Question

我尝试使用node-crawler项目https://github.com/sylvinus/node-crawler

这里是使用代码（它在doc中）

var Crawler = require("crawler");
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
        $('a').each(function(index, a) {
            var toQueueUrl = $(a).attr('href');
            c.queue(toQueueUrl);
        });
    }
});

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

当我运行此代码时，它会发出此错误：

TypeError: undefined is not a function
    at Object.Crawler.callback (/home/app/app.js:10:9)
    at Crawler._onContent (/home/app/node_modules/crawler/lib/crawler.js:461:17)
    at Request._callback (/home/app/node_modules/crawler/lib/crawler.js:351:18)
    at Request.self.callback (/home/app/node_modules/crawler/node_modules/request/request.js:236:22)
    at Request.emit (events.js:98:17)
    at Request.<anonymous> (/home/app/node_modules/crawler/node_modules/request/request.js:1142:14)
    at Request.emit (events.js:117:20)
    at IncomingMessage.<anonymous> (/home/app/node_modules/crawler/node_modules/request/request.js:1096:12)
    at IncomingMessage.emit (events.js:117:20)
    at _stream_readable.js:944:16

我使用的node.js版本：v0.10.37

Answer 1

// Update your node.js, node-crawler and try this code instead of your callback function
callback : function (error, res, done) {
  var $ = res.$;
  $('a').each(function(index, a) {
    var toQueueUrl = $(a).attr('href');
    c.queue(toQueueUrl);
  });
}

Node.js Node-Crawler TypeError：undefined不是函数

1 个答案: