如何缓存远程视频

Question

我想播放远程服务器上的视频。所以我写了这个函数。$remoteFile = 'blabla.com/video_5GB.mp4';play($remoteFile);function play($url){    ini_set('memory_limit', '1024M');    set_time_limit(3600);    ob_start();    if (isset($_SERVER['HTTP_RANGE'])) $opts['http']['header'] = "Range: " . $_SERVER['HTTP_RANGE'];    $opts['http']['method'] = "HEAD";    $conh = stream_context_create($opts);    $opts['http']['method'] = "GET";    $cong = stream_context_create($opts);    $out[] = file_get_contents($url, false, $conh);    $out[] = $httap_response_header;    ob_end_clean();    array_map("header", $http_response_header);    readfile($url, false, $cong);}上面的功能在播放视频时效果很好。但我不想增加远程服务器的负担我的问题是如何每 5 小时将视频文件缓存到我的服务器上。如果可能，缓存文件夹包含来自远程视频的小文件（5MB / 10MB）

Answer 1

正如我在评论中提到的，以下代码仅在一小部分 MP4 文件上进行了测试。它可能需要做更多的工作，但它确实满足了您的即时需求。

它使用 exec() 生成一个单独的进程，在需要时（即在第一次请求时或 5 小时后）生成缓存文件。每个视频必须有自己的缓存文件夹，因为缓存的块简称为 1、2、3 等。请参阅代码中的其他注释。

play.php - 这是用户从浏览器调用的脚本

<?php

ini_set('memory_limit', '1024M');

set_time_limit(3600);

$remoteFile = 'blabla.com/video_5GB.mp4';

play($remoteFile);

/**

 * @param string $url

 *

 * This will serve the video from the remote url

 */

function playFromRemote($url)

{

  ob_start();

  $opts = array();

  if(isset($_SERVER['HTTP_RANGE']))

  {

    $opts['http']['header'] = "Range: ".$_SERVER['HTTP_RANGE'];

  }

  $opts['http']['method'] = "HEAD";

  $conh = stream_context_create($opts);

  $opts['http']['method'] = "GET";

  $cong = stream_context_create($opts);

  $out[] = file_get_contents($url, false, $conh);

  $out[] = $http_response_header;

  ob_end_clean();

  $fh = fopen('response.log', 'a');

  if($fh !== false)

  {

    fwrite($fh, print_r($http_response_header, true)."\n\n\n\n");

    fclose($fh);

  }

  array_map("header", $http_response_header);

  readfile($url, false, $cong);

}

/**

 * @param string $cacheFolder Directory in which to find the cached chunk files

 * @param string $url

 *

 * This will serve the video from the cache, it uses a "completed.log" file which holds the byte ranges of each chunk

 * this makes it easier to locate the first chunk of a range request. The file is generated by the cache script

 */

function playFromCache($cacheFolder, $url)

{

  $bytesFrom = 0;

  $bytesTo = 0;

  if(isset($_SERVER['HTTP_RANGE']))

  {

    //the client asked for a specific range, extract those from the http_range server var

    //can take the form "bytes=123-567" or just a from "bytes=123-"

    $matches = array();

    if(preg_match('/^bytes=(\d+)-(\d+)?$/', $_SERVER['HTTP_RANGE'], $matches))

    {

      $bytesFrom = intval($matches[1]);

      if(!empty($matches[2]))

      {

        $bytesTo = intval($matches[2]);

      }

    }

  }

  //completed log is a json_encoded file containing an array or byte ranges that directly

  //correspond with the chunk files generated by the cache script

  $log = json_decode(file_get_contents($cacheFolder.DIRECTORY_SEPARATOR.'completed.log'));

  $totalBytes = 0;

  $chunk = 0;

  foreach($log as $ind => $bytes)

  {

    //find the first chunk file we need to open

    if($bytes[0] <= $bytesFrom && $bytes[1] > $bytesFrom)

    {

      $chunk = $ind + 1;

    }

    //and while we are at it save the last byte range "to" which is the total number of bytes of all the chunk files

    $totalBytes = $bytes[1];

  }

  if($bytesTo === 0)

  {

    if($totalBytes === 0)

    {

      //if we get here then something is wrong with the cache, revert to serving from the remote

      playFromRemote($url);

      return;

    }

    $bytesTo = $totalBytes - 1;

  }

  //calculate how many bytes will be returned in this request

  $contentLength = $bytesTo - $bytesFrom + 1;

  //send some headers - I have hardcoded MP4 here because that is all I have developed with

  //if you are using different video formats then testing and changes will no doubt be required

  header('Content-Type: video/mp4');

  header('Content-Length: '.$contentLength);

  header('Accept-Ranges: bytes');

  //Send a header so we can recognise that the content was indeed served by the cache

  header('X-Cached-Date: '.(date('Y-m-d H:i:s', filemtime($cacheFolder.DIRECTORY_SEPARATOR.'completed.log'))));

  if($bytesFrom > 0)

  {

    //We are sending back a range so it needs a header and the http response must be 206: Partial Content

    header(sprintf('content-range: bytes %s-%s/%s', $bytesFrom, $bytesTo, $totalBytes));

    http_response_code(206);

  }

  $bytesSent = 0;

  while(is_file($cacheFolder.DIRECTORY_SEPARATOR.$chunk) && $bytesSent < $contentLength)

