PHP爬虫两篇转载

http://hi.baidu.com/xiaojiang/item/774af38966cf44ca98255ff0

classCurlComponent{var $headers;var $user_agent;var $compression;var $COOKIE_file;var $proxy;functionset_value($COOKIEs&＃61;TRUE,$COOKIE&＃61;&＃39;COOKIEs.txt&＃39;,$compression&＃61;&＃39;gzip&＃39;,$proxy&＃61;&＃39;&＃39;) {$this->headers[] &＃61; "Accept: image/gif, image/x-bitmap, image/jpeg, image/pjpeg";$this->headers[] &＃61; "Connection: Keep-Alive";$this->headers[] &＃61; "Content-type: application/x-www-form-urlencoded";$this->user_agent &＃61; "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; .NET CLR 1.0.3705; .NET CLR 1.1.4322; Media Center PC 4.0)";$this->compression&＃61;$compression;$this->proxy&＃61;$proxy;$this->COOKIEs&＃61;$COOKIEs;if ($this->COOKIEs &＃61;&＃61; TRUE) $this->COOKIE($COOKIE);}functionCOOKIE($COOKIE_file) {if (file_exists($COOKIE_file)) {$this->COOKIE_file&＃61;$COOKIE_file;} else {&＃64;fopen($COOKIE_file,&＃39;w&＃39;)or$this->error("The COOKIE file could not be opened. Make sure this directory has the correct permissions");$this->COOKIE_file&＃61;$COOKIE_file;&＃64;fclose($COOKIE_file);}}functionget($url,$refer&＃61;&＃39;&＃39;) {$process &＃61;curl_init($url);curl_setopt($process,CURLOPT_REFERER, $refer);curl_setopt($process,CURLOPT_HTTPHEADER, $this->headers);curl_setopt($process,CURLOPT_USERAGENT, $this->user_agent);if ($this->COOKIEs &＃61;&＃61; TRUE)curl_setopt($process,CURLOPT_COOKIEFILE, $this->COOKIE_file);if ($this->COOKIEs &＃61;&＃61; TRUE)curl_setopt($process,CURLOPT_COOKIEJAR, $this->COOKIE_file);curl_setopt($process,CURLOPT_ENCODING, $this->compression);curl_setopt($process,CURLOPT_TIMEOUT, 30000);if ($this->proxy)curl_setopt($cUrl,CURLOPT_PROXY, &＃39;proxy_ip:proxy_port&＃39;);curl_setopt($process,CURLOPT_RETURNTRANSFER, 1);$return &＃61;curl_exec($process);curl_close($process);return $return;}functionpost($url,$data,$refer) {$process &＃61;curl_init($url);curl_setopt($process,CURLOPT_REFERER, $refer);curl_setopt($process,CURLOPT_HTTPHEADER, $this->headers);curl_setopt($process,CURLOPT_USERAGENT, $this->user_agent);if ($this->COOKIEs &＃61;&＃61; TRUE)curl_setopt($process,CURLOPT_COOKIEFILE, $this->COOKIE_file);if ($this->COOKIEs &＃61;&＃61; TRUE)curl_setopt($process,CURLOPT_COOKIEJAR, $this->COOKIE_file);curl_setopt($process,CURLOPT_ENCODING, $this->compression);curl_setopt($process,CURLOPT_TIMEOUT, 30000);if ($this->proxy)curl_setopt($cUrl,CURLOPT_PROXY, &＃39;proxy_ip:proxy_port&＃39;);curl_setopt($process,CURLOPT_POSTFIELDS, $data);curl_setopt($process,CURLOPT_RETURNTRANSFER, 1);curl_setopt($process,CURLOPT_FOLLOWLOCATION, 1);curl_setopt($process,CURLOPT_POST, 1);$return &＃61;curl_exec($process);curl_close($process);return $return;}functionerror($error) {echo "

http://www.hdj.me/get-COOKIE-without-COOKIEjar-by-curl

PHP中CURL类是一个非常牛逼的工具类&＃xff0c;具体怎么牛逼就不啰嗦了。
对于COOKIE&＃xff0c;CURL类也有很不错的支持&＃xff0c;但不够灵活&＃xff0c;并未能通过现成的方法以变量的方法获取到&＃xff0c;而以要通过以下方法实现。

先把COOKIE保存文件&＃xff0c;调用的时候还得读取文件&＃xff0c;这样意味着两次的IO操作&＃xff0c;效率如何&＃xff0c;不用说大家都清楚了。
那么有没有办法可以绕过写读文件呢&＃xff1f;不卖关子&＃xff0c;直接上代码&＃xff1a;

// 初始化CURL
$ch&＃61; curl_init();
curl_setopt($ch, CURLOPT_URL,$url);
// 获取头部信息
curl_setopt($ch, CURLOPT_HEADER, 1);
// 返回原生的&＃xff08;Raw&＃xff09;输出
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
// 执行并获取返回结果
$content&＃61; curl_exec($ch);
// 关闭CURL
curl_close($ch);
// 解析HTTP数据流
list($header,$body) &＃61;explode("\r\n\r\n",$content);
// 解析COOKIE
preg_match("/set\-COOKIE:([^\r\n]*)/i",$header,$matches);
// 后面用CURL提交的时候可以直接使用
// curl_setopt($ch, CURLOPT_COOKIE, $COOKIE);
$COOKIE&＃61; $matches[1];

打完收工&＃xff01;欢迎大家来喷&＃xff01;