Node.js的报告网址为200，而不是404

Question

我有一个Node.js的应用期运用在http://bartonlp.org:8080运行express.js。我看到这一点，例如，在我的日志输出：

"GET http://www.baidu.com/?rnd=19712180733831423955225532 HTTP/1.0" 200 2749 

我本来期望所有其他的要求来生产一个404错误，而不是200。这看起来像请求www.baidu.com实际上得到回答。

这怎么会发生？我在我的app.get唯一（“/” ......是一个主要的页面。

这是一个很小的node.js加express.js app.js和路由/ index.js。 这给了相同的结果与原始文件，这里是我的日志文件的副本：

::ffff:94.102.49.174 - - [22/Sep/2016:23:22:29 +0000] "GET http://www.baidu.com/cache/global/img/gs.gif HTTP/1.1" 404 975 "-" "Mozilla" 
::ffff:61.157.96.111 - - [22/Sep/2016:23:49:10 +0000] "GET http://www.baidu.com/?rnd=3342104796019809757566816 HTTP/1.0" 200 197 "-" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2;Windows NT 5.1;Windows NT 5.3; Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1) ; .NET CLR 1.1.4322; .NET CLR 2.0.50727)" 
::ffff:61.157.96.111 - - [22/Sep/2016:23:49:10 +0000] "GET http://50.117.47.67:43530/?rnd=2031422537804277052916912 HTTP/1.0" 200 197 "-" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2;Windows NT 5.1;Windows NT 5.3; Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1) ; .NET CLR 1.1.4322; .NET CLR 2.0.50727)" 
::ffff:61.157.96.111 - - [22/Sep/2016:23:49:11 +0000] "GET http://123.249.29.201:/?rnd=173003480482578803940608 HTTP/1.0" 200 197 "-" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2;Windows NT 5.1;Windows NT 5.3; Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1) ; .NET CLR 1.1.4322; .NET CLR 2.0.50727)" 
::ffff:61.157.96.112 - - [22/Sep/2016:23:56:31 +0000] "GET http://123.249.29.201:/?rands=_518421966013600083518500 HTTP/1.0" 200 197 "-" "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)" 
::ffff:61.157.96.112 - - [22/Sep/2016:23:56:31 +0000] "GET http://www.baidu.com/?rands=_14790662340951392923112 HTTP/1.0" 200 197 "-" "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)" 
::ffff:61.157.96.112 - - [22/Sep/2016:23:56:32 +0000] "GET http://50.117.47.15:28712/?rands=_71269649426275522095128 HTTP/1.0" 200 197 "-" "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)" 
::ffff:61.157.96.112 - - [22/Sep/2016:23:56:33 +0000] "GET http://50.117.86.106/?rands=_146883056102225940108720 HTTP/1.0" 200 197 "-" "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)" 
::ffff:62.210.162.182 - - [23/Sep/2016:00:04:23 +0000] "GET/HTTP/1.1" 200 197 "-" "Ruby" 
::ffff:62.210.162.182 - - [23/Sep/2016:00:04:29 +0000] "GET/HTTP/1.1" 200 197 "-" "Mozilla/5.0 (Windows NT 5.1; rv:9.0.1) Gecko/20100101 Firefox/9.0.1" 
::ffff:62.210.162.182 - - [23/Sep/2016:00:04:30 +0000] "GET /HNAP1/ HTTP/1.1" 404 975 "-" "Mozilla/5.0 (Windows NT 5.1; rv:9.0.1) Gecko/20100101 Firefox/9.0.1" 

“的底部/ HNAP1 /”失败，一个404，这是我所期望 但这些日志行。所有获得200：

::ffff:61.157.96.111 - - [22/Sep/2016:23:49:10 +0000] "GET http://www.baidu.com/?rnd=3342104796019809757566816 HTTP/1.0" 200 197 "-" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2;Windows NT 5.1;Windows NT 5.3; Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1) ; .NET CLR 1.1.4322; .NET CLR 2.0.50727)" 
::ffff:61.157.96.111 - - [22/Sep/2016:23:49:10 +0000] "GET http://50.117.47.67:43530/?rnd=2031422537804277052916912 HTTP/1.0" 200 197 "-" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2;Windows NT 5.1;Windows NT 5.3; Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1) ; .NET CLR 1.1.4322; .NET CLR 2.0.50727)" 
::ffff:61.157.96.111 - - [22/Sep/2016:23:49:11 +0000] "GET http://123.249.29.201:/?rnd=173003480482578803940608 HTTP/1.0" 200 197 "-" "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2;Windows NT 5.1;Windows NT 5.3; Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1) ; .NET CLR 1.1.4322; .NET CLR 2.0.50727)" 
::ffff:61.157.96.112 - - [22/Sep/2016:23:56:31 +0000] "GET http://123.249.29.201:/?rands=_518421966013600083518500 HTTP/1.0" 200 197 "-" "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)" 
::ffff:61.157.96.112 - - [22/Sep/2016:23:56:31 +0000] "GET http://www.baidu.com/?rands=_14790662340951392923112 HTTP/1.0" 200 197 "-" "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)" 
::ffff:61.157.96.112 - - [22/Sep/2016:23:56:32 +0000] "GET http://50.117.47.15:28712/?rands=_71269649426275522095128 HTTP/1.0" 200 197 "-" "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)" 
::ffff:61.157.96.112 - - [22/Sep/2016:23:56:33 +0000] "GET http://50.117.86.106/?rands=_146883056102225940108720 HTTP/1.0" 200 197 "-" "Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)" 

