问用节点爬虫或简单爬虫进行NodeJS网络爬行

EN

var Crawler = require("simplecrawler");
var moment = require("moment");
var cheerio = require("cheerio");

var crawler = new Crawler("http://example.com");

function log() {
    var time = moment().format("HH:mm:ss");
    var args = Array.from(arguments);

    args.unshift(time);
    console.log.apply(console, args);
}

crawler.downloadUnsupported = false;
crawler.decodeResponses = true;

crawler.addFetchCondition(function(queueItem) {
    return !queueItem.path.match(/\.(zip|jpe?g|png|mp4|gif)$/i);
});

crawler.on("crawlstart", function() {
    log("crawlstart");
});

crawler.on("fetchcomplete", function(queueItem, responseBuffer) {
    log("fetchcomplete", queueItem.url);
});

crawler.on("fetch404", function(queueItem, response) {
    log("fetch404", queueItem.url, response.statusCode);
});

crawler.on("fetcherror", function(queueItem, response) {
    log("fetcherror", queueItem.url, response.statusCode);
});

crawler.on("complete", function() {
    log("complete");
});

crawler.start();