从MongoDB 3.2版本开始，你可以使用$sample聚合管道操作符从集合中随机获得N个文档:

// Get one random document from the mycoll collection.
db.mycoll.aggregate([{ $sample: { size: 1 } }])

如果你想从集合的筛选子集中选择随机文档，在管道中预先添加$match阶段:

// Get one random document matching {a: 10} from the mycoll collection.
db.mycoll.aggregate([
    { $match: { a: 10 } },
    { $sample: { size: 1 } }
])

正如注释中所指出的，当size大于1时，返回的文档样例中可能有重复项。

MongoDB现在有$rand

要选择n个非重复项，请使用{$addFields: {_f: {$rand:{}}}}进行聚合，然后按_f进行$sort和$limit n。

这工作得很好，它是快速的，适用于多个文档，不需要填充rand字段，它最终会填充自己:

向集合上的.rand字段添加索引 使用查找和刷新，如下所示:

// Install packages:
//   npm install mongodb async
// Add index in mongo:
//   db.ensureIndex('mycollection', { rand: 1 })

var mongodb = require('mongodb')
var async = require('async')

// Find n random documents by using "rand" field.
function findAndRefreshRand (collection, n, fields, done) {
  var result = []
  var rand = Math.random()

  // Append documents to the result based on criteria and options, if options.limit is 0 skip the call.
  var appender = function (criteria, options, done) {
    return function (done) {
      if (options.limit > 0) {
        collection.find(criteria, fields, options).toArray(
          function (err, docs) {
            if (!err && Array.isArray(docs)) {
              Array.prototype.push.apply(result, docs)
            }
            done(err)
          }
        )
      } else {
        async.nextTick(done)
      }
    }
  }

  async.series([

    // Fetch docs with unitialized .rand.
    // NOTE: You can comment out this step if all docs have initialized .rand = Math.random()
    appender({ rand: { $exists: false } }, { limit: n - result.length }),

    // Fetch on one side of random number.
    appender({ rand: { $gte: rand } }, { sort: { rand: 1 }, limit: n - result.length }),

    // Continue fetch on the other side.
    appender({ rand: { $lt: rand } }, { sort: { rand: -1 }, limit: n - result.length }),

    // Refresh fetched docs, if any.
    function (done) {
      if (result.length > 0) {
        var batch = collection.initializeUnorderedBulkOp({ w: 0 })
        for (var i = 0; i < result.length; ++i) {
          batch.find({ _id: result[i]._id }).updateOne({ rand: Math.random() })
        }
        batch.execute(done)
      } else {
        async.nextTick(done)
      }
    }

  ], function (err) {
    done(err, result)
  })
}

// Example usage
mongodb.MongoClient.connect('mongodb://localhost:27017/core-development', function (err, db) {
  if (!err) {
    findAndRefreshRand(db.collection('profiles'), 1024, { _id: true, rand: true }, function (err, result) {
      if (!err) {
        console.log(result)
      } else {
        console.error(err)
      }
      db.close()
    })
  } else {
    console.error(err)
  }
})

ps.如何在mongodb问题中找到随机记录被标记为此问题的副本。不同之处在于，这个问题明确地询问单个记录，而另一个问题明确地询问随机文档。

我对php的解决方案:

/**
 * Get random docs from Mongo
 * @param $collection
 * @param $where
 * @param $fields
 * @param $limit
 * @author happy-code
 * @url happy-code.com
 */
private function _mongodb_get_random (MongoCollection $collection, $where = array(), $fields = array(), $limit = false) {

    // Total docs
    $count = $collection->find($where, $fields)->count();

    if (!$limit) {
        // Get all docs
        $limit = $count;
    }

    $data = array();
    for( $i = 0; $i < $limit; $i++ ) {

        // Skip documents
        $skip = rand(0, ($count-1) );
        if ($skip !== 0) {
            $doc = $collection->find($where, $fields)->skip($skip)->limit(1)->getNext();
        } else {
            $doc = $collection->find($where, $fields)->limit(1)->getNext();
        }

        if (is_array($doc)) {
            // Catch document
            $data[ $doc['_id']->{'$id'} ] = $doc;
            // Ignore current document when making the next iteration
            $where['_id']['$nin'][] = $doc['_id'];
        }

        // Every iteration catch document and decrease in the total number of document
        $count--;

    }

    return $data;
}

如果没有数据，这是很困难的。_id字段是什么?它们是mongodb对象id吗?如果是这样，你可以得到最大值和最小值:

lowest = db.coll.find().sort({_id:1}).limit(1).next()._id;
highest = db.coll.find().sort({_id:-1}).limit(1).next()._id;

然后，如果你假设id是均匀分布的(但它们不是，但至少这是一个开始):

unsigned long long L = first_8_bytes_of(lowest)
unsigned long long H = first_8_bytes_of(highest)

V = (H - L) * random_from_0_to_1();
N = L + V;
oid = N concat random_4_bytes();

randomobj = db.coll.find({_id:{$gte:oid}}).limit(1);

对所有记录进行计数，生成一个0到计数之间的随机数，然后执行:

db.yourCollection.find().limit(-1).skip(yourRandomNumber).next()