溫馨提示×
您好，登錄后才能下訂單哦！
點擊 登錄注冊 即表示同意《億速云用戶服務條款》
您好，登錄后才能下訂單哦！
Node.js中怎么實現異步流控制，很多新手對此不是很清楚，為了幫助大家解決這個難題，下面小編將為大家詳細講解，有這方面需求的人可以來學習下，希望你能有所收獲。
1.原生JavaScript模式
本篇不針對初學者，因此會省略掉大部分的基礎內容的講解：
(spider_v1.js)
const request = require("request");
const fs = require("fs");
const mkdirp = require("mkdirp");
const path = require("path");
const utilities = require("./utilities");
function spider(url, callback) {
const filename = utilities.urlToFilename(url);
console.log(`filename: ${filename}`);
fs.exists(filename, exists => {
if (!exists) {
console.log(`Downloading ${url}`);
request(url, (err, response, body) => {
if (err) {
callback(err);
} else {
mkdirp(path.dirname(filename), err => {
if (err) {
callback(err);
} else {
fs.writeFile(filename, body, err => {
if (err) {
callback(err);
} else {
callback(null, filename, true);
}
});
}
});
}
});
} else {
callback(null, filename, false);
}
});
}
spider(process.argv[2], (err, filename, downloaded) => {
if (err) {
console.log(err);
} else if (downloaded) {
console.log(`Completed the download of ${filename}`);
} else {
console.log(`${filename} was already downloaded`);
}
});上邊的代碼的流程大概是這樣的：
把url轉換成filename
判斷該文件名是否存在，若存在直接返回，否則進入下一步
發請求，獲取body
把body寫入到文件中
這是一個非常簡單版本的蜘蛛，他只能抓取一個url的內容，看到上邊的回調多么令人頭疼。那么我們開始進行優化。
首先，if else 這種方式可以進行優化，這個很簡單，不用多說，放一個對比效果：
/// before
if (err) {
callback(err);
} else {
callback(null, filename, true);
}
/// after
if (err) {
return callback(err);
}
callback(null, filename, true);代碼這么寫，嵌套就會少一層，但經驗豐富的程序員會認為，這樣寫過重強調了error，我們編程的重點應該放在處理正確的數據上，在可讀性上也存在這樣的要求。
另一個優化是函數拆分，上邊代碼中的spider函數中，可以把下載文件和保存文件拆分出去。
(spider_v2.js)
const request = require("request");
const fs = require("fs");
const mkdirp = require("mkdirp");
const path = require("path");
const utilities = require("./utilities");
function saveFile(filename, contents, callback) {
mkdirp(path.dirname(filename), err => {
if (err) {
return callback(err);
}
fs.writeFile(filename, contents, callback);
});
}
function download(url, filename, callback) {
console.log(`Downloading ${url}`);
request(url, (err, response, body) => {
if (err) {
return callback(err);
}
saveFile(filename, body, err => {
if (err) {
return callback(err);
}
console.log(`Downloaded and saved: ${url}`);
callback(null, body);
});
})
}
function spider(url, callback) {
const filename = utilities.urlToFilename(url);
console.log(`filename: ${filename}`);
fs.exists(filename, exists => {
if (exists) {
return callback(null, filename, false);
}
download(url, filename, err => {
if (err) {
return callback(err);
}
callback(null, filename, true);
})
});
}
spider(process.argv[2], (err, filename, downloaded) => {
if (err) {
console.log(err);
} else if (downloaded) {
console.log(`Completed the download of ${filename}`);
} else {
console.log(`${filename} was already downloaded`);
}
});上邊的代碼基本上是采用原生優化后的結果，但這個蜘蛛的功能太過簡單，我們現在需要抓取某個網頁中的所有url，這樣才會引申出串行和并行的問題。
(spider_v3.js)
const request = require("request");
const fs = require("fs");
const mkdirp = require("mkdirp");
const path = require("path");
const utilities = require("./utilities");
function saveFile(filename, contents, callback) {
mkdirp(path.dirname(filename), err => {
if (err) {
return callback(err);
}
fs.writeFile(filename, contents, callback);
});
}
function download(url, filename, callback) {
console.log(`Downloading ${url}`);
