【发布时间】:2018-06-22 03:30:45
【问题描述】:
嗨,我遇到了这个错误,我正在关注如何使用 javascript 进行网络抓取的教程。但是当我执行它时我得到了这个错误
Visiting page https://arstechnica.com/
testcrawl.js:6
Error: Error: connect ETIMEDOUT 50.31.169.131:443
testcrawl.js:9
TypeError: Cannot read property 'statusCode' of undefined
testcrawl.js:12
at Request._callback (c:\Users\nab\practise\testcrawl.js:12:43)
at self.callback (c:\Users\nab\node_modules\request\request.js:185:22)
at emitOne (events.js:116:13)
at Request.emit (events.js:211:7)
at Request.onRequestError (c:\Users\nab\node_modules\request\request.js:877:8)
at emitOne (events.js:116:13)
at ClientRequest.emit (events.js:211:7)
at TLSSocket.socketErrorListener (_http_client.js:387:9)
at emitOne (events.js:116:13)
at TLSSocket.emit (events.js:211:7)
这些是我正在运行的脚本
var request = require('request');
var cheerio = require('cheerio');
var URL = require('url-parse');
var pageToVisit = "https://arstechnica.com/";
console.log("Visiting page " + pageToVisit);
request(pageToVisit, function(error, response, body) {
if(error) {
console.log("Error: " + error);
}
// Check status code (200 is HTTP OK)
console.log("Status code: " + response.statusCode);
if(response.statusCode === 200) {
// Parse the document body
var $ = cheerio.load(body);
console.log("Page title: " + $('title').text());
}
});
为什么会出现这个错误,我该如何解决这个问题?
【问题讨论】:
-
这个网站:
https://arstechnica.com/正在从您的浏览器打开吗? -
@InusSaha 是的,我从我的浏览器打开它
-
您可以尝试设置
timeout选项看看吗?喜欢request({url:pageToVisit, timeout:20000}, function(error, response, body) { -
@InusSaha 你的意思是这样的请求({url:'arstechnica.com', timeout:20000}, function(error, response, body) { console.log('error:', error) ; console.log('statusCode:', response && response.statusCode); console.log('body:', body); });
-
@nabskim 你的代码对我有用。
标签: javascript node.js npm web-crawler