Quand on n'a pas une expérience approfondie de l'utilisation des rappels de fonctions, il est quand même un peu difficile de lire ces contenus. En raison des caractéristiques asynchrones uniques de Node.js, le problème de « l'enfer des rappels » est apparu. Dans cet article, j'ai enregistré plus en détail comment résoudre le problème du flux asynchrone. Cet article présente principalement une brève discussion sur le contrôle de flux asynchrone dans Node.js. L'éditeur pense que c'est assez bon, je vais donc le partager avec vous maintenant et le donner comme référence. Suivons l'éditeur et jetons un œil. J'espère que cela pourra aider tout le monde.
Avant-propos
L'article sera très long, et cet article est une explication du mode streaming asynchrone. Cet article utilisera un exemple simple d'araignée Web. Sa fonction est d'explorer le contenu Web de l'URL spécifiée et de l'enregistrer dans le projet. À la fin de l'article, vous pouvez trouver la démo du code source de l'article entier.
1. Mode JavaScript natif
Cet article n'est pas destiné aux débutants, la plupart du contenu de base sera donc omis :
(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`); } });
Le processus du code ci-dessus ressemble à ceci :
Convertir l'URL en nom de fichier
Déterminez si le nom du fichier existe. S'il existe, revenez directement, sinon passez à l'étape suivante
Envoyez une demande et récupérez le corps
Écrivez le corps dans le fichier
Il s'agit d'une version très simple de l'araignée. Elle ne peut explorer que le contenu d'une URL. le rappel ci-dessus est. Les gens ont des maux de tête. Ensuite, nous commençons à optimiser.
Tout d'abord, la méthode if else peut être optimisée. C'est très simple. Inutile de dire que voici un effet de comparaison :
/// before if (err) { callback(err); } else { callback(null, filename, true); } /// after if (err) { return callback(err); } callback(null, filename, true);
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`); } });
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); }); }) } /// 最大的启发是实现了如何异步循环遍历数组 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`); } });
const links = utilities.getPageLinks(currentUrl, body);
/// 最大的启发是实现了如何异步循环遍历数组 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); }
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); }); }) } /// 最大的启发是实现了如何异步循环遍历数组 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`); } });
/// 最大的启发是实现了如何异步循环遍历数组 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); }); }
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;
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); }); }) } /// 最大的启发是实现了如何异步循环遍历数组 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 => { /// 给队列出传递一个任务,这个任务首先是一个函数,其次该函数接受一个参数 /// 当调用任务时,触发该函数,然后给函数传递一个参数,告诉该函数在任务结束时干什么 downloadQueue.pushTask(done => { spider(link, nesting - 1, err => { /// 这里表示,只要发生错误,队列就会退出 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`); } });
2. Utilisez la bibliothèque asynchrone
Mettre différentes fonctions dans différentes fonctions nous apportera d'énormes avantages La bibliothèque asynchrone est très populaire et ses performances sont également bonnes, il est basé sur le rappel en interne. (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); }); } /// 最大的启发是实现了如何异步循环遍历数组 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`); } });
const series = require("async/series"); // 串行 const eachSeries = require("async/eachSeries"); // 并行 const queue = require("async/queue"); // 队列
3.Promesse
Promise是一个协议,有很多库实现了这个协议,我们用的是ES6的实现。简单来说promise就是一个约定,如果完成了,就调用它的resolve方法,失败了就调用它的reject方法。它内有实现了then方法,then返回promise本身,这样就形成了调用链。
其实Promise的内容有很多,在实际应用中是如何把普通的函数promise化。这方面的内容在这里也不讲了,我自己也不够格
(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编程的本质就是为了解决在函数中设置回调函数的问题 /// 通过中间层promise来实现异步函数同步化 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') { /// 抛出错误,这个方便与在整个异步链的最后通过呢catch来捕获这个链中的错误 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); });
可以看到上边的代码中的函数都是没有callback的,只需要在最后catch就可以了。
在设计api的时候,应该支持两种方式,及支持callback,又支持promise
function asyncpision(pidend, pisor, cb) { return new Promise((resolve, reject) => { "use strict"; process.nextTick(() => { const result = pidend / pisor; 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); }); }); } asyncpision(10, 2, (err, result) => { "use strict"; if (err) { return console.log(err); } console.log(result); }); asyncpision(22, 11) .then((result) => console.log(result)) .catch((err) => console.log(err));
4.Generator
Generator很有意思,他可以让暂停函数和恢复函数,利用thunkify和co这两个库,我们下边的代码实现起来非常酷。
(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); } } /// 通过co就自动处理了回调函数,直接返回了回调函数中的参数,把这些参数放到一个数组中,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); } });
相关推荐:
Ce qui précède est le contenu détaillé de. pour plus d'informations, suivez d'autres articles connexes sur le site Web de PHP en chinois!