request(url, (err, response, body) => {
if (err) {
return callback(err);
}
saveFile(filename, body, err => {
if (err) {
return callback(err);
}
console.log(`Downloaded and saved: ${url}`);
callback(null, body);
});
})
}
/// 最大的啟發是實現了如何異步循環遍歷數組
function spiderLinks(currentUrl, body, nesting, callback) {
if (nesting === 0) {
return process.nextTick(callback);
}
const links = utilities.getPageLinks(currentUrl, body);
function iterate(index) {
if (index === links.length) {
return callback();
}
spider(links[index], nesting - 1, err => {
if (err) {
return callback(err);
}
iterate((index + 1));
})
}
iterate(0);
}
function spider(url, nesting, callback) {
const filename = utilities.urlToFilename(url);
fs.readFile(filename, "utf8", (err, body) => {
if (err) {
if (err.code !== 'ENOENT') {
return callback(err);
}
return download(url, filename, (err, body) => {
if (err) {
return callback(err);
}
spiderLinks(url, body, nesting, callback);
});
}
spiderLinks(url, body, nesting, callback);
});
}
spider(process.argv[2], 2, (err, filename, downloaded) => {
if (err) {
console.log(err);
} else if (downloaded) {
console.log(`Completed the download of ${filename}`);
} else {
console.log(`${filename} was already downloaded`);
}
});上邊的代碼相比之前的代碼多了兩個核心功能，首先是通過輔助類獲取到了某個body中的links：
const links = utilities.getPageLinks(currentUrl, body);
內部實現就不解釋了，另一個核心代碼就是：
/// 最大的啟發是實現了如何異步循環遍歷數組
function spiderLinks(currentUrl, body, nesting, callback) {
if (nesting === 0) {
return process.nextTick(callback);
}
const links = utilities.getPageLinks(currentUrl, body);
function iterate(index) {
if (index === links.length) {
return callback();
}
spider(links[index], nesting - 1, err => {
if (err) {
return callback(err);
}
iterate((index + 1));
})
}
iterate(0);
}可以說上邊這一小段代碼，就是采用原生實現異步串行的pattern了。除了這些之外，還引入了nesting的概念，通過這是這個屬性，可以控制抓取層次。
到這里我們就完整的實現了串行的功能，考慮到性能，我們要開發并行抓取的功能。
(spider_v4.js)
const request = require("request");
const fs = require("fs");
const mkdirp = require("mkdirp");
const path = require("path");
const utilities = require("./utilities");
function saveFile(filename, contents, callback) {
mkdirp(path.dirname(filename), err => {
if (err) {
return callback(err);
}
fs.writeFile(filename, contents, callback);
});
}
function download(url, filename, callback) {
console.log(`Downloading ${url}`);
request(url, (err, response, body) => {
if (err) {
return callback(err);
}
saveFile(filename, body, err => {
if (err) {
return callback(err);
}
console.log(`Downloaded and saved: ${url}`);
callback(null, body);
});
})
}
/// 最大的啟發是實現了如何異步循環遍歷數組
function spiderLinks(currentUrl, body, nesting, callback) {
if (nesting === 0) {
return process.nextTick(callback);
}
const links = utilities.getPageLinks(currentUrl, body);
if (links.length === 0) {
return process.nextTick(callback);
}
let completed = 0, hasErrors = false;
function done(err) {
if (err) {
hasErrors = true;
return callback(err);
}
if (++completed === links.length && !hasErrors) {
return callback();
}
}
links.forEach(link => {
spider(link, nesting - 1, done);
});
}
const spidering = new Map();
function spider(url, nesting, callback) {
if (spidering.has(url)) {
return process.nextTick(callback);
}
spidering.set(url, true);
const filename = utilities.urlToFilename(url);
/// In this pattern, there will be some issues.
