我最近编写了这个代码，并认为在这里分享它是有意义的。代码使用了异步库。

var fs = require('fs');
var async = require('async');

var scan = function(dir, suffix, callback) {
  fs.readdir(dir, function(err, files) {
    var returnFiles = [];
    async.each(files, function(file, next) {
      var filePath = dir + '/' + file;
      fs.stat(filePath, function(err, stat) {
        if (err) {
          return next(err);
        }
        if (stat.isDirectory()) {
          scan(filePath, suffix, function(err, results) {
            if (err) {
              return next(err);
            }
            returnFiles = returnFiles.concat(results);
            next();
          })
        }
        else if (stat.isFile()) {
          if (file.indexOf(suffix, file.length - suffix.length) !== -1) {
            returnFiles.push(filePath);
          }
          next();
        }
      });
    }, function(err) {
      callback(err, returnFiles);
    });
  });
};

你可以这样使用它:

scan('/some/dir', '.ext', function(err, files) {
  // Do something with files that ends in '.ext'.
  console.log(files);
});

There are basically two ways of accomplishing this. In an async environment you'll notice that there are two kinds of loops: serial and parallel. A serial loop waits for one iteration to complete before it moves onto the next iteration - this guarantees that every iteration of the loop completes in order. In a parallel loop, all the iterations are started at the same time, and one may complete before another, however, it is much faster than a serial loop. So in this case, it's probably better to use a parallel loop because it doesn't matter what order the walk completes in, just as long as it completes and returns the results (unless you want them in order).

一个平行循环看起来是这样的:

var fs = require('fs');
var path = require('path');
var walk = function(dir, done) {
  var results = [];
  fs.readdir(dir, function(err, list) {
    if (err) return done(err);
    var pending = list.length;
    if (!pending) return done(null, results);
    list.forEach(function(file) {
      file = path.resolve(dir, file);
      fs.stat(file, function(err, stat) {
        if (stat && stat.isDirectory()) {
          walk(file, function(err, res) {
            results = results.concat(res);
            if (!--pending) done(null, results);
          });
        } else {
          results.push(file);
          if (!--pending) done(null, results);
        }
      });
    });
  });
};

一个串行循环看起来像这样:

var fs = require('fs');
var path = require('path');
var walk = function(dir, done) {
  var results = [];
  fs.readdir(dir, function(err, list) {
    if (err) return done(err);
    var i = 0;
    (function next() {
      var file = list[i++];
      if (!file) return done(null, results);
      file = path.resolve(dir, file);
      fs.stat(file, function(err, stat) {
        if (stat && stat.isDirectory()) {
          walk(file, function(err, res) {
            results = results.concat(res);
            next();
          });
        } else {
          results.push(file);
          next();
        }
      });
    })();
  });
};

并且在你的主目录中测试它(警告:如果你的主目录中有很多东西，结果列表将会非常大):

walk(process.env.HOME, function(err, results) {
  if (err) throw err;
  console.log(results);
});

编辑:改进的示例。

它使用了节点8中最多的新功能，包括Promises、util/promisify、destructuring、async-await、map+reduce等等，让你的同事在试图弄清楚发生了什么时挠头。

节点 8+

没有外部依赖。

const { promisify } = require('util');
const { resolve } = require('path');
const fs = require('fs');
const readdir = promisify(fs.readdir);
const stat = promisify(fs.stat);

async function getFiles(dir) {
  const subdirs = await readdir(dir);
  const files = await Promise.all(subdirs.map(async (subdir) => {
    const res = resolve(dir, subdir);
    return (await stat(res)).isDirectory() ? getFiles(res) : res;
  }));
  return files.reduce((a, f) => a.concat(f), []);
}

使用

getFiles(__dirname)
  .then(files => console.log(files))
  .catch(e => console.error(e));

节点 10.10+

更新到节点10+，甚至更多的whizbang:

const { resolve } = require('path');
const { readdir } = require('fs').promises;

async function getFiles(dir) {
  const dirents = await readdir(dir, { withFileTypes: true });
  const files = await Promise.all(dirents.map((dirent) => {
    const res = resolve(dir, dirent.name);
    return dirent.isDirectory() ? getFiles(res) : res;
  }));
  return Array.prototype.concat(...files);
}

请注意，从节点11.15.0开始，您可以使用files.flat()而不是array. prototype.concat(…files)来扁平化files数组。

11 +节点

如果你想让所有人都大吃一惊，你可以使用下面使用异步迭代器的版本。除了非常酷之外，它还允许使用者每次提取一个结果，这使得它更适合于真正大的目录。

const { resolve } = require('path');
const { readdir } = require('fs').promises;

async function* getFiles(dir) {
  const dirents = await readdir(dir, { withFileTypes: true });
  for (const dirent of dirents) {
    const res = resolve(dir, dirent.name);
    if (dirent.isDirectory()) {
      yield* getFiles(res);
    } else {
      yield res;
    }
  }
}

用法发生了变化，因为返回类型现在是异步迭代器而不是promise

;(async () => {
  for await (const f of getFiles('.')) {
    console.log(f);
  }
})()

如果有人感兴趣，我在这里写了更多关于异步迭代器的文章:https://qwtel.com/posts/software/async-generators-in-the-wild/

只是简单的散步

let pending = [baseFolderPath]
function walk () {
    pending.shift();
    // do stuffs width pending[0] and change pending items
    if (pending[0]) walk(pending[0])
}
walk(pending[0])

另一个简单而有用的方法

function walkDir(root) {
    const stat = fs.statSync(root);

    if (stat.isDirectory()) {
        const dirs = fs.readdirSync(root).filter(item => !item.startsWith('.'));
        let results = dirs.map(sub => walkDir(`${root}/${sub}`));
        return [].concat(...results);
    } else {
        return root;
    }
}

为了好玩，这里有一个基于流的版本，它与highland.js streams库一起工作。作者之一是维克多·伍。

###
  directory >---m------> dirFilesStream >---------o----> out
                |                                 |
                |                                 |
                +--------< returnPipe <-----------+

  legend: (m)erge  (o)bserve

 + directory         has the initial file
 + dirListStream     does a directory listing
 + out               prints out the full path of the file
 + returnPipe        runs stat and filters on directories

###

_ = require('highland')
fs = require('fs')
fsPath = require('path')

directory = _(['someDirectory'])
mergePoint = _()
dirFilesStream = mergePoint.merge().flatMap((parentPath) ->
  _.wrapCallback(fs.readdir)(parentPath).sequence().map (path) ->
    fsPath.join parentPath, path
)
out = dirFilesStream
# Create the return pipe
returnPipe = dirFilesStream.observe().flatFilter((path) ->
  _.wrapCallback(fs.stat)(path).map (v) ->
    v.isDirectory()
)
# Connect up the merge point now that we have all of our streams.
mergePoint.write directory
mergePoint.write returnPipe
mergePoint.end()
# Release backpressure.  This will print files as they are discovered
out.each H.log
# Another way would be to queue them all up and then print them all out at once.
# out.toArray((files)-> console.log(files))