38\u79f0\u4e3a\u5bf9\u7b49\u7f51\u7edc\u3002\u76f8\u4fe1\u5927\u5bb6\u90fd\u7528\u8fc7\u8fc5\u96f7\uff0c\u5c31\u4e0d\u591a\u8bf4\u4e86\u3002<\/p>\n<h3>1.2 DHT\u7f51\u7edc<\/h3>\n<p>DHT\uff08Distributed Hash Table\uff0c\u5206\u5e03\u5f0f\u54c8\u5e0c\u8868\uff09\uff0cDHT\u7531\u8282\u70b9\u7ec4\u6210\uff0c\u5b83\u5b58\u50a8peer\u7684\u4f4d\u7f6e\uff0c\u662f\u4e00\u79cd\u5206\u5e03\u5f0f\u5b58\u50a8\u65b9\u6cd5\u3002\u5728\u4e0d\u9700\u8981\u670d\u52a1\u5668\u7684\u60c5\u51b5\u4e0b\uff0c\u6bcf\u4e2a\u5ba2\u6237\u7aef\u8d1f\u8d23\u4e00\u4e2a\u5c0f\u8303\u56f4\u7684\u8def\u7531\uff0c\u5e76\u8d1f\u8d23\u5b58\u50a8\u4e00\u5c0f\u90e8\u5206\u6570\u636e\uff0c\u4ece\u800c\u5b9e\u73b0\u6574\u4e2aDHT\u7f51\u7edc\u7684\u5bfb\u5740\u548c\u5b58\u50a8\uff0c\u5176\u4e2dBT\u5ba2\u6237\u7aef\u5305\u542b\u4e00\u4e2aDHT\u8282\u70b9\uff0c\u7528\u6765\u8054\u7cfbDHT\u4e2d\u5176\u4ed6\u8282\u70b9\uff0c\u4ece\u800c\u5f97\u5230peer\u7684\u4f4d\u7f6e\uff0c\u8fdb\u800c\u901a\u8fc7BitTorrent\u534f\u8bae\u4e0b\u8f7d\u3002<\/p>\n<p>\u7b80\u5355\u6765\u8bf4DHT\u5c31\u662f\u8d1f\u8d23\u7ba1\u7406\u63d0\u4f9b\u4fe1\u606f\u548c\u670d\u52a1\u8282\u70b9\u7684\u7ba1\u7406\u4e0e\u8def\u7531\u529f\u80fd\uff0c\u4e24\u4e2a\u9700\u8981\u533a\u5206\u7684\u6982\u5ff5\uff1a<\/p>\n<p>\u201cpeer\u201d \u662f\u5728\u4e00\u4e2a TCP \u7aef\u53e3\u4e0a\u76d1\u542c\u7684\u5ba2\u6237\u7aef\/\u670d\u52a1\u5668\uff0c\u5b83\u5b9e\u73b0\u4e86 BitTorrent \u534f\u8bae\u3002<\/p>\n<p>\u201c\u8282\u70b9\u201d \u662f\u5728\u4e00\u4e2a UDP \u7aef\u53e3\u4e0a\u76d1\u542c\u7684\u5ba2\u6237\u7aef\/\u670d\u52a1\u5668\uff0c\u5b83\u5b9e\u73b0\u4e86 DHT(\u5206\u5e03\u5f0f\u54c8\u5e0c\u8868) \u534f\u8bae\u3002<\/p>\n<h3>1.3 Kademlia\u7b97\u6cd5<\/h3>\n<p>Kademlia\u662fDHT\u7f51\u7edc\u7684\u4e00\u79cd\u5b9e\u73b0\u3002\u5728Kademlia\u7f51\u7edc\u4e2d\uff0c\u8ddd\u79bb\u662f\u901a\u8fc7\u5f02\u6216(XOR)\u8ba1\u7b97\u7684\uff0c\u7ed3\u679c\u4e3a\u65e0\u7b26\u53f7\u6574\u6570\u3002distance(A, B) = |A xor B|\uff0c\u503c\u8d8a\u5c0f\u8868\u793a\u8d8a\u8fd1\u3002<\/p>\n<h3>1.4 KRPC\u534f\u8bae<\/h3>\n<p>KRPC \u662f\u8282\u70b9\u4e4b\u95f4\u7684\u4ea4\u4e92\u534f\u8bae\uff0c\u662f\u7531 bencode \u7f16\u7801\u7ec4\u6210\u7684\u4e00\u4e2a\u7b80\u5355\u7684 RPC \u7ed3\u6784\uff0c\u4ed6\u4f7f\u7528 UDP \u62a5\u6587\u53d1\u9001\u3002\u4e00\u4e2a\u72ec\u7acb\u7684\u8bf7\u6c42\u5305\u88ab\u53d1\u51fa\u53bb\u7136\u540e\u4e00\u4e2a\u72ec\u7acb\u7684\u5305\u88ab\u56de\u590d\u3002\u8fd9\u4e2a\u534f\u8bae\u6ca1\u6709\u91cd\u53d1\u3002\u5b83\u5305\u542b 3 \u79cd\u6d88\u606f\uff1a\u8bf7\u6c42\uff0c\u56de\u590d\u548c\u9519\u8bef\u3002\u5bf9DHT\u534f\u8bae\u800c\u8a00\uff0c\u8fd9\u91cc\u6709 4 \u79cd\u8bf7\u6c42\uff1a<\/p>\n<blockquote><p><b>ping<\/b>\u00a0\u68c0\u67e5\u4e00\u4e2a\u8282\u70b9\u662f\u5426\u6709\u6548<\/p>\n<p><b>find_node<\/b>\u00a0\u5411\u4e00\u4e2a\u8282\u70b9\u53d1\u9001\u67e5\u627e\u8282\u70b9\u7684\u8bf7\u6c42\uff0c\u5728\u521d\u59cb\u8def\u7531\u8868\u6216\u9a8c\u8bc1\u6876\u662f\u5426\u5b58\u6d3b\u65f6\u4f7f\u7528<\/p>\n<p><b>get_peers<\/b>\u00a0\u5411\u4e00\u4e2a\u8282\u70b9\u53d1\u9001\u67e5\u627e\u8d44\u6e90\u7684\u8bf7\u6c42<\/p>\n<p><b>announce_peer<\/b>\u00a0\u5411\u4e00\u4e2a\u8282\u70b9\u53d1\u9001\u81ea\u5df1\u5df2\u7ecf\u5f00\u59cb\u4e0b\u8f7d\u67d0\u4e2a\u8d44\u6e90\u7684\u901a\u77e5<\/p><\/blockquote>\n<p>\u4e00\u6761KRPC\u6d88\u606f\u7531\u4e00\u4e2a\u72ec\u7acb\u7684\u5b57\u5178\u7ec4\u6210\uff0c\u5176\u4e2d<b>t<\/b>\u548c<b>y<\/b>\u5173\u952e\u5b57\u662f\u6bcf\u6761\u4fe1\u606f\u90fd\u5305\u542b\u7684<\/p>\n<h3>1.5 MagNet\u534f\u8bae<\/h3>\n<p>MagNet\u534f\u8bae\uff0c\u4e5f\u5c31\u662f\u78c1\u529b\u94fe\u63a5\u3002\u662f\u4e00\u4e2a\u901a\u8fc7sha1\u7b97\u6cd5\u751f\u6210\u4e00\u4e2a20\u5b57\u8282\u957f\u7684\u5b57\u7b26\u4e32\uff0cP2P\u5ba2\u6237\u7aef\u4f7f\u7528\u78c1\u529b\u94fe\u63a5\uff0c\u4e0b\u8f7d\u8d44\u6e90\u7684\u79cd\u5b50\u6587\u4ef6\uff0c\u7136\u540e\u6839\u636e\u79cd\u5b50\u6587\u4ef6\u4e0b\u8f7d\u8d44\u6e90\u3002<\/p>\n<p>\u56e0\u5df2\u6709\u73b0\u6210\u7684\u811a\u672c\u5b9e\u73b0\uff0c\u53ea\u9700\u8981\u5bf9\u76f8\u5173\u534f\u8bae\u6709\u4e2a\u5927\u6982\u4e86\u89e3\u5c31\u53ef\u4ee5\u52a8\u624b\u4e86\u3002<\/p>\n<h2>0\u00d702 DHT\u722c\u866b<\/h2>\n<h3>2.1 \u5b9e\u73b0\u539f\u7406<\/h3>\n<p>\u4f2a\u88c5\u6210DHT\u8282\u70b9\u52a0\u5165DHT\u7f51\u7edc\u4e2d\u6536\u96c6\u4fe1\u606f\uff0cDHT\u4e2dnode\uff08\u52a0\u5165\u7f51\u7edc\u7684\u65f6\u5019\u968f\u673a\u751f\u6210\uff09\u4e0einfohash\u90fd\u662f\u4f7f\u7528160bit\u7684\u8868\u793a\u65b9\u5f0f\uff0c\u4e5f\u5c31\u662f40\u4f4d\u768416\u8fdb\u5236\uff0c\u610f\u5473\u7740\u6570\u91cf\u7ea7\u67092^160\uff0c\u722c\u866b\u4e3b\u8981\u6536\u96c6<b>get_peer<\/b>\u3001<b>announce_peer<\/b>\u8fd9\u4e24\u4e2a\u8bf7\u6c42\u7684\u4fe1\u606f<\/p>\n<h3>2.2 