/// Possible problems to download the same url again and again。
fs.readFile(filename, "utf8", (err, body) => {
if (err) {
if (err.code !== 'ENOENT') {
return callback(err);
}
return download(url, filename, (err, body) => {
if (err) {
return callback(err);
}
spiderLinks(url, body, nesting, callback);
});
}
spiderLinks(url, body, nesting, callback);
});
}
spider(process.argv[2], 2, (err, filename, downloaded) => {
if (err) {
console.log(err);
} else if (downloaded) {
console.log(`Completed the download of ${filename}`);
} else {
console.log(`${filename} was already downloaded`);
}
});這段代碼同樣很簡單，也有兩個核心內容。一個是如何實現并發：
/// 最大的啟發是實現了如何異步循環遍歷數組
function spiderLinks(currentUrl, body, nesting, callback) {
if (nesting === 0) {
return process.nextTick(callback);
}
const links = utilities.getPageLinks(currentUrl, body);
if (links.length === 0) {
return process.nextTick(callback);
}
let completed = 0, hasErrors = false;
function done(err) {
if (err) {
hasErrors = true;
return callback(err);
}
if (++completed === links.length && !hasErrors) {
return callback();
}
}
links.forEach(link => {
spider(link, nesting - 1, done);
});
}上邊的代碼可以說是實現并發的一個pattern。利用循環遍歷來實現。另一個核心是，既然是并發的，那么利用 fs.exists 就會存在問題，可能會重復下載同一文件，這里的解決方案是：
使用Map緩存某一url，url應該作為key
現在我們又有了新的需求，要求限制同時并發的最大數，那么在這里就引進了一個我認為最重要的概念：隊列。
(task-Queue.js)
class TaskQueue {
constructor(concurrency) {
this.concurrency = concurrency;
this.running = 0;
this.queue = [];
}
pushTask(task) {
this.queue.push(task);
this.next();
}
next() {
while (this.running < this.concurrency && this.queue.length) {
const task = this.queue.shift();
task(() => {
this.running--;
this.next();
});
this.running++;
}
}
}
module.exports = TaskQueue;上邊的代碼就是隊列的實現代碼，核心是 next() 方法，可以看出，當task加入隊列中后，會立刻執行，這不是說這個任務一定馬上執行，而是指的是next會立刻調用。
(spider_v5.js)
const request = require("request");
const fs = require("fs");
const mkdirp = require("mkdirp");
const path = require("path");
const utilities = require("./utilities");
const TaskQueue = require("./task-Queue");
const downloadQueue = new TaskQueue(2);
function saveFile(filename, contents, callback) {
mkdirp(path.dirname(filename), err => {
if (err) {
return callback(err);
}
fs.writeFile(filename, contents, callback);
});
}
function download(url, filename, callback) {
console.log(`Downloading ${url}`);
request(url, (err, response, body) => {
if (err) {
return callback(err);
}
saveFile(filename, body, err => {
if (err) {
return callback(err);
}
console.log(`Downloaded and saved: ${url}`);
callback(null, body);
});
})
}
/// 最大的啟發是實現了如何異步循環遍歷數組
function spiderLinks(currentUrl, body, nesting, callback) {
if (nesting === 0) {
return process.nextTick(callback);
}
const links = utilities.getPageLinks(currentUrl, body);
if (links.length === 0) {
return process.nextTick(callback);
}
let completed = 0, hasErrors = false;
links.forEach(link => {
/// 給隊列出傳遞一個任務，這個任務首先是一個函數，其次該函數接受一個參數
/// 當調用任務時，觸發該函數，然后給函數傳遞一個參數，告訴該函數在任務結束時干什么
downloadQueue.pushTask(done => {
spider(link, nesting - 1, err => {
/// 這里表示，只要發生錯誤，隊列就會退出
if (err) {
hasErrors = true;
return callback(err);
}
if (++completed === links.length && !hasErrors) {
callback();
}
done();
});
});
});
}
const spidering = new Map();
function spider(url, nesting, callback) {
if (spidering.has(url)) {
return process.nextTick(callback);
}
spidering.set(url, true);
const filename = utilities.urlToFilename(url);
/// In this pattern, there will be some issues.
