Recently I have been getting into web crawlers and I have figured out ow to search for text but is there any way that I can have my web crawler search for something else such as videos and images and then download them and organize them.
here is my web-crawler so far:
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'));
});
}
I have gotten most of this code from an online tutorial to help me get started but I need more help the code works I just wanted to know if and how would it be possible to web crawl images and video.
Newer Code:
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 + $(this).attr('href'));
});
}
Just like you use cheerio to search the body for links, you can also search the body for either <img>
or <video>
tags. You don't say exactly what you want to do when you find those tags, but you could create a function similar to your collectInternalLinks()
that would collect media objects for further processing:
// return array of image URLs (these may be page-relative URLS)
function collectImages($) {
return $("img").map(function() {
return $(this).prop("src");
}).get();
}
// return collection of video elements
function collectVideos($) {
let videoUrls = [];
$("video").each(function() {
let src = $(this).prop("src");
if (src) {
videoUrls.push(src);
} else {
let subElements = $(this).find("track, source");
subElements.each(function() {
let src = $(this).prop("src");
if (src) {
videoUrls.push(src);
}
});
}
});
return videoUrls;
}
Collecting video URLs is a bit more involved because those URLs can be specified a number of different ways ( .src
property, embedded <track>
tags, embedded <source>
tags, etc...) so you'd have to parse out each possible way for each <video>
tag.
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.