get_peer<\/h3>\n<p><b>get_peers<\/b>\u4e0etorrent\u6587\u4ef6\u7684infohash\u6709\u5173\uff0c\u627e\u5230\u5f85\u67e5\u8d44\u6e90\u662f\u5426\u6709<b>peer<\/b>\u3002\u8fd9\u65f6KPRC\u4e2d\u7684<b>q=get_peers<\/b>\uff0c\u5176\u4e2d\u5305\u542b\u8282\u70b9<b>id<\/b>\u548c<b>info_hash<\/b>\u4e24\u4e2a\u53c2\u6570\uff0c\u5982\u679c\u88ab\u8bf7\u6c42\u7684\u8282\u70b9\u6709\u5bf9\u5e94info_hash\u7684<b>peers<\/b>\uff0c\u5c06\u8fd4\u56de\u4e00\u4e2a\u5173\u952e\u5b57<b>values<\/b>\uff0c\u5982\u679c\u65e0\u5219\u8fd4\u56de\u5173\u952e\u5b57<b>nodes<\/b>\uff0c\u540c\u65f6\u4e5f\u8fd4\u56de\u4e00\u4e2a<b>token<\/b>\uff0c<b>token<\/b>\u5728<b>annouce_peer<\/b>\u4e2d\u9700\u8981\u643a\u5e26\u3002<\/p>\n<p>\u53c2\u6570\uff1a<\/p>\n<pre><code class=\"hljs json\">{\"<span class=\"hljs-attr\">id<\/span>\" : <span class=\"hljs-string\">\"&lt;querying nodes id&gt;\"<\/span>, \"<span class=\"hljs-attr\">info_hash<\/span>\" : <span class=\"hljs-string\">\"&lt;20-byte infohash of target torrent&gt;\"<\/span>}\r\n<\/code><\/pre>\n<p>\u56de\u590d\uff1a<\/p>\n<pre><code class=\"hljs json\">{\"<span class=\"hljs-attr\">id<\/span>\" : <span class=\"hljs-string\">\"&lt;queried nodes id&gt;\"<\/span>, \"<span class=\"hljs-attr\">token<\/span>\" :<span class=\"hljs-string\">\"&lt;opaque write token&gt;\"<\/span>, \"<span class=\"hljs-attr\">values<\/span>\" : [<span class=\"hljs-string\">\"&lt;peer 1 info string&gt;\"<\/span>, <span class=\"hljs-string\">\"&lt;peer 2 info string&gt;\"<\/span>]}\r\n<\/code><\/pre>\n<p>\u6216\u8005<\/p>\n<pre><code class=\"hljs json\">{\"<span class=\"hljs-attr\">id<\/span>\" : <span class=\"hljs-string\">\"&lt;queried nodes id&gt;\"<\/span>, \"<span class=\"hljs-attr\">token<\/span>\" :<span class=\"hljs-string\">\"&lt;opaque write token&gt;\"<\/span>, \"<span class=\"hljs-attr\">nodes<\/span>\" : <span class=\"hljs-string\">\"&lt;compact node info&gt;\"<\/span>}\r\n<\/code><\/pre>\n<p>\u8fd9\u91cc\u8fc7\u6765\u7684info_hash\u4e0d\u4e00\u5b9a\u662f\u6709\u771f\u5b9e\u5b58\u5728\u7684<\/p>\n<h3>2.3 announce_peer<\/h3>\n<p>\u8fd9\u4e2a\u8bf7\u6c42\u7528\u6765\u8868\u660e\u53d1\u51fa<b>announce_peer<\/b>\u8bf7\u6c42\u7684\u8282\u70b9\uff0c\u6b63\u5728\u67d0\u4e2a\u7aef\u53e3\u4e0b\u8f7dtorrent\u6587\u4ef6\u3002\u5305\u542b\u56db\u4e2a\u53c2\u6570<b>\u8bf7\u6c42\u8282\u70b9id<\/b>\u3001<b>info_hash<\/b>\u3001<b>\u6574\u578b\u7aef\u53e3port<\/b>\u548c<b>tonken<\/b>\uff0c\u6536\u5230\u8bf7\u6c42\u7684\u8282\u70b9\u68c0\u67e5\u8fd9\u4e2a<b>token<\/b>\uff0c\u5982\u679c\u76f8\u540c\uff0c\u5219\u8fd4\u56de\u8282\u70b9\u7684<b>IP<\/b>\u548c<b>port<\/b>\u7b49\u8054\u7cfb\u4fe1\u606f\u3002\u722c\u866b\u4e2d\u4e0d\u80fd\u76f4\u63a5\u7528<b>announce_peer<\/b>\uff0c\u5426\u5219\u5f88\u5bb9\u6613\u4ece\u4e0a\u4e0b\u6587\u4e2d\u5224\u65ad\u662f\u901a\u62a5\u865a\u5047\u8d44\u6e90\u800c\u88ab\u7981\u6389\u3002<\/p>\n<p>\u53c2\u6570\uff1a<\/p>\n<pre><code class=\"hljs json\">{\"<span class=\"hljs-attr\">id<\/span>\" : <span class=\"hljs-string\">\"&lt;querying nodes id&gt;\"<\/span>, \"<span class=\"hljs-attr\">implied_port<\/span>\": &lt;<span class=\"hljs-number\">0<\/span> or <span class=\"hljs-number\">1<\/span>&gt;, \"<span class=\"hljs-attr\">info_hash<\/span>\" : <span class=\"hljs-string\">\"&lt;20-byte infohash of target torrent&gt;\"<\/span>, \"<span class=\"hljs-attr\">port<\/span>\" : &lt;port number&gt;, \"<span class=\"hljs-attr\">token<\/span>\" : <span class=\"hljs-string\">\"&lt;opaque token&gt;\"<\/span>}\r\n<\/code><\/pre>\n<p>\u56de\u590d\uff1a<\/p>\n<pre><code class=\"hljs json\">{\"<span class=\"hljs-attr\">id<\/span>\" : <span class=\"hljs-string\">\"&lt;queried nodes id&gt;\"<\/span>}\r\n<\/code><\/pre>\n<p>\u8fd9\u91cc\u8fc7\u6765\u7684info_hash\u8868\u660e\u5df2\u7ecf\u6709\u5728\u4e0b\u8f7d\u4e86\uff0c\u5927\u90e8\u5206\u662f\u5b58\u5728\u7684\uff0c\u8fd9\u91cc\u4e3b\u8981\u6536\u96c6\u8fd9\u4e2a\u8bf7\u6c42\u7684\u4fe1\u606f<b>info_hash<\/b>\u3001<b>ip<\/b>\u3001<b>port<\/b>\u3001<b>name<\/b>\uff08name\u4e0d\u4e00\u5b9a\u6709\uff09<\/p>\n<p><b>ping<\/b>\u548c<b>find_node<\/b>\u548c\u62a5\u6587\u6848\u4f8b\u770b\u4e00\u4e0b\u5b98\u65b9\u6587\u6863\u6216\u6587\u7ae0\u540e\u7684\u53c2\u8003\u7ffb\u8bd1\u6587\u7ae0\uff0c\u6587\u6863\u5df2\u7ecf\u5199\u5f97\u5f88\u8be6\u7ec6\u4e86\uff1b\u4e86\u89e3\u4e86\u8fd9\u4e24\u4e2a\u8bf7\u6c42\uff0c\u57fa\u672c\u89e3\u51b3\u4fe1\u606f\u6536\u96c6\u7684\u95ee\u9898\u4e86\u3002<\/p>\n<h3>2.4 Python\u5b9e\u73b0<\/h3>\n<p>\u73b0\u5728\u7f51\u7edc\u4e0a\u51fa\u73b0\u7684\u6709\uff1a<\/p>\n<blockquote><p><a