node.js - node async写的爬虫小程序请求高手指导

Question

var cnodeUrl = "https://segmentfault.com/";

// 存放所有主题链接链接
var topicUrls = [];

/**
 * 所有的url请求完成后，ep控制异步结束，进入每一个主题
 */
ep.after('topic_html', topicUrls.length, function(topics) {

    var concurrencyCount = 0;  // 记录并发数

    /**
     * 进入主题，取得题目
     * @callback topics [{title:''}]
     */
    var fetchUrl = function(myurl, callback) {
        var fetchStart = new Date().getTime();
        concurrencyCount++;
        console.log('现在的并发数是', concurrencyCount, '，正在抓取的是', myurl);

        superagent.get(myurl).end(function(err, ssres) {
            if (err) {
                callback(err, myurl + ' error happened!');
            }
            var time = new Date().getTime() - fetchStart;
            console.log('抓取 ' + myurl + ' 成功', '，耗时' + time + '毫秒');
            concurrencyCount--;

            var $ = cheerio.load(ssres.text);
            var reslut = {
                title: $('.question__author>a>strong').text(),
                answer: $('#answers-title').text()
            };
            callback(null, result);
        })
    }

    // 控制最大并发数为5，在结果中取出callback返回来的整个结果数组。
    async.mapLimit(topicUrls, 5, function (myurl, callback) {
        fetchUrl(myurl, callback);
    }, function (err, result) {
        console.log('===== result: ======\n', result);
        //res.send(result);
    });
})

// 获得所有主题链接 topicUrls
superagent.get(cnodeUrl).end(function(err, sres) {
    if(err) {
        return next(err);
    }
    var $ = cheerio.load(sres.text);
    $('.stream-list').each(function(idx, element) {
        var $element = $(element).find('.title>a');
        var href = url.resolve(cnodeUrl, $element.attr('href'));
        topicUrls.push(href);
    })
    console.log('get authorUrls successful!\n', topicUrls);
    ep.emit('topic_html', 'get topicUrls successful');
})

得到的结果是：

请教一下哪里出了问题？

Answer 1

Rewritten:

var async = require('async');
var cheerio = require('cheerio');
var superagent = require('superagent');


var url = require('url');
var cnodeUrl = "https://segmentfault.com/";


// 存放所有主题链接链接
var topicUrls = [];

// 获得所有主题链接 topicUrls
superagent.get(cnodeUrl).end(function(err, sres) {
    if(err) {
        return next(err);
    }
    var $ = cheerio.load(sres.text);
    $('.stream-list__item').each(function(idx, element) {
        var $element = $(element).find('.title>a');
        var href = url.resolve(cnodeUrl, $element.attr('href'));
        topicUrls.push(href);
    })
    // 控制最大并发数为5，在结果中取出callback返回来的整个结果数组。
    async.mapLimit(topicUrls, 5, function (myurl, callback) {
        fetchUrl(myurl, callback);
    }, function (err, result) {
        console.log('===== result: ======', result);
    });
})


function fetchUrl(myurl,callback) {
    var fetchStart = new Date().getTime();
    superagent.get(myurl).end(function(err, ssres) {
        if (err) {
            callback(err, myurl + ' error happened!');
        }
        var time = new Date().getTime() - fetchStart;
        console.log('抓取 ' + myurl + ' 成功', '，耗时' + time + '毫秒');
        // concurrencyCount--;

        var $ = cheerio.load(ssres.text);
        var reslut = {
            title: $('.question__author>a>strong').text(),
            answer: $('#answers-title').text()
        };
        callback(null, reslut);
    })
}

I think you are referring to the code above

https://github.com/alsotang/node-lessons/blob/master/lesson4/app.js

This course is written, maybe the eventproxy method you use is incorrect