</pre><pre name="code" class="python">/*
对于nodejs中由于几乎大部分的操作都是异步的,所以我们都是通过一层层的函数来实现。
而异步也会带来一些问题,那就是同时并发过度的request,就会导致链接失败(或则连接被关闭)
如何做到既能异步操作,又能控制并发数目,asyn库应该是可以满足需要
*/
const url = require('url');
const request = require('request');
const http = require('http');
const fs = require('fs');
const util = require('util');
const async = require('async');
function getUrl(id, arr) {
var arrs = [];
for (var i = 0; i < arr[1]; ++i) {
var n = i + '';
if (n !== '0') {
while (n.length < 3) {
n = 0 + n;
}
}
var r = util.format('http://img.zngirls.com/gallery/%d/%d/%s.jpg', id, arr[0], n);
arrs.push(r);
}
//console.log(arrs);
return arrs;
}
function direct_download(_url, filename, cb) {
var arrPath = filename.split('/');
if (arrPath.length > 1) {
var fullPath = '';
arrPath = arrPath.slice(0, -1);
do {
fullPath += arrPath.shift() + '/';
if (!fs.existsSync(fullPath)) {
fs.mkdir(fullPath);
}
} while (arrPath.length > 0);
}
var opt = {
proxy: 'http://proxy3.bj.petrochina:8080',
url: _url,
headers: {
referer: 'http://www.baidu.com',
}
}
request.get({
proxy: 'http://proxy3.bj.petrochina:8080',
url: _url,
headers: {
referer: 'http://www.baidu.com',
}
}).pipe(fs.createWriteStream(filename)).on('close', function () {
console.log("图片下载成功啦");
if (cb) {
cb(null, "successful !");
//callback貌似必须调用,第二个参数将传给下一个回调函数的result,result是一个数组
}
});
//download(_url, filename);
/*
request.get(opt, function(err,res, body){
if(err){
console.log(err);
console.log("有一张图片请求失败啦...");
}else{
fs.writeFile(filename, body, function(err){
if(err){
console.log(err);
console.log("有一张图片写入失败啦...");
}else{
console.log("图片下载成功啦");
if(cb){
cb(null,"successful !");
//callback貌似必须调用,第二个参数将传给下一个回调函数的result,result是一个数组
}
}
});
}
});
*/
}
function download(ur, fileName) {
//实现下载(网络异步)和文件保存(IO异步操作)
var u = url.parse(ur);
var options = {
//代理服务器
host: 'proxy3.bj.petrochina',
port: 8080,
path: ur,
//增加请求头,绕过服务器检测
//headers : {Referer:'http://www.baidu.com',}
headers: {
Referer: 'http://www.baidu.com',
Accept: 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate, sdch',
'Accept-Language': 'zh-CN,zh;q=0.8,en;q=0.6',
Host: 't1.zngirls.com',
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36',
}
};
http.get(options, function (res) {
//打开一个文件对象,在数据传输过程中,每次以块的形式
//写入到文件中
var fd = fs.openSync(fileName, 'w');
//监听数据传输
res.on('data', function (chunk) {
fs.writeSync(fd, chunk, 0, chunk.length);
//console.log(util.inspect(chunk,true));
});
//监听传输完成
res.on('end', function () {
fs.closeSync(fd);
console.log(`save to ${fileName}`);
});
});
}
function somany_request() {
var id = 18071;
//var gallery = [[18812, 49], [19695, 49], [19019, 43], [18214, 49], [16751, 54], [13207, 72], [13206, 68]];
var gallery = [[18812, 49], [19695, 49], [19019, 43], [18214, 49], [16751, 54], [13207, 72], [13206, 68]];
var pictures = []
gallery.forEach(function (i) {
var urls = getUrl(id, i);
urls.forEach(function (_url) {
var filename = _url.split('/').slice(-4).join('/');
pictures.push({url: _url, filename: filename});
//direct_download(_url, filename);
});
});
//开始启动异步下载
async.mapLimit(pictures, 10, function (pic, cb) {
console.log('已经有10张图片进入下载队列...');
direct_download(pic.url, pic.filename, cb);
}, function (err, result) {
if (err) {
console.log(err);
} else {
console.log('下载任务全部完成');
}
});
}
somany_request();
//direct_download('http://img.zngirls.com/gallery/18071/18812/0.jpg', 'gallery/18071/18812/0.jpg');
nodejs中使用async来对异步操作进行同步,避免多个异步同时启动引发连接错误
最新推荐文章于 2023-03-15 18:32:11 发布