href=\"https:\/\/github.com\/0x0d\/dhtfck\" target=\"_blank\" rel=\"noopener\">dhtfck<\/a><\/p>\n<p><a href=\"https:\/\/github.com\/Fuck-You-GFW\/simDHT\" target=\"_blank\" rel=\"noopener\">simDHT<\/a><\/p>\n<p><a href=\"https:\/\/github.com\/blueskyz\/DHTCrawler\" target=\"_blank\" rel=\"noopener\">DHTCrawler<\/a><\/p>\n<p><a href=\"https:\/\/github.com\/NanYoMy\/DHT-woodworm\" target=\"_blank\" rel=\"noopener\">DHT-woodworm<\/a><\/p>\n<p>\u2026\u2026<\/p><\/blockquote>\n<p>\u4ee5\u4e0a\u662f\u57fa\u4e8ePython 2.x\u7248\u672c\u7684\uff0c\u5176\u4e2dDHTCrawler\u662f\u57fa\u4e8elibtorrent\u5e93\u5b9e\u73b0\uff0c\u56e0\u4e3a\u77ed\u65f6\u95f4\u5185\u9700\u8981\u6536\u96c6\u5927\u91cf\u79cd\u5b50\uff0c\u6211\u7684\u505a\u6cd5\u662f\u5148\u6536\u96c6\u5927\u91cfinfo_hash\uff0c\u7136\u540e\u76f4\u63a5\u4ece\u79cd\u5b50\u5e93\u4e0b\u8f7d\uff0c\u8fd9\u91cc\u8981\u7528\u5230\u4e00\u4e2a\u57fa\u4e8e\u5f02\u6b65\uff08Python 3.5\uff09\u7684DHT\u722c\u866b<b><a href=\"https:\/\/github.com\/whtsky\/maga\" target=\"_blank\" rel=\"noopener\">Maga<\/a><\/b><\/p>\n<pre><code class=\"hljs cpp\">Maga                      - A DHT crawler framework <span class=\"hljs-keyword\">using<\/span> asyncio.<\/code><\/pre>\n<p>\u53ef\u4ee5\u4f7f\u7528\u4ee5\u4e0b\u65b9\u6cd5\u5b89\u88c5<\/p>\n<pre><code class=\"hljs nginx\"><span class=\"hljs-attribute\">pip3<\/span> install maga\r\n<\/code><\/pre>\n<p>\u5982\u679c\u4f7f\u7528git\u4e0b\u8f7d\uff0c\u6e90\u7801\u91cc\u9762\u7684bencoder\u5e93\u9700\u8981\u4fee\u6539\u4e00\u4e0b\uff0c\u6bd4\u5982\u6539\u6210bcoding\uff0c\u4f7f\u7528<\/p>\n<pre><code class=\"hljs python\"><span class=\"hljs-keyword\">from<\/span> maga <span class=\"hljs-keyword\">import<\/span> Maga\r\n\r\nimport logging\r\nlogging.basicConfig(level=logging.INFO)\r\n\r\n<span class=\"hljs-class\"><span class=\"hljs-keyword\">class<\/span> <span class=\"hljs-title\">Crawler<\/span><span class=\"hljs-params\">(Maga)<\/span>:<\/span>\r\n    <span class=\"hljs-keyword\">async<\/span> <span class=\"hljs-function\"><span class=\"hljs-keyword\">def<\/span> <span class=\"hljs-title\">handler<\/span><span class=\"hljs-params\">(self, infohash)<\/span>:<\/span>\r\n        logging.info(infohash)\r\n\r\ncrawler = Crawler()\r\ncrawler.run(<span class=\"hljs-number\">6881<\/span>)\r\n<\/code><\/pre>\n<p>\u4f20\u8fc7\u6765\u7684info_hash\u662f<b>get_peers<\/b>\u548c<b>announce_peer<\/b>\u7684\uff0c\u6536\u96c6<b>announce_peer<\/b>\u7684\u9700\u8981\u4fee\u6539\u6e90\u7801\u8fc7\u6ee4\u4e00\u4e0b\u533a\u5206<\/p>\n<blockquote><p>\u6ce8\uff1a\u8fd9\u91cc\u9700\u8981\u516c\u7f51IP\uff08\u80fd\u8ba9\u5176\u4ed6DHT\u8282\u70b9\u8bbf\u95ee\u5230\u672c\u5730\u76d1\u542c\u7684\u7aef\u53e3\u5c31\u884c\uff09<\/p><\/blockquote>\n<h3>2.5 \u6570\u636e\u5b58\u50a8<\/h3>\n<p>\u6570\u636e\u5e93\u4f7f\u7528MySQL\uff0c\u8fde\u63a5\u4f7f\u7528aiomysql\uff08<a href=\"http:\/\/aiomysql.readthedocs.org\/en\/latest\/index.html\" target=\"_blank\" rel=\"noopener\">\u6587\u6863<\/a><b><\/b>\uff09\uff0c\u8003\u8651\u5230\u6570\u636e\u8868\u591a\uff0c\u6309hash\u9996\u5b57\u6bcd\u520616\u5f20\u8868\u5b58\u50a8\u5185\u5bb9\uff0c\u7c7b\u4f3c\u5982\u4e0b<\/p>\n<pre><code class=\"hljs css\"><span class=\"hljs-selector-tag\">announce_peer_0<\/span>\r\n<span class=\"hljs-selector-tag\">announce_peer_1<\/span>\r\n.....<span class=\"hljs-selector-class\">.<\/span>\r\n<span class=\"hljs-selector-class\">announce_peer_e<\/span>\r\n<span class=\"hljs-selector-class\">announce_peer_f<\/span>\r\n<\/code><\/pre>\n<h3>2.6 \u6536\u96c6\u7ed3\u679c<\/h3>\n<p>\u4e22\u5728\u963f\u91cc\u4e91ECS\uff081\u6838\u30011G\u3001100M\/s\uff09\u4e0a\u8dd1\u4e8666\u5c0f\u65f6\uff08\u4e00\u4e2a\u5468\u672b\uff09\uff0c\u6536\u96c6\u4fe1\u606f\u5982\u4e0b<\/p>\n<p><b>get_peers<\/b>\u8bf7\u6c42\u7684info_hash\u00a0<b>21,313,390<\/b>\u6761\u8bb0\u5f55\uff08\u4e0d\u91cd\u590d\uff09<br \/>\n<b>announce_peer<\/b>\u8bf7\u6c42\u7684info_hash\u00a0<b>849,355<\/b>\u6761\u8bb0\u5f55\uff08\u4e0d\u91cd\u590d\uff09<br \/>\n<b>get_peers<\/b>\u548c<b>announce_peer<\/b>\u8bf7\u6c42\u7684info_hash\u00a0<b>76,411,582<\/b>\u6761\u8bb0\u5f55\uff08\u542b\u91cd\u590d\uff09<\/p>\n<p>\u6570\u91cf\u5c11\u6709\u53ef\u80fd\u662f\u811a\u672c\u6ca1\u5199\u597d\u9020\u6210\u7684\uff0c\u4e5f\u53ef\u80fd\u88ab\u67d0\u4e9bDHT\u8282\u70b9pass\u6389\u4e86<\/p>\n<h2>0\u00d703 magnet &amp; torrent<\/h2>\n<p>\u6709\u4e86\u79cd\u5b50\u7684HASH\u8fd8\u5f97\u5c06\u5176\u201c\u8f6c\u6210\u201d\u79cd\u5b50\u624d\u884c\uff0c\u5927\u81f4\u6709\u4e24\u79cd\u5f62\u5f0f\uff0c\u4f7f\u7528\u534f\u8bae\u6536\u96c6\u548c\u76f4\u63a5\u5230\u76ee\u524d\u7f51\u4e0a\u516c\u5f00\u7684\u7f13\u5b58\u79cd\u5b50\u5e93\u4e0b\u8f7d<\/p>\n<h3>3.1 