php小偷程序新概念之实时更新（二）

前一篇讲到了如何将资源本地化，这篇博文将讲述如何资源本地化的同时实时更新。

二级页面，文章页面要实时更新其实没有什么必要，只要定时或者稳定间隔时间更新页面就行了。方法有如下几种：

1，利用cookie或者session定时或者间隔时间重新生成页面和文件

2，当生成的文件大小超过一定量（如150M）时，删除文件重新生成。

由于我用的是虚拟空间，以节约成本角度出发我用的是第二种方法。

下面几个方法能达到要求：

           public function content(){
		//session_start();
		$address = ltrim($this->address, '/');
		if(file_exists($address))
		{//echo $this->address;exit;
			/*$session_name = "cache_time_html";
			 if($_COOKIE[$session_name])
			 {
				$show_data = '';
				$grab_caches_time =  Cookie::get($session_name);
				if((time() - $grab_caches_time) > $this->cache_time_html)
				{//echo time() - $grab_caches_time;exit;
				$_COOKIE[$session_name] = null;
				unset($_COOKIE[$session_name]);
				self::creat_html();
				}
				else
				{//echo time() - $grab_caches_time;exit;
				$show_data = @file_get_contents(ltrim($this->address, '/'));
				print_r($show_data);
				exit;
				}
				}
				else
				{
				Cookie::set($session_name, time());
				self::creat_html();
				}*/
			$show_data = @file_get_contents(ltrim($this->address, '/'));
			print_r($show_data);
			exit;
		}
		else
		{  //echo 2;exit;
			self::creat_html();
		}
	}
	/**
	 * 生成静态页面
	 */
	private function creat_html()
	{
		//echo $this->html_address;exit;
		$content = $this->grap->curl_get_content($this->html_address);
		if(!$content) $content = @file_get_contents($this->html_address);
		if($content)
		{
			//替换删除内容
			$param1 = '/<div\s+?class="w">\s+?友情链接:(.*)<\/div>/isU';
			$param2 = '/<form  action="" method="post" id="Re_comment" name="CatRecom">(.*)<\/form>/isU';
			$param3 = '/<div class="none">(.*)<\/div>/isU';
			$param = array($param1, $param2, $param3);
			$this->grap->replace_preg($content, $param);
			$replace = array('网站导航', '收藏本站', '[<a href="/login.html">登陆</a>|<a href="/register.html">注册</a>]');
			$this->grap->replace_preg($content, $replace, '1', '0');
			//保存图片到本地
			$image_place = array('');
			$replace = array('' => '');
			$this->grap->get_image($content, $this->sorce_url, "/public/images", $image_place, $replace);
			//保存css到本地
			$this->grap->get_css($content, $this->sorce_url, "/public/images");//print_r($content);exit;
			//保存js到本地
			$this->grap->get_js($content, $this->sorce_url, "/public/images");
			//处理页面超链接
			self::href_oprate($content);
			//生成文件夹
			$this->grap->get_file_adress($this->address);
			$address = ltrim($this->address, '/');
			/*$files = fopen($address, 'w');
			 fwrite($file, $content);
			 fclose($file);*/
			@file_put_contents($address, $content);
			print_r($content);exit;
		}
		else
		{
			echo '没有获取到页面内容，请刷新重试！';
		}
	}
	/**
	 * 处理页面超链接
	 *
	 * @param srting $content
	 */
	private function href_oprate(&$content)
	{
		$content = str_replace($this->sorce_url, '', $content);
		$zx_patton = array(
			    '',
		);
		$zx_replace = array(
			    '',
		);
		$content = str_replace($zx_patton, $zx_replace, $content);
		@preg_match_all("/<a([^>]*)/i",$content,$match);
		$href = $match['1'];
		foreach ($href as $key => $val)
		{
			if(!stristr($val, 'href')) continue;
			if(stristr($val, "http://") || stristr($val, "https://") || stristr($val, "/login.html") || stristr($val, "/register.html") || stristr($val, ".php"))
			{
				$content = str_replace($val, '', $content);
			}
			if(!stristr($val, "javascript"))
			{
				$fg = stristr($val, 'href="') ? 'href="' : "href='";
				$arr_url = explode($fg, $val);
				$arr_url['1'] = trim($arr_url['1']);
				if(substr($arr_url['1'], 0, 1) == '"' && substr($arr_url['1'], 0, 1) == "'") continue;
				if(substr($arr_url['1'], 0, 1) == '/')
				{
					if(substr($arr_url['1'], 0, 2) !== '/"' && substr($arr_url['1'], 0, 2) !== "/'")
					{
						$arr_url['1'] = substr($arr_url['1'], 0, 1) != '/' ? '/html/'.$arr_url['1'] : '/html'.$arr_url['1'] ;
					}
					$new_url = implode($arr_url, $fg);//echo $val.'||'.$new_url.'<hr>';

					$content = str_replace($val, $new_url, $content);
				}
			}
		}//exit;
	}

实例演示： http://news.80jiaju.com/