做采集的时候，可以使用file_get_contents()去获取网页源代码，但是使用file_get_contents采集，速度慢，而且超时时间，不好控制。如果采集的页面不存在，需要等待的时间很长。一般来说，curl的速度最快，其次是socket，最后是file_get_contents。
现在跟大家分享一个很强大的采集类，会根据你的服务器当前的配置，自动选择最快的方式。已经封装了curl和socket，file_get_contents
用法很简单：
1、采用get方法请求
Http::doGet(网址);//超市时间可忽略，默认是5秒
Http::doGet(网址,超时时间);
如echo Http::doGet('http://www.baidu.com');
2、采用post方法请求
Http::doPost(网址,数据,超时时间);
如
$url='http://www.canphp.com/test.php';
$data['name']='单骑';
$data['email']='admin@canphp.com';
Http::doPost($url,$data,10);
test.php页面接收数据
$_POST['name'];
$_POST['email'];
这个http类不仅可以用来采集，还有一个很强大的作用，模拟php异步多进程。
比如有index.php和a.php, b.php, c.php
在index.php中
Http::doGet('http://www.canphp.com/a.php',1);
Http::doGet('http://www.canphp.com/b.php',1);
Http::doGet('http://www.canphp.com/c.php',1);
a.php, b.php, c.php程序分别在头部加上ignore_user_abort(true);
那么就可以实现多进程了。
原理：
通过curl或socket发送请求给a.php, b.php, c.php，由于超时时间比较短，只是触发了a.php, b.php, c.php三个页面，不需要等待数据返回，连接已中断，但是a.php, b.php, c.php程序中加上了ignore_user_abort(true);忽略客户端连接，还会继续执行。
<?php // 数据采集，doGET,doPOST,文件下载， class Http { static public $way = 0; // 手动设置访问方式 static public function setWay($way) { self :: $way = intval($way); } static public function getSupport() { // 如果指定访问方式，则按指定的方式去访问 if (isset(self :: $way) && in_array(self :: $way, array(1, 2, 3))) return self :: $way; // 自动获取最佳访问方式 if (function_exists('curl_init')) { // curl方式 return 1; } else if (function_exists('fsockopen')) { // socket return 2; } else if (function_exists('file_get_contents')) { // php系统函数file_get_contents return 3; } else { return 0; } } // 通过get方式获取数据 static public function doGet($url, $timeout = 5, $header = "") { if (empty($url) || empty($timeout)) return false; if (!preg_match('/^(http|https)/is', $url)) $url = "http://" . $url; $code = self :: getSupport(); switch ($code) { case 1:return self :: curlGet($url, $timeout, $header); break; case 2:return self :: socketGet($url, $timeout, $header); break; case 3:return self :: phpGet($url, $timeout, $header); break; default:return false; } } // 通过POST方式发送数据 static public function doPost($url, $post_data = array(), $timeout = 5, $header = "") { if (empty($url) || empty($post_data) || empty($timeout)) return false; if (!preg_match('/^(http|https)/is', $url)) $url = "http://" . $url; $code = self :: getSupport(); switch ($code) { case 1:return self :: curlPost($url, $post_data, $timeout, $header); break; case 2:return self :: socketPost($url, $post_data, $timeout, $header); break; case 3:return self :: phpPost($url, $post_data, $timeout, $header); break; default:return false; } } // 通过curl get数据 static public function curlGet($url, $timeout = 5, $header = "") { $header = empty($header)?self :: defaultHeader():$header; $ch = curl_init(); curl_setopt($ch, CURLOPT_URL, $url); curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, $timeout); curl_setopt($ch, CURLOPT_TIMEOUT, $timeout); curl_setopt($ch, CURLOPT_HTTPHEADER, array($header)); //模拟的header头 $result = curl_exec($ch); curl_close($ch); return $result; } // 通过curl post数据 static public function curlPost($url, $post_data = array(), $timeout = 5, $header = "") { $header = empty($header)?'':$header; $post_string = http_build_query($post_data); $ch = curl_init(); curl_setopt($ch, CURLOPT_POST, true); curl_setopt($ch, CURLOPT_POSTFIELDS, $post_string); curl_setopt($ch, CURLOPT_URL, $url); curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, $timeout); curl_setopt($ch, CURLOPT_TIMEOUT, $timeout); curl_setopt($ch, CURLOPT_HTTPHEADER, array($header)); //模拟的header头 $result = curl_exec($ch); curl_close($ch); return $result; } // 通过socket get数据 static public function socketGet($url, $timeout = 5, $header = "") { $header = empty($header)?self :: defaultHeader():$header; $url2 = parse_url($url); $url2["path"] = isset($url2["path"])? $url2["path"]: "/" ; $url2["port"] = isset($url2["port"])? $url2["port"] : 80; $url2["query"] = isset($url2["query"])? "?" . $url2["query"] : ""; $host_ip = @gethostbyname($url2["host"]); if (($fsock = fsockopen($host_ip, $url2['port'], $errno, $errstr, $timeout)) < 0) { return false; } $request = $url2["path"] . $url2["query"]; $in = "GET " . $request . " HTTP/1.0 "; if (false === strpos($header, "Host:")) { $in .