这里是我的app.js：

var express = require('express'); 
var path = require('path'); 
var favicon = require('serve-favicon'); 
var logger = require('morgan'); 
var cookieParser = require('cookie-parser'); 
var bodyParser = require('body-parser'); 
var routes = require('./routes/index'); 
var app = express(); 
// view engine setup 
app.set('views', path.join(__dirname, 'views')); 
app.set('view engine', 'jade'); 
// uncomment after placing your favicon in /public 
app.use(favicon(path.join(__dirname, 'public', 'favicon.ico'))); 
app.use(logger('combined')); 
app.use(bodyParser.json()); 
app.use(bodyParser.urlencoded({ extended: false })); 
app.use(cookieParser()); 
app.use(express.static(path.join(__dirname, 'public'))); 
app.use('/', routes); 
// catch 404 and forward to error handler 
app.use(function(req, res, next) { 
    var err = new Error('Not Found'); 
    err.status = 404; 
    next(err); 
}); 
// error handlers 
// development error handler 
// will print stacktrace 
if (app.get('env') === 'development') { 
    app.use(function(err, req, res, next) { 
    res.status(err.status || 500); 
    res.render('error', { 
    message: err.message, 
    error: err 
    }); 
    }); 
} 
// production error handler 
// no stacktraces leaked to user 
app.use(function(err, req, res, next) { 
    res.status(err.status || 500); 
    res.render('error', { 
    message: err.message, 
    error: {} 
    }); 
}); 
module.exports = app; 

这里是我的路线/ index.js

var express = require('express'); 
var router = express.Router(); 
/* GET home page. */ 
router.get('/', function(req, res, next) { 
    res.render('index', { title: 'My Test Node App' }); 
}); 
module.exports = router; 

这里是斌/ WWW脚本

#!/usr/bin/env node 
/** 
* Module dependencies. 
*/ 
var app = require('../app'); 
var debug = require('debug')('newnode:server'); 
var http = require('http'); 
/** 
* Get port from environment and store in Express. 
*/ 
var port = normalizePort(process.env.PORT || '3000'); 
console.log("PORT: ", port); 
app.set('port', port); 
/** 
* Create HTTP server. 
*/ 
var server = http.createServer(app); 
/** 
* Listen on provided port, on all network interfaces. 
*/ 
server.listen(port); 
server.on('error', onError); 
server.on('listening', onListening); 
/** 
* Normalize a port into a number, string, or false. 
*/ 
function normalizePort(val) { 
    var port = parseInt(val, 10); 
    if (isNaN(port)) { 
    // named pipe 
    return val; 
    } 
    if (port >= 0) { 
    // port number 
    return port; 
    } 
    return false; 
} 
/** 
* Event listener for HTTP server "error" event. 
*/ 
function onError(error) { 
    if (error.syscall !== 'listen') { 
    throw error; 
    } 
    var bind = typeof port === 'string' 
    ? 'Pipe ' + port 
    : 'Port ' + port; 
    // handle specific listen errors with friendly messages 
    switch (error.code) { 
    case 'EACCES': 
     console.error(bind + ' requires elevated privileges'); 
     process.exit(1); 
     break; 
    case 'EADDRINUSE': 
     console.error(bind + ' is already in use'); 
     process.exit(1); 
     break; 
    default: 
     throw error; 
    } 
} 

/** 
* Event listener for HTTP server "listening" event. 
*/ 
function onListening() { 
    var addr = server.address(); 
    var bind = typeof addr === 'string' 
    ? 'pipe ' + addr 
    : 'port ' + addr.port; 
    console.log('Listening on ' + bind); 
} 

这个环境做 '表达newnode' 之后。

我希望这可以解释不够好。

我的问题又是为什么那些“http://www.baidu.com ...”记录最终得到一个200而不是404吗？

Answer 1

这不是一个“不可能的URL”。它完全有效，但完整的URL（例如http://example.org/foo）而不是路径（/foo）通常用于HTTP代理，其中完整的URL是客户端希望通过代理服务器访问的站点。

编辑：在审查了最近发布的服务器端路由代码后，路由设置没有错误。相反，它似乎有一个Express中的错误it only inspects the path portion of a request url（忽略任何其他解析的部分）。我提交了一个问题here。

所以在您的特定情况下，那些要求一个完整的URL（即有没有路径）的客户目前正在接受来自您的/路由处理的响应。其他完整网址（例如http://www.baidu.com/cache/global/img/gs.gif）不匹配，因为您没有./public/cache/global/img/gs.gif，也没有明确的路由处理程序/cache/global/img/gs.gif）。对于那些在服务器端日志中正确看到404的人。

编辑2：令人惊讶的，这是没有考虑由快递维护一个bug，所以你将不得不在每个路由执行的检查req.originalUrl和/或类似性质或包括通用中间件处理程序（之前任何其他请求处理程序（可能是日志记录中间件除外），如果您关心拒绝这些完整的URL请求，它将检查这些完整的URL并正确处理它们。

这里有一个例子中间件，你会增加第一到您的中间件/路由处理器堆栈：

app.use(function(req, res, next) { 
    if (req.originalUrl.charCodeAt(0) !== 47/*'/'*/) 
    return res.sendStatus(400); 
    next(); 
});