magnet\u8f6ctorrent<\/h3>\n<p><b>\u534f\u8bae\u5b9e\u73b0<\/b><\/p>\n<p>\u53ef\u4ee5\u4f7f\u7528libtorrent\u5e93\u5b9e\u73b0\uff0clibtorrent\u5e93\u662fp2p\u4e0b\u8f7d\u7684\u5ba2\u6237\u7aef\u5e93\uff0c\u6709\u4e30\u5bcc\u7684\u63a5\u53e3\uff0c\u5177\u4f53\u53ef\u4ee5\u53c2\u8003<b><a href=\"https:\/\/github.com\/blueskyz\/DHTCrawler\" target=\"_blank\" rel=\"noopener\">DHTCrawler<\/a><\/b>\u6216<b><a href=\"https:\/\/github.com\/danfolkes\/Magnet2Torrent\" target=\"_blank\" rel=\"noopener\">Magnet2Torrent<\/a><\/b><\/p>\n<p><b>\u79cd\u5b50\u5e93\u4e0b\u8f7d<\/b><\/p>\n<p>\u4e5f\u5c31\u662f\u5199web\u722c\u866b\u4e0b\u8f7d\u73b0\u6210\u7684\u79cd\u5b50\uff0c\u591a\u7ebf\u7a0b\u6216\u4f7f\u7528\u5f02\u6b65\uff0c\u8fd9\u4e2a\u770b\u4e2a\u4eba\u7231\u597d\u6574<\/p>\n<p>\u5199\u4e86\u4e2a\u811a\u672c\u53bb\u6293<a href=\"http:\/\/bt.box.n0808.com\/\">http:\/\/bt.box.n0808.com<\/a>\u4e0a\u7684\u7f13\u5b58\u79cd\u5b50\uff0c\u4e3a\u4e86\u63d0\u9ad8\u6548\u7387\uff0c\u4ec5\u4f7f\u7528<b>announce_peer<\/b>\u4e2d\u7684info_hash(<b>849,355<\/b>)\uff0c\u5f97\u5230<b>509,146<\/b>\u4e2a\u79cd\u5b50\uff0c\u5927\u5c0f<b>19,327,952<\/b>\uff08<b>18.4GB<\/b>\uff09<\/p>\n<p>\u4f7f\u7528\u5f02\u6b65\uff0c\u722c\u53bb\u7684\u65f6\u5019\u4e0d\u514d\u4f1a\u51fa\u73b0\u8fde\u63a5\u65ad\u6389\u7684\u60c5\u51b5\uff0c16\u5f20\u8868\u4e3a\u4e86\u4fdd\u6301100%\u5730\u5904\u7406\u6240\u6709\u4fe1\u606f\uff0c\u4f7f\u7528\u4e00\u4e2a\u5217\u8868\u548c\u4e00\u4e2a\u5faa\u73af\uff0c\u6bcf\u5f53\u4e00\u4e2a\u8868\u5df2\u5904\u7406\u5b8c\u5c31\u79fb\u9664\uff0c\u76f4\u5230\u7a7a\u9000\u51fa\u5faa\u73af\uff0c\u91c7\u96c6\u8fc7\u7a0b\u4e2d\u770b\u7f51\u7edc\u8d44\u6e90\u8c03\u6574\u540c\u65f6\u5904\u7406\u4efb\u52a1\u7684\u6570\u91cfmax_tasks<\/p>\n<pre><code class=\"hljs ruby\">table = list(<span class=\"hljs-string\">'0123456789abcdef'<\/span>)\r\n<span class=\"hljs-keyword\">while<\/span> len(table)&gt;<span class=\"hljs-number\">0<\/span><span class=\"hljs-symbol\">:<\/span>\r\n\u00a0\u00a0\u00a0 <span class=\"hljs-keyword\">for<\/span> t <span class=\"hljs-keyword\">in<\/span> <span class=\"hljs-symbol\">table:<\/span>\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 sql = <span class=\"hljs-string\">'select distinct info_hash from announce_peer_{} where status=0;'<\/span>.format(t)\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 hash_list = await <span class=\"hljs-keyword\">self<\/span>.find(sql)\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \u00a0\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 <span class=\"hljs-keyword\">if<\/span> len(hash_list)&gt;<span class=\"hljs-number\">0<\/span><span class=\"hljs-symbol\">:<\/span>\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 await asyncio.wait([<span class=\"hljs-keyword\">self<\/span>.hash_queue.put(i[<span class=\"hljs-number\">0<\/span>].upper()) <span class=\"hljs-keyword\">for<\/span> i <span class=\"hljs-keyword\">in<\/span> hash_list])\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 tasks = [asyncio.ensure_future(<span class=\"hljs-keyword\">self<\/span>.fetch_worker()) <span class=\"hljs-keyword\">for<\/span> <span class=\"hljs-number\">_<\/span> <span class=\"hljs-keyword\">in<\/span> range(<span class=\"hljs-keyword\">self<\/span>.max_tasks)]\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 await <span class=\"hljs-keyword\">self<\/span>.hash_queue.join()\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 <span class=\"hljs-keyword\">for<\/span> task <span class=\"hljs-keyword\">in<\/span> <span class=\"hljs-symbol\">tasks:<\/span>\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 task.cancel()\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 <span class=\"hljs-symbol\">else:<\/span>\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 table.remove(t)\r\n<\/code><\/pre>\n<p>\u7531\u4e8e\u5927\u91cf\u7684\u8bf7\u6c42\uff0c\u722c\u53bb\u8fc7\u7a0b\u4e2d\u6709\u53ef\u80fd\u4f1a\u51fa\u73b0\u50f5\u5c38\u8fde\u63a5\uff0c\u4e00\u76f4\u8fde\u7740\u53c8\u4e0d\u4e0b\u8f7d\uff0c\u4f7f\u7528\u8d85\u65f6\u628a\u5b83\u6254\u6389\uff0c\u4e0b\u4e00\u6b21\u5faa\u73af\u518d\u8fdb\u884c\u6293\u53d6\uff1b\u5728\u83b7\u53d6\u7ed3\u679c\u7684\u8fc7\u7a0b\u4e2d\u53ea\u8ba4200\u3001403\u3001404\u8fd9\u51e0\u79cd\u72b6\u6001\uff0c\u76f4\u63a5\u6254\u6389\uff0c\u4e0b\u4e00\u6b21\u5faa\u73af\u518d\u8fdb\u884c\u6293\u53d6<\/p>\n<pre><code class=\"hljs markdown\">try:\r\n\u00a0\u00a0\u00a0 with aiohttp.Timeout(300):\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 async with aiohttp.get(url) as response:\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 try:\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 