/// Possible problems to download the same url again and again。
fs.readFile(filename, "utf8", (err, body) => {
if (err) {
if (err.code !== 'ENOENT') {
return callback(err);
}
return download(url, filename, (err, body) => {
if (err) {
return callback(err);
}
spiderLinks(url, body, nesting, callback);
});
}
spiderLinks(url, body, nesting, callback);
});
}
spider(process.argv[2], 2, (err, filename, downloaded) => {
if (err) {
console.log(`error: ${err}`);
} else if (downloaded) {
console.log(`Completed the download of ${filename}`);
} else {
console.log(`${filename} was already downloaded`);
}
});因此，為了限制并發的個數，只需在 spiderLinks 方法中，把task遍歷放入隊列就可以了。這相對來說很簡單。
到這里為止，我們使用原生JavaScript實現了一個有相對完整功能的網絡蜘蛛，既能串行，也能并發，還可以控制并發個數。
2.使用async庫
把不同的功能放到不同的函數中，會給我們帶來巨大的好處，async庫十分流行，它的性能也不錯，它內部基于callback。
(spider_v6.js)
const request = require("request");
const fs = require("fs");
const mkdirp = require("mkdirp");
const path = require("path");
const utilities = require("./utilities");
const series = require("async/series");
const eachSeries = require("async/eachSeries");
function download(url, filename, callback) {
console.log(`Downloading ${url}`);
let body;
series([
callback => {
request(url, (err, response, resBody) => {
if (err) {
return callback(err);
}
body = resBody;
callback();
});
},
mkdirp.bind(null, path.dirname(filename)),
callback => {
fs.writeFile(filename, body, callback);
}
], err => {
if (err) {
return callback(err);
}
console.log(`Downloaded and saved: ${url}`);
callback(null, body);
});
}
/// 最大的啟發是實現了如何異步循環遍歷數組
function spiderLinks(currentUrl, body, nesting, callback) {
if (nesting === 0) {
return process.nextTick(callback);
}
const links = utilities.getPageLinks(currentUrl, body);
if (links.length === 0) {
return process.nextTick(callback);
}
eachSeries(links, (link, cb) => {
"use strict";
spider(link, nesting - 1, cb);
}, callback);
}
const spidering = new Map();
function spider(url, nesting, callback) {
if (spidering.has(url)) {
return process.nextTick(callback);
}
spidering.set(url, true);
const filename = utilities.urlToFilename(url);
fs.readFile(filename, "utf8", (err, body) => {
if (err) {
if (err.code !== 'ENOENT') {
return callback(err);
}
return download(url, filename, (err, body) => {
if (err) {
return callback(err);
}
spiderLinks(url, body, nesting, callback);
});
}
spiderLinks(url, body, nesting, callback);
});
}
spider(process.argv[2], 1, (err, filename, downloaded) => {
if (err) {
console.log(err);
} else if (downloaded) {
console.log(`Completed the download of ${filename}`);
} else {
console.log(`${filename} was already downloaded`);
}
});在上邊的代碼中，我們只使用了async的三個功能：
const series = require("async/series"); // 串行
const eachSeries = require("async/eachSeries"); // 并行
const queue = require("async/queue"); // 隊列由于比較簡單，就不做解釋了。async中的隊列的代碼在(spider_v7.js)中，和上邊我們自定義的隊列很相似，也不做更多解釋了。
3.Promise
Promise是一個協議，有很多庫實現了這個協議，我們用的是ES6的實現。簡單來說promise就是一個約定，如果完成了，就調用它的resolve方法，失敗了就調用它的reject方法。它內有實現了then方法，then返回promise本身，這樣就形成了調用鏈。
其實Promise的內容有很多，在實際應用中是如何把普通的函數promise化。這方面的內容在這里也不講了，我自己也不夠格
(spider_v8.js)
const utilities = require("./utilities");
const request = utilities.promisify(require("request"));
const fs = require("fs");
const readFile = utilities.promisify(fs.readFile);
const writeFile = utilities.promisify(fs.writeFile);
const mkdirp = utilities.promisify(require("mkdirp"));
const path = require("path");
function saveFile(filename, contents, callback) {
mkdirp(path.dirname(filename), err => {
if (err) {
return callback(err);
}
