Node.js网络爬虫图像/视频

最近我一直在使用网络爬虫，我已经知道如何搜索文本，但是有没有办法让我的网络爬虫搜索其他东西，如视频和图像，然后下载并组织它们。

这是我到目前为止的网络爬虫:

var request = require('request');
var cheerio = require('cheerio');
var URL = require('url-parse');
var fs = require('fs');
var START_URL = "https://www.google.com";
var SEARCH_WORD = "apples";
var MAX_PAGES_TO_VISIT = 200;
var pagesVisited = {};
var numPagesVisited = 0;
var pagesToVisit = [];
var url = new URL(START_URL);
var baseUrl = url.protocol + "//" + url.hostname;
pagesToVisit.push(START_URL);
 crawl();
 function crawl() {
  if(numPagesVisited >= MAX_PAGES_TO_VISIT) {
    console.log("Reached max limit of number of pages to visit.");
     return;
  }
  var nextPage = pagesToVisit.pop();
  if (nextPage in pagesVisited) {
    // We've already visited this page, so repeat the crawl
    crawl();
  } else {
    // New page we haven't visited
    visitPage(nextPage, crawl);
  }
}
function visitPage(url, callback) {
  // Add page to our set
  pagesVisited[url] = true;
 numPagesVisited++;
  // Make the request
 console.log("Visiting page " + url);
  request(url, function(error, response, body) {
     // Check status code (200 is HTTP OK)
     console.log("Status code: " + response.statusCode);
     if(response.statusCode !== 200) {
       callback();
       return;
    }
    // Parse the document body
      var $ = cheerio.load(body);
     var isWordFound = searchForWord($, SEARCH_WORD);
     if(isWordFound) {
      console.log('Word ' + SEARCH_WORD + ' found at page ' + url);
     } else {
       collectInternalLinks($);
       // In this short program, our callback is just calling crawl()
       callback();
     }
  });
 }
function searchForWord($, word) {
  var bodyText = $('html > body').text().toLowerCase();
  return(bodyText.indexOf(word.toLowerCase()) !== -1);
}
 function collectInternalLinks($) {
     var relativeLinks = $("a[href^='/']");
console.log("Found " + relativeLinks.length + " relative links on page");
relativeLinks.each(function() {
    pagesToVisit.push(baseUrl + $(this).attr('href'));
});
}

我已经从一个在线教程中得到了大部分的代码，以帮助我开始，但我需要更多的帮助，代码的工作，我只是想知道，如果以及如何可能的网络抓取图像和视频。

var request = require('request');
var cheerio = require('cheerio');
var URL = require('url-parse');
var fs = require('fs');
var START_URL = "http://moetube.net";
//var SEARCH_WORD = "anime";
 var MAX_PAGES_TO_VISIT = 200;
 var pagesVisited = {};
 var numPagesVisited = 0;
 var pagesToVisit = [];
  var url = new URL(START_URL);
 var baseUrl = url.protocol + "//" + url.hostname;
 pagesToVisit.push(START_URL);
 crawl();
 function crawl() {
   if(numPagesVisited >= MAX_PAGES_TO_VISIT) {
     console.log("Reached max limit of number of pages to visit.");
     return;
   }
   var nextPage = pagesToVisit.pop();
   if (nextPage in pagesVisited) {
     // We've already visited this page, so repeat the crawl
     crawl();
    } else {
       // New page we haven't visited
       visitPage(nextPage, crawl);
     }
   }
   function visitPage(url, callback) {
    // Add page to our set
    pagesVisited[url] = true;
    numPagesVisited++;
     // Make the request
     console.log("Visiting page " + url);
    request(url, function(error, response, body) {
    var $ = cheerio.load(body);
      // Check status code (200 is HTTP OK)
      console.log("Status code: " + response.statusCode);
      collectImages($);
      if(response.statusCode !== 200) {
        callback();
          return;
       }
      // Parse the document body
     // var isWordFound = searchForWord($, SEARCH_WORD);
    // if(isWordFound) {
     //   console.log('Word ' + SEARCH_WORD + ' found at page ' + url);
    // } else {
       collectInternalLinks($);
       // In this short program, our callback is just calling crawl()
       callback();
   //  }
   });
}
   function searchForWord($, word) {
   var bodyText = $('html > body').text().toLowerCase();
  return(bodyText.indexOf(word.toLowerCase()) !== -1);
    }
function collectImages($) {
   return $("img").map(function() {
        return $(this).text();
         console.log((this).text() + "JHJHHHHHHHHHHHHHHHHHHHH");
     }).get();
      }
 function collectInternalLinks($) {
     var relativeLinks = $("a[href^='/']");
     console.log("Found " + relativeLinks.length + " relative links on page");
     relativeLinks.each(function() {
         pagesToVisit.push(baseUrl + $(this).attr('href'));
     });
 }