assert response.status == 200\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 print('[<span class=\"hljs-string\">+<\/span>][<span class=\"hljs-symbol\">{}<\/span>]{}'.format(response.status, response.url))\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 return await response.read()\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 except:\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 if response.status==404:\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 await self.update(info_hash, 2)\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 elif response.status==403:\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 await self.update(info_hash, 3)\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 print('[<span class=\"hljs-string\">-<\/span>][<span class=\"hljs-symbol\">{}<\/span>]{}'.format(response.status, response.url))\r\nexcept:\r\n\u00a0\u00a0\u00a0 print('[<span class=\"hljs-string\">!<\/span>][<span class=\"hljs-symbol\">000<\/span>]{}'.format(url))\r\n<\/code><\/pre>\n<p>\u4fdd\u5b58\u79cd\u5b50\uff0c\u76f4\u63a5\u5199\u5165\u8fd4\u56de\u7684\u6570\u636e\u5c31\u53ef\u4ee5\u4e86<\/p>\n<pre><code class=\"hljs perl\">with <span class=\"hljs-keyword\">open<\/span>(<span class=\"hljs-string\">'.\/torrent\/{}.torrent'<\/span>.<span class=\"hljs-keyword\">format<\/span>(info_hash), <span class=\"hljs-string\">'wb'<\/span>) as f:\r\n\u00a0\u00a0\u00a0 f.<span class=\"hljs-keyword\">write<\/span>(torrent)\r\n<\/code><\/pre>\n<p>\u534f\u8bae\u89e3\u6790\u6536\u96c6\u76f8\u5bf9\u6bd4\u8f83\u6162\uff0c\u79cd\u5b50\u5e93\u4e0b\u8f7d\u6bd4\u8f83\u6709\u5c40\u9650\u6027<\/p>\n<h3>3.2 torrent\u89e3\u6790<\/h3>\n<p>\u4f7f\u7528libtorrent\u5e93\uff0c\u5b89\u88c5<\/p>\n<pre><code class=\"hljs nginx\"><span class=\"hljs-attribute\">apt<\/span> -y install python3-libtorrent\r\n<\/code><\/pre>\n<p>\u76f4\u63a5\u4f20\u5165\u79cd\u5b50\uff0c\u53ef\u4ee5\u89e3\u6790\u5f97\u5230\u79cd\u5b50\u540d\u79f0\u3001\u54c8\u5e0c\u503c\u3001\u5305\u542b\u7684\u6587\u4ef6\u53ca\u5927\u5c0f\u7b49\u4fe1\u606f<\/p>\n<pre><code class=\"hljs python\"><span class=\"hljs-keyword\">import<\/span> libtorrent <span class=\"hljs-keyword\">as<\/span> lt\r\n\r\ninfo = lt.torrent_info(<span class=\"hljs-string\">'test.torrent'<\/span>)\r\n\r\nname       = info.name()              <span class=\"hljs-comment\"># \u79cd\u5b50\u540d\u79f0<\/span>\r\n<span class=\"hljs-comment\">info_hash  = str(info.info_hash())    # \u79cd\u5b50hash\u503c<\/span>\r\n<span class=\"hljs-comment\">num_files  = info.num_files()         # \u79cd\u5b50\u5305\u542b\u7684\u6587\u4ef6\u6570\u91cf<\/span>\r\n<span class=\"hljs-comment\">total_size = info.total_size()        # \u79cd\u5b50\u5927\u5c0f<\/span>\r\n<\/code><\/pre>\n<p>\u9664\u4ee5\u4e0a\u4e4b\u5916\uff0c\u8fd8\u53ef\u4ee5\u83b7\u53d6\u79cd\u5b50\u7684<b>\u6ce8\u91ca<\/b>\u3001<b>trackers<\/b>\u7b49\u4fe1\u606f<\/p>\n<p>\u83b7\u53d6\u79cd\u5b50\u4e0b\u7684\u6587\u4ef6\u5217\u8868\u4fe1\u606f\uff0cpath\u662f\u76f8\u5bf9\u79cd\u5b50\u7684\u8def\u5f84\uff0csize\u662f\u8be5\u6587\u4ef6\u7684\u5927\u5c0f\uff08\u5355\u4f4d\u6bd4\u7279\uff09<\/p>\n<pre><code class=\"hljs css\"><span class=\"hljs-selector-tag\">for<\/span> <span class=\"hljs-selector-tag\">i<\/span> <span class=\"hljs-selector-tag\">in<\/span> <span class=\"hljs-selector-tag\">info<\/span><span class=\"hljs-selector-class\">.files<\/span>():\r\n\u00a0\u00a0\u00a0 <span class=\"hljs-selector-tag\">print<\/span>(<span class=\"hljs-selector-tag\">i<\/span><span class=\"hljs-selector-class\">.path<\/span><span class=\"hljs-selector-class\">.strip<\/span>(),<span class=\"hljs-selector-tag\">i<\/span><span class=\"hljs-selector-class\">.size<\/span>)\r\n<\/code><\/pre>\n<p>\u83b7\u53d6\u79cd\u5b50\u6587\u4ef6\u4e2d\u7684tracker\u4fe1\u606f\uff0c\u6709\u4e9b\u4f1a\u542b\u6709\u8be1\u5f02\u7684\u5b57\u7b26\u65e0\u6cd5\u6b63\u5e38\u83b7\u53d6\uff0c\u52a0\u4e2atry\u5ffd\u7565<\/p>\n<pre><code class=\"hljs python\"><span class=\"hljs-keyword\">for<\/span> i <span class=\"hljs-keyword\">in<\/span> info.trackers():\r\n\u00a0\u00a0\u00a0 <span class=\"hljs-keyword\">try<\/span>:\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 url = print(i.url.strip())\r\n\u00a0\u00a0\u00a0 <span class=\"hljs-keyword\">except<\/span>:\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 <span class=\"hljs-keyword\">continue<\/span>\r\n<\/code><\/pre>\n<p>\u4e3a\u4e86\u65b9\u4fbf\u5206\u79bb\u548c\u9632\u6b62\u4e2d\u65ad\uff0c\u811a\u672c\u76f4\u63a5\u5217\u51fatorrent\u76ee\u5f55\u4e0b\u7684\u6240\u6709\u79cd\u5b50\u6587\u4ef6\u653e\u5165\u96c6\u5408\uff0c\u6570\u636e\u5e93\u62bd\u51fa\u6240\u6709\u5df2\u89e3\u6790\u7684\u79cd\u5b50HASH\u653e\u5165\u96c6\u5408\uff0c\u6bcf\u6b21\u542f\u52a8\u53d6\u4e24\u96c6\u5408\u7684\u5dee<\/p>\n<pre><code