fs.writeFile(filename, contents, callback);
});
}
function download(url, filename) {
console.log(`Downloading ${url}`);
let body;
return request(url)
.then(response => {
"use strict";
body = response.body;
return mkdirp(path.dirname(filename));
})
.then(() => writeFile(filename, body))
.then(() => {
"use strict";
console.log(`Downloaded adn saved: ${url}`);
return body;
});
}
/// promise編程的本質就是為了解決在函數中設置回調函數的問題
/// 通過中間層promise來實現異步函數同步化
function spiderLinks(currentUrl, body, nesting) {
let promise = Promise.resolve();
if (nesting === 0) {
return promise;
}
const links = utilities.getPageLinks(currentUrl, body);
links.forEach(link => {
"use strict";
promise = promise.then(() => spider(link, nesting - 1));
});
return promise;
}
function spider(url, nesting) {
const filename = utilities.urlToFilename(url);
return readFile(filename, "utf8")
.then(
body => spiderLinks(url, body, nesting),
err => {
"use strict";
if (err.code !== 'ENOENT') {
/// 拋出錯誤，這個方便與在整個異步鏈的最后通過呢catch來捕獲這個鏈中的錯誤
throw err;
}
return download(url, filename)
.then(body => spiderLinks(url, body, nesting));
}
);
}
spider(process.argv[2], 1)
.then(() => {
"use strict";
console.log('Download complete');
})
.catch(err => {
"use strict";
console.log(err);
});可以看到上邊的代碼中的函數都是沒有callback的，只需要在最后catch就可以了。
在設計api的時候，應該支持兩種方式，及支持callback，又支持promise
function asyncDivision(dividend, divisor, cb) {
return new Promise((resolve, reject) => {
"use strict";
process.nextTick(() => {
const result = dividend / divisor;
if (isNaN(result) || !Number.isFinite(result)) {
const error = new Error("Invalid operands");
if (cb) {
cb(error);
}
return reject(error);
}
if (cb) {
cb(null, result);
}
resolve(result);
});
});
}
asyncDivision(10, 2, (err, result) => {
"use strict";
if (err) {
return console.log(err);
}
console.log(result);
});
asyncDivision(22, 11)
.then((result) => console.log(result))
.catch((err) => console.log(err));4.Generator
Generator很有意思，他可以讓暫停函數和恢復函數，利用thunkify和co這兩個庫，我們下邊的代碼實現起來非常酷。
(spider_v9.js)
const thunkify = require("thunkify");
const co = require("co");
const path = require("path");
const utilities = require("./utilities");
const request = thunkify(require("request"));
const fs = require("fs");
const mkdirp = thunkify(require("mkdirp"));
const readFile = thunkify(fs.readFile);
const writeFile = thunkify(fs.writeFile);
const nextTick = thunkify(process.nextTick);
function* download(url, filename) {
console.log(`Downloading ${url}`);
const response = yield request(url);
console.log(response);
const body = response[1];
yield mkdirp(path.dirname(filename));
yield writeFile(filename, body);
console.log(`Downloaded and saved ${url}`);
return body;
}
function* spider(url, nesting) {
const filename = utilities.urlToFilename(url);
let body;
try {
body = yield readFile(filename, "utf8");
} catch (err) {
if (err.code !== 'ENOENT') {
throw err;
}
body = yield download(url, filename);
}
yield spiderLinks(url, body, nesting);
}
function* spiderLinks(currentUrl, body, nesting) {
if (nesting === 0) {
return nextTick();
}
const links = utilities.getPageLinks(currentUrl, body);
for (let i = 0; i < links.length; i++) {
yield spider(links[i], nesting - 1);
}
}
/// 通過co就自動處理了回調函數，直接返回了回調函數中的參數，把這些參數放到一個數組中，但是去掉了err信息
co(function* () {
try {
yield spider(process.argv[2], 1);
console.log('Download complete');
} catch (err) {
console.log(err);
}
});看完上述內容是否對您有幫助呢？如果還想對相關知識有進一步的了解或閱讀更多相關文章，請關注億速云行業資訊頻道，感謝您對億速云的支持。
免責聲明：本站發布的內容（圖片、視頻和文字）以原創、轉載和分享為主，文章觀點不代表本網站立場，如果涉及侵權請聯系站長郵箱：is@yisu.com進行舉報，并提供相關證據，一經查實，將立刻刪除涉嫌侵權內容。
