node.js - 错误 : getaddrinfo ENOTFOUND parishackers. 组织 parishackers.org:80

Question

错误:getaddrinfo ENOTFOUND parishackers.org parishackers.org:80 发生错误。我写了代码，

var Crawler = require("node-webcrawler");
var url = require('url');

var c = new Crawler({
    maxConnections : 10,
    // This will be called for each crawled page
    callback : function (error, result, $) {
        // $ is Cheerio by default
        //a lean implementation of core jQuery designed specifically for the server
        if(error){
            console.log(error);
        }else{
            console.log($("title").text());
        }
    }
});

// Queue just one URL, with default callback
c.queue('http://www.amazon.com');

// Queue a list of URLs
c.queue(['http://www.google.com/','http://www.yahoo.com']);

// Queue URLs with custom callbacks & parameters
c.queue([{
    uri: 'http://parishackers.org/',
    jQuery: false,

    // The global callback won't be called
    callback: function (error, result) {
        if(error){
            console.log(error);
        }else{
            console.log('Grabbed', result.body.length, 'bytes');
        }
    }
}]);

// Queue some HTML code directly without grabbing (mostly for tests)
c.queue([{
    html: '<p>This is a <strong>test</strong></p>'
}]);

但是当我运行代码时，谷歌雅虎Amazon.com:电子产品、服装、电脑、书籍、DVD 等在线购物

{ Error: getaddrinfo ENOTFOUND parishackers.org parishackers.org:80
    at errnoException (dns.js:50:10)
    at GetAddrInfoReqWrap.onlookup [as oncomplete] (dns.js:92:26)
  code: 'ENOTFOUND',
  errno: 'ENOTFOUND',
  syscall: 'getaddrinfo',
  hostname: 'parishackers.org',
  host: 'parishackers.org',
  port: 80 }

发生错误。我认为程序抓取了一部分数据，但我不知道为什么程序可以完全做到这一点。我安装了类似 npm install node-webcrawler 的库。我读了另一个网站，所以我认为这个错误是由于链接错误而发生的，对吧？我应该如何解决这个问题？我的代码有什么问题？

Answer 1

由于无效域名 http://parishackers.org 而引发错误 (getaddrinfo ENOTFOUND parishackers.org parishackers.org:80) 。使用有效的 url 链接，您的 Node 网络爬虫将像魅力一样工作。修改了代码片段供您引用

var Crawler = require("node-webcrawler");
var url = require('url');

var c = new Crawler({
    maxConnections : 10,
    // This will be called for each crawled page
    callback : function (error, result, $) {
        // $ is Cheerio by default
        //a lean implementation of core jQuery designed specifically for the server
        if(error){
            console.log(error);
        }else{
            console.log($("title").text());
        }
    }
});

// Queue just one URL, with default callback
c.queue('http://www.amazon.com');

// Queue a list of URLs
c.queue(['http://www.google.com/','http://www.yahoo.com']);

// Queue URLs with custom callbacks & parameters
c.queue([{
    uri: 'http://www.amazon.com',
    jQuery: false,

    // The global callback won't be called
    callback: function (error, result) {
        if(error){
            console.log(error);
        }else{
            console.log('Grabbed', result.body.length, 'bytes');
        }
    }
}]);

// Queue some HTML code directly without grabbing (mostly for tests)
c.queue([{
    html: '<p>This is a <strong>test</strong></p>'
}]);