class=\"hljs bash\">torr_<span class=\"hljs-built_in\">set<\/span> = <span class=\"hljs-built_in\">set<\/span>([t <span class=\"hljs-keyword\">for<\/span> t <span class=\"hljs-keyword\">in<\/span> os.listdir(TORRENT_DIR) <span class=\"hljs-keyword\">if<\/span> t.endswith(<span class=\"hljs-string\">'.torrent'<\/span>)])\r\n\r\ntask_list = list(torr_<span class=\"hljs-built_in\">set<\/span> - <span class=\"hljs-built_in\">hash<\/span>_<span class=\"hljs-built_in\">set<\/span>)  <span class=\"hljs-comment\"># hash_set \u4e3a\u6570\u636e\u5e93\u53d6\u51fa\u5df2\u7ecf\u89e3\u6790\u7684\u79cd\u5b50\u540d\u79f0\u96c6\u5408<\/span>\r\n<\/code><\/pre>\n<h3>3.3 \u6570\u636e\u5b58\u50a8<\/h3>\n<p>\u79cd\u5b50\u4fe1\u606f\u4e00\u5f20\u8868\uff0c\u6587\u4ef6\u5217\u8868\u6309HASH\u9996\u5b57\u6bcd\u520616\u5f20\u8868\uff0ctrackers\u4e00\u5f20\uff08\u521a\u5f00\u59cb\u4ee5\u4e3a\u4e00\u4e2a\u79cd\u5b50\u4e5f\u5c313\uff5e5\u6761\u4e0d\u4f1a\u5f88\u591a\u4e00\u5f20\u8868\u591f\u7528\uff0c\u540e\u6765\u53d1\u73b0\u6709\u5c06\u8fd1400W -_-!\uff09<\/p>\n<pre><code class=\"hljs css\"><span class=\"hljs-selector-tag\">torrent_info<\/span>\r\n<span class=\"hljs-selector-tag\">torrent_trackers<\/span>\r\n\r\n<span class=\"hljs-selector-tag\">torrent_files_0<\/span>\r\n<span class=\"hljs-selector-tag\">torrent_files_1<\/span>\r\n.....<span class=\"hljs-selector-class\">.<\/span>\r\n<span class=\"hljs-selector-class\">torrent_files_e<\/span>\r\n<span class=\"hljs-selector-class\">torrent_files_f<\/span>\r\n<\/code><\/pre>\n<p>\u7136\u540e\u7528\u811a\u672c\u89e3\u6790\u79cd\u5b50\u628a\u4fe1\u606f\u5bfc\u8fdb\u6570\u636e\u5e93\uff0c\u6700\u540e\u53d1\u73b0\u5176\u4e2d\u670975\u4e2a\u540d\u79f0\u4e0ehash\u4e0d\u5bf9\u5e94\uff0c7\u4e2a\u65e0\u6548\u79cd\u5b50<\/p>\n<h2>0\u00d704 \u5185\u5bb9\u5206\u6790<\/h2>\n<p>\u8bf4\u4e86\u90a3\u4e48\u591a\uff0c\u662f\u65f6\u5019\u770b\u770b\u6709\u591a\u5c11\u846b\u82a6\u5a03\u5927\u6218\u94a2\u94c1\u4fa0\u4e86\uff0c\u4ee5\u4e0b\u56fe\u8868\u4f7f\u7528D3.js\u751f\u6210\u3002<\/p>\n<h3>4.1 \u603b\u5bb9\u91cf<\/h3>\n<p>\u5168\u90e8\u79cd\u5b50\u603b\u5bb9\u91cf\uff1a1.20PB\uff0c\u89e3\u6790\u5904\u7406\u7684\u5927\u5c0f\u5355\u4f4d\u662f\u76f4\u63a5\uff0c\u76f4\u63a5\u6c42\u548c\u8f6c\u6362\u5355\u4f4d\u5373\u53ef<\/p>\n<pre><code class=\"hljs sql\"><span class=\"hljs-keyword\">select<\/span> <span class=\"hljs-keyword\">concat<\/span>(<span class=\"hljs-keyword\">round<\/span>(<span class=\"hljs-keyword\">sum<\/span>(total_size)\/<span class=\"hljs-number\">1024<\/span>\/<span class=\"hljs-number\">1024<\/span>\/<span class=\"hljs-number\">1024<\/span>\/<span class=\"hljs-number\">1024<\/span>\/<span class=\"hljs-number\">1024<\/span>,<span class=\"hljs-number\">2<\/span>),<span class=\"hljs-string\">\"PB\"<\/span>) <span class=\"hljs-keyword\">as<\/span> <span class=\"hljs-string\">\"total_size\"<\/span> <span class=\"hljs-keyword\">from<\/span> torrent_info;\r\n<\/code><\/pre>\n<p><a class=\"highslide-image\" href=\"http:\/\/image.3001.net\/images\/20160408\/14600800727208.png\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" src=\"http:\/\/image.3001.net\/images\/20160408\/14600800727208.png!small\" alt=\"torrent_0.png\" width=\"690\" data-original=\"http:\/\/image.3001.net\/images\/20160408\/14600800727208.png!small\" \/><\/a><\/p>\n<h3>4.2 Tracker URL TOP 20<\/h3>\n<p>Tracker\u670d\u52a1\u5668\u4e3b\u8981\u662f\u6536\u96c6\u4e0b\u8f7d\u8005\u7684\u4fe1\u606f\uff0c\u5e76\u5c06\u6b64\u4fe1\u606f\u63d0\u4f9b\u7ed9\u5176\u4ed6\u4e0b\u8f7d\u8005\uff0c\u4f7f\u4e0b\u8f7d\u8005\u4eec\u76f8\u4e92\u8fde\u63a5\u8d77\u6765\uff0c\u4f20\u8f93\u6570\u636e\u3002<\/p>\n<p><a class=\"highslide-image\" href=\"http:\/\/image.3001.net\/images\/20160408\/14600800988718.png\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" src=\"http:\/\/image.3001.net\/images\/20160408\/14600800988718.png!small\" alt=\"torrent_1.png\" width=\"690\" data-original=\"http:\/\/image.3001.net\/images\/20160408\/14600800988718.png!small\" \/><\/a><\/p>\n<h3>4.3 \u79cd\u5b50\u540d\u79f0\u4e2d\u57df\u540d TOP 20<\/h3>\n<p>xxx.mp4\u4e0exxx.com\u90fd\u7b26\u5408\u540c\u6837\u7684\u89c4\u5219\uff0c\u4e0b\u8f7d\u9876\u7ea7\u57df\u540d\u540e\u7f00\u8fdb\u884c\u6b63\u5219\u5339\u914d\uff0cmysql\u7684\u6b63\u5219\u4e0d\u597d\u4f7f\uff0c\u7528python\u5339\u914d\u4ee5\u57df\u540d\u4e3akey\u7528\u5b57\u5178\u4fdd\u5b58\uff0c\u7136\u540e\u7528sorted()\u6392\u5e8f<\/p>\n<pre><code class=\"hljs python\">sorted(domain.items(),key=<span