/// 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); }
可以说上边这一小段代码，就是采用原生实现异步串行的pattern了。除了这些之外，还引入了nesting的概念，通过这是这个属性，可以控制抓取层次。
到这里我们就完整的实现了串行的功能，考虑到性能，我们要开发并行抓取的功能。
(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`); } });
这段代码同样很简单，也有两个核心内容。一个是如何实现并发：
/// 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); }); }
上边的代码可以说是实现并发的一个pattern。利用循环遍历来实现。另一个核心是，既然是并发的，那么利用 fs.exists 就会存在问题，可能会重复下载同一文件，这里的解决方案是：
使用Map缓存某一url，url应该作为key
现在我们又有了新的需求，要求限制同时并发的最大数，那么在这里就引进了一个我认为最重要的概念：队列。
(task-Queue.js)