PHP实例：利用PHP抓取百度阅读的方法示例

PHP实例
<?php
class BaiduYuedu {
 protected $bookId;
 protected $bookToken;
 protected $cookie;
 protected $result;
 public function __construct($bookId, $bookToken, $cookie){
  $this->bookId = $bookId;
  $this->bookToken = $bookToken;
  $this->cookie = $cookie;
 }
 public static function parseNode($node){
  $str = '';
  if(is_string($node['c'])){
   $str .= $node['c'];
  }else if(is_array($node['c'])){
   foreach($node['c'] as $d){
    $str .= self::parseNode($d);
   }
  }
  switch($node['t']){
   case 'h2':
    $str .= "\n\n";
    break;
   case 'br':
   case 'div':
   case 'p':
    $str .= "\n";
    break;
   case 'img':
   case 'span':
    break;
   case 'obj':
    $tmp = '(' . self::parseNode($node['data'][0]) . ')';
    $str .= str_replace("\n", '', $tmp);
    break;
   default:
    trigger_error('Unkown type:'.$node['t'], E_USER_WARNING);
    break;
  }
  return $str;
 }
 public function get($page = 1){
  echo "getting page {$page}...\n";
  $ch = curl_init();
  $url = sprintf('http://wenku.baidu.com/content/%s/?m=%s&type=json&cn=%d', $this->bookId, $this->token, $page);
  curl_setopt_array($ch, array(
   CURLOPT_URL   => $url,
   CURLOPT_RETURNTRANSFER => 1,
   CURLOPT_HEADER   => 0,
   CURLOPT_HTTPHEADER  => array('Cookie: '. $this->cookie)
  ));
  $ret = json_decode(curl_exec($ch), true);
  curl_close($ch);
  $str = '';
  if(!empty($ret)){
   $str .= self::parseNode($ret);
   $str .= $this->get($page + 1);
  }
  return $str;
 }
 public function start(){
  $this->result = $this->get();
 }
 public function getResult(){
  return $this->result;
 }
 public function saveTo($path){
  if(empty($this->result)){
   trigger_error('Result is empty', E_USER_ERROR);
   return;
  }
  file_put_contents($path, $this->result);
  echo "save to {$path}\n";
 }
}
//使用示例
$yuedu = new BaiduYuedu('49422a3769eae009581becba', '8ed1dedb240b11bf0731336eff95093f', '你的百度域cookie');
$yuedu->start();
$yuedu->saveTo('result.txt');