class=\"hljs-keyword\">lambda<\/span> d:d[<span class=\"hljs-number\">1<\/span>],reverse=<span class=\"hljs-keyword\">True<\/span>)[:<span class=\"hljs-number\">20<\/span>]\r\n<\/code><\/pre>\n<p><a class=\"highslide-image\" href=\"http:\/\/image.3001.net\/images\/20160408\/14600801245436.png\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" src=\"http:\/\/image.3001.net\/images\/20160408\/14600801245436.png!small\" alt=\"torrent_2.png\" width=\"690\" data-original=\"http:\/\/image.3001.net\/images\/20160408\/14600801245436.png!small\" \/><\/a><\/p>\n<h3>4.4 \u79cd\u5b50\u5305\u542b\u6587\u4ef6\u6269\u5c55\u540d\u4e0e\u6570\u91cf\u5173\u7cfb<\/h3>\n<p>libtorrent\u6ca1\u6709\u73b0\u6210\u7684\u6269\u5c55\u540d\u5c5e\u6027\uff0c\u4e3b\u8981\u901a\u8fc7.\u6765\u53d6\u6700\u540e\u51e0\u4e2a\u5b57\u7b26\u4e32\u4fdd\u5b58\u5230\u6570\u636e\u5e93\uff0c\u76f4\u63a5sql\u5206\u7ec4\u7edf\u8ba1<\/p>\n<p><a class=\"highslide-image\" href=\"http:\/\/image.3001.net\/images\/20160408\/14600801635149.png\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" src=\"http:\/\/image.3001.net\/images\/20160408\/14600801635149.png!small\" alt=\"torrent_3.png\" width=\"690\" data-original=\"http:\/\/image.3001.net\/images\/20160408\/14600801635149.png!small\" \/><\/a><\/p>\n<h3>4.5 \u79cd\u5b50\u5305\u542b\u6587\u4ef6\u4e2a\u6570\u4e0e\u6570\u91cf\u5173\u7cfb<\/h3>\n<p>\u79cd\u5b50\u6709\u5355\u6587\u4ef6\u79cd\u5b50\u548c\u591a\u6587\u4ef6\u79cd\u5b50\u4e4b\u5206\uff0c\u6570\u91cf\u591a\u7684\u5927\u90e8\u5206\u662f\u6b4c\u66f2\u7b49\u4fe1\u606f<\/p>\n<p><a class=\"highslide-image\" href=\"http:\/\/image.3001.net\/images\/20160408\/14600801879813.png\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" src=\"http:\/\/image.3001.net\/images\/20160408\/14600801879813.png!small\" alt=\"torrent_4.png\" width=\"690\" data-original=\"http:\/\/image.3001.net\/images\/20160408\/14600801879813.png!small\" \/><\/a><\/p>\n<h3>4.6 \u79cd\u5b50\u5927\u5c0f\u4e0e\u6570\u91cf\u5173\u7cfb<\/h3>\n<p>\u5355\u4e2a\u79cd\u5b50\u7684\u5927\u5c0f\uff0c\u5c0f\u4e8e1GB\u7684\u5927\u591a\u6570\u662f\u89c6\u9891<\/p>\n<p><a class=\"highslide-image\" href=\"http:\/\/image.3001.net\/images\/20160408\/14600802187048.png\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" src=\"http:\/\/image.3001.net\/images\/20160408\/14600802187048.png!small\" alt=\"torrent_5.png\" width=\"690\" data-original=\"http:\/\/image.3001.net\/images\/20160408\/14600802187048.png!small\" \/><\/a><\/p>\n<h3>4.7 DHT\u7aef\u53e3 TOP 10<\/h3>\n<p><b>announce_peer<\/b>\u8fc7\u6765\u7684\u7aef\u53e3\uff0c\u57fa\u672c\u90fd\u662f\u968f\u673a\u7684\uff0c\u5206\u6790\u8fd9\u4e2a\u6ca1\u5565\u610f<\/p>\n<p><a class=\"highslide-image\" href=\"http:\/\/image.3001.net\/images\/20160408\/14600802856910.png\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" src=\"http:\/\/image.3001.net\/images\/20160408\/14600802856910.png!small\" alt=\"torrent_6.png\" width=\"690\" data-original=\"http:\/\/image.3001.net\/images\/20160408\/14600802856910.png!small\" \/><\/a><\/p>\n<h3>4.8 DHT\u8282\u70b9\u5206\u5e03\u56fe<\/h3>\n<p><b>announce_peer<\/b>\u8fc7\u6765\u7684IP\uff0c\u90fd\u662f\u76f8\u90bb\u7684\u591a\uff0c\u5206\u6790\u610f\u4e49\u4e5f\u4e0d\u5927\uff0c\u53ea\u662f\u60f3\u770b\u770b\u5927\u81f4\u5206\u5e03\uff0cip\u5730\u5740\u4fe1\u606f\u8c03\u7528<a href=\"http:\/\/ip.taobao.com\/service\/getIpInfo.php?ip=1.1.1.1\">http:\/\/ip.taobao.com\/service\/getIpInfo.php?ip=1.1.1.1<\/a>\u63a5\u53e3\uff0c\u6ce8\u610f\u4fdd\u5b58\u8fd4\u56de\u4e2d\u7684country_id\u8fd9\u4e2a\u53c2\u6570\uff0c\u4f7f\u7528\u7684\u662fISO 3166-1 Alpha-2\u7684\u56fd\u5bb6\u7f16\u7801\uff0c\u6709\u65f6\u5019\u751f\u6210\u56fe\u8868\u8981\u7528ISO 3166-1 Alpha-3\u7684\u65f6\u5019\u65b9\u4fbf\u8f6c\u6362<\/p>\n<p><a class=\"highslide-image\" href=\"http:\/\/image.3001.net\/images\/20160408\/14600803299748.png\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" src=\"http:\/\/image.3001.net\/images\/20160408\/14600803299748.png!small\" alt=\"torrent_7.png\" width=\"690\" data-original=\"http:\/\/image.3001.net\/images\/20160408\/14600803299748.png!small\" \/><\/a><\/p>\n<h3>4.9 \u540d\u79f0\u4e2d\u5173\u952e\u8bcd TOP 500<\/h3>\n<p>\u6700\u540e\uff0c\u6765\u70b9\u6bc1\u4e09\u89c2\u7684\uff0c\u636e\u8bf4\u4e00\u773c\u80fd\u5b9a\u4f4d\u67d0\u8bcd\u7684\u90fd\u662f\u5927\u795e\u3002\u3002\u3002\u3002<\/p>\n<p>\u5c06\u6240\u6709\u79cd\u5b50\u540d\u79f0\u5bfc\u51fa\u5230\u4e00\u4e2a\u6587\u672c\u6587\u4ef6\uff0c\u4f7f\u7528\u201c\u7ed3\u5df4\u201d\u4e2d\u6587\u5206\u8bcd\uff08\u5b89\u88c5<b>pip3 install