  {

    $cfh = fopen($cacheFolder.DIRECTORY_SEPARATOR.$chunk, 'rb');

    if($cfh !== false)

    {

      //if we are fetching a range then we might need to seek the correct starting point in the first chunk we look at

      //this check will be performed on all chunks but only the first one should need seeking so no harm done

      if($log[$chunk - 1][0] < $bytesFrom)

      {

        fseek($cfh, $bytesFrom - $log[$chunk - 1][0]);

      }

      //read and send data until the end of the file or we have sent what was requested

      while(!feof($cfh) && $bytesSent < $contentLength)

      {

        $data = fread($cfh, 1024);

        //check we are not going to be sending too much back and if we are then truncate the data to the correct length

        if($bytesSent + strlen($data) > $contentLength)

        {

          $data = substr($data, 0, $contentLength - $bytesSent);

        }

        $bytesSent += strlen($data);

        echo $data;

      }

      fclose($cfh);

    }

    //move to the next chunk

    $chunk ++;

  }

}

function play($url)

{

  //I have chosen a simple way to make a folder name, this can be improved any way you need

  //IMPORTANT: Each video must have its own cache folder

  $cacheFolder = sha1($url);

  if(!is_dir($cacheFolder))

  {

    mkdir($cacheFolder, 0755, true);

  }

  //First check if we are currently in the process of generating the cache and so just play from remote

  if(is_file($cacheFolder.DIRECTORY_SEPARATOR.'caching.log'))

  {

    playFromRemote($url);

  }

  //Otherwise check if we have never completed the cache or it was completed 5 hours ago and if so spawn a process to generate the cache

  elseif(!is_file($cacheFolder.DIRECTORY_SEPARATOR.'completed.log') || filemtime($cacheFolder.DIRECTORY_SEPARATOR.'completed.log') + (5 * 60 * 60) < time())

  {

    //fork the caching to a separate process - the & echo $! at the end causes the process to run as a background task

    //and print the process ID returning immediately

    //The cache script can be anywhere, pass the location to sprintf in the first position

    //A base64 encoded url is passed in as argument 1, sprintf second position

    $cmd = sprintf('php %scache.php %s & echo $!', __DIR__.DIRECTORY_SEPARATOR, base64_encode($url));

    $pid = exec($cmd);

    //with that started we need to serve the request from the remote url

    playFromRemote($url);

  }

  else

  {

    //if we got this far then we have a completed cache so serve from there

    playFromCache($cacheFolder, $url);

  }

}

cache.php - 该脚本将由 play.php 通过 exec() 调用

<?php

//This script expects as argument 1 a base64 encoded url

if(count($argv)!==2)

{

  die('Invalid Request!');

}

$url = base64_decode($argv[1]);

//make sure to use the same method of obtaining the cache folder name as the main play script

//or change the code to pass it in as an argument

$cacheFolder = sha1($url);

if(!is_dir($cacheFolder))

{

  die('Invalid Arguments!');

}

//double check it is not already running

if(is_file($cacheFolder.DIRECTORY_SEPARATOR.'caching.log'))

{

  die('Already Running');

}

//create a file so we know this has started, the file will be removed at the end of the script

file_put_contents($cacheFolder.DIRECTORY_SEPARATOR.'caching.log', date('d/m/Y H:i:s'));

//get rid of the old completed log

if(is_file($cacheFolder.DIRECTORY_SEPARATOR.'completed.log'))

{

  unlink($cacheFolder.DIRECTORY_SEPARATOR.'completed.log');

}

$bytesFrom = 0;

$bytesWritten = 0;

$totalBytes = 0;

//this is the size of the chunk files, currently 10MB

$maxSizeInBytes = 10 * 1024 * 1024;

$chunk = 1;

//open the url for binary reading and first chunk for binary writing

$fh = fopen($url, 'rb');

$cfh = fopen($cacheFolder.DIRECTORY_SEPARATOR.$chunk, 'wb');

if($fh !== false && $cfh!==false)

{

  $log = array();

  while(!feof($fh))

  {

    $data = fread($fh, 1024);

    fwrite($cfh, $data);

    $totalBytes += strlen($data); //use actual length here

    $bytesWritten += strlen($data);

    //if we are on or passed the chunk size then close the chunk and open a new one

    //keeping a log of the byte range of the chunk

    if($bytesWritten>=$maxSizeInBytes)

    {

      $log[$chunk-1] = array($bytesFrom,$totalBytes);

      $bytesFrom = $totalBytes;

      fclose($cfh);

      $chunk++;

      $bytesWritten = 0;

      $cfh = fopen($cacheFolder.DIRECTORY_SEPARATOR.$chunk, 'wb');

    }

  }

  fclose($fh);

  $log[$chunk-1] = array($bytesFrom,$totalBytes);

  fclose($cfh);

  //write the completed log. This is a json encoded string of the chunk byte ranges and will be used

  //by the play script to quickly locate the starting chunk of a range request

  file_put_contents($cacheFolder.DIRECTORY_SEPARATOR.'completed.log', json_encode($log));

  //finally remove the caching log so the play script doesn't think the process is still running

  unlink($cacheFolder.DIRECTORY_SEPARATOR.'caching.log');

}