jieba<\/b>\uff09\u63d0\u53d6\u7edf\u8ba1\uff0c\u76f4\u63a5\u8c03\u7528\u5b98\u65b9demo\u811a\u672cextract_tags_with_weight.py\u5373\u53ef\uff0c-k\u662f\u8f93\u51fa\u6570\u91cf\uff0c9999999+\u662f\u4e3a\u4e86\u8f93\u51fa\u5168\u90e8\uff0c-w\u662f\u8ba1\u7b97\u6743\u91cd\uff0c\u7136\u540e\u76f4\u63a5\u7528shell\u8fc7\u6ee4\u6389\u975e\u4e2d\u6587\u5b57\u7b26<\/p>\n<pre><code class=\"hljs nginx\"><span class=\"hljs-attribute\">python3<\/span> extract_tags_with_weight.py -k <span class=\"hljs-number\">9999999999<\/span> -w <span class=\"hljs-number\">1<\/span> torrent_name.txt | awk <span class=\"hljs-string\">'{print <span class=\"hljs-variable\">$2<\/span>}'<\/span> | LANG=C grep -v <span class=\"hljs-string\">'^[[:graph:]]*$'<\/span> | head -n <span class=\"hljs-number\">500<\/span> | xargs\r\n<\/code><\/pre>\n<p><a class=\"highslide-image\" href=\"http:\/\/image.3001.net\/images\/20160408\/14600803772514.png\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" src=\"http:\/\/image.3001.net\/images\/20160408\/14600803772514.png!small\" alt=\"torrent_8.png\" width=\"690\" data-original=\"http:\/\/image.3001.net\/images\/20160408\/14600803772514.png!small\" \/><\/a><\/p>\n<p>\u5f88\u591a\u540d\u5b57\u88ab\u62c6\u5206\u4e86\uff0c\u8f7d\u5165\u5b9a\u5236\u5b57\u5178\uff08\u6bd4\u5982\u6f14\u5458\u540d\u5355\u7b49\uff09\u6548\u679c\u53ef\u80fd\u597d\u70b9\uff0c<b>jieba<\/b>\u5206\u8bcd\u8fd8\u652f\u6301TextRank\u7b97\u6cd5\u62bd\u8bcd\u7b49\u529f\u80fd\uff0c\u4e86\u89e3\u66f4\u591a\u8bf7\u79fb\u6b65\u9879\u76eeGithub\uff1a<a href=\"https:\/\/github.com\/fxsjy\/jieba\/tree\/jieba3k\">https:\/\/github.com\/fxsjy\/jieba\/tree\/jieba3k<\/a><\/p>\n<p>\u53ef\u89c6\u5316\u5c55\u793a\u6548\u679c<\/p>\n<p><a class=\"highslide-image\" href=\"http:\/\/image.3001.net\/images\/20160408\/1460080415704.png\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" src=\"http:\/\/image.3001.net\/images\/20160408\/1460080415704.png!small\" alt=\"torrent_9.png\" width=\"690\" data-original=\"http:\/\/image.3001.net\/images\/20160408\/1460080415704.png!small\" \/><\/a><\/p>\n<p>\u90a3\u4e48\uff0c\u6709\u4eba\u5199\u4e2a\u811a\u672c\u4e0e\u5404\u79cd\u4e91\u81ea\u52a8\u79bb\u7ebf\u7edf\u8ba1\u6709\u6548\u7387\u4e48\uff1f<\/p>\n<h2>0\u00d705 \u53c2\u8003<\/h2>\n<p>\u3010python\u5f00\u53d1\u7684 dht\u7f51\u7edc\u722c\u866b\u3011\u00a0<a href=\"https:\/\/m.oschina.net\/blog\/305538\">https:\/\/m.oschina.net\/blog\/305538<\/a><br \/>\n\u3010DHT \u722c\u866b\u521d\u6b65\u3011<a href=\"http:\/\/firemiles.github.io\/2016\/02\/14\/DHT-%E7%88%AC%E8%99%AB%E5%88%9D%E6%AD%A5\/\">http:\/\/firemiles.github.io\/2016\/02\/14\/DHT-%E7%88%AC%E8%99%AB%E5%88%9D%E6%AD%A5\/<\/a><br \/>\n\u3010DHT Protocol\uff1aBitTorrent DHT \u534f\u8bae\u4e2d\u6587\u7ffb\u8bd1\u3011<a href=\"http:\/\/justjavac.com\/other\/2015\/02\/01\/bittorrent-dht-protocol.html\">http:\/\/justjavac.com\/other\/2015\/02\/01\/bittorrent-dht-protocol.html<\/a><\/p>\n<p>\u5199\u5f97\u6709\u70b9\u4e71\uff0c\u6709\u95ee\u9898\u79c1\u4fe1\u5427\uff0c\u672c\u6587\u6d89\u53ca\u7684\u4e00\u4e9b\u8d44\u6599<a href=\"https:\/\/github.com\/zrools\/spider\/tree\/gh-pages\/asyncDHT\" target=\"_blank\" rel=\"noopener\">\u6233\u8fd9\u91cc(Github)<\/a><\/p>\n<p><strong>*\u539f\u521b\u4f5c\u8005\uff1azrools\uff0c\u672c\u6587\u5c5eFreeBuf\u539f\u521b\u5956\u52b1\u8ba1\u5212\u6587\u7ae0\uff0c\u672a\u7ecf\u8bb8\u53ef\u7981\u6b62\u8f6c\u8f7d<\/strong><\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>DHT\u722c\u866b\uff1a18.4GB\u79cd\u5b50\u5206\u6790\u5c0f\u8bb0 z<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"colormag_page_container_layout":"default_layout","colormag_page_sidebar_layout":"default_layout","footnotes":""},"categories":[24],"tags":[121],"class_list":["post-1523","post","type-post","status-publish","format-standard","hentry","category-value_docs","tag-05-"],"_links":{"self":[{"href":"https:\/\/i007.cc\/wordpress\/wp-json\/wp\/v2\/posts\/1523","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/i007.cc\/wordpress\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/i007.cc\/wordpress\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/i007.cc\/wordpress\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/i007.cc\/wordpress\/wp-json\/wp\/v2\/comments?post=1523"}],"version-history":[{"count":0,"href":"https:\/\/i007.cc\/wordpress\/wp-json\/wp\/v2\/posts\/1523\/revisions"}],"wp:attachment":[{"href":"https:\/\/i007.cc\/wordpress\/wp-json\/wp\/v2\/media?parent=1523"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/i007.cc\/wordpress\/wp-json\/wp\/v2\/categories?post=1523"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/i007.cc\/wordpress\/wp-json\/wp\/v2\/tags?post=1523"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}