= "Host: " . $url2["host"] . " "; } $in .= $header; $in .= "Connection: Close "; if (!@fwrite($fsock, $in, strlen($in))) { @fclose($fsock); return false; } return self :: GetHttpContent($fsock); } // 通过socket post数据 static public function socketPost($url, $post_data = array(), $timeout = 5, $header = "") { $header = empty($header)?self :: defaultHeader():$header; $post_string = http_build_query($post_data); $url2 = parse_url($url); $url2["path"] = ($url2["path"] == "" ? "/" : $url2["path"]); $url2["port"] = ($url2["port"] == "" ? 80 : $url2["port"]); $host_ip = @gethostbyname($url2["host"]); $fsock_timeout = $timeout; //超时时间 if (($fsock = fsockopen($host_ip, $url2['port'], $errno, $errstr, $fsock_timeout)) < 0) { return false; } $request = $url2["path"] . ($url2["query"] ? "?" . $url2["query"] : ""); $in = "POST " . $request . " HTTP/1.0 "; $in .= "Host: " . $url2["host"] . " "; $in .= $header; $in .= "Content-type: application/x-www-form-urlencoded "; $in .= "Content-Length: " . strlen($post_string) . " "; $in .= "Connection: Close "; $in .= $post_string . " "; unset($post_string); if (!@fwrite($fsock, $in, strlen($in))) { @fclose($fsock); return false; } return self :: GetHttpContent($fsock); } // 通过file_get_contents函数get数据 static public function phpGet($url, $timeout = 5, $header = "") { $header = empty($header)?self :: defaultHeader():$header; $opts = array( 'http' => array('protocol_version' => '1.0', // http协议版本(若不指定php5.2系默认为http1.0) 'method' => "GET", // 获取方式 'timeout' => $timeout , // 超时时间 'header' => $header) ); $context = stream_context_create($opts); return @file_get_contents($url, false, $context); } // 通过file_get_contents 函数post数据 static public function phpPost($url, $post_data = array(), $timeout = 5, $header = "") { $header = empty($header)?self :: defaultHeader():$header; $post_string = http_build_query($post_data); $header .= "Content-length: " . strlen($post_string); $opts = array('http' => array( 'protocol_version' => '1.0', // http协议版本(若不指定php5.2系默认为http1.0) 'method' => "POST", // 获取方式 'timeout' => $timeout , // 超时时间 'header' => $header, 'content' => $post_string) ); $context = stream_context_create($opts); return @file_get_contents($url, false, $context); } // 默认模拟的header头 static private function defaultHeader() { $header = "User-Agent:Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9.2.12) Gecko/20101026 Firefox/3.6.12 "; $header .= "Accept:text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8 "; $header .= "Accept-language: zh-cn,zh;q=0.5 "; $header .= "Accept-Charset: GB2312,utf-8;q=0.7,*;q=0.7 "; return $header; } // 获取通过socket方式get和post页面的返回数据 static private function GetHttpContent($fsock = null) { $out = null; while ($buff = @fgets($fsock, 2048)) { $out .= $buff; } fclose($fsock); $pos = strpos($out, " "); $head = substr($out, 0, $pos); //http head $status = substr($head, 0, strpos($head, " ")); //http status line $body = substr($out, $pos + 4, strlen($out) - ($pos + 4)); //page body if (preg_match("/^HTTP/d.ds([d]+)s.*$/", $status, $matches)) { if (intval($matches[1]) / 100 == 2) { return $body; } else { return false; } } else { return false; } } /** * 功能： 下载文件 * 参数:$filename 下载文件路径 * $showname 下载显示的文件名 * $expire 下载内容浏览器缓存时间 */ static public function download($filename, $showname = '', $expire = 1800) { if (file_exists($filename) && is_file($filename)) { $length = filesize($filename); } else { die('下载文件不存在！'); } $type = mime_content_type($filename); // 发送Http Header信息 开始下载 header("Pragma: public"); header("Cache-control: max-age=" . $expire); // header('Cache-Control: no-store, no-cache, must-revalidate'); header("Expires: " . gmdate("D, d M Y H:i:s", time() + $expire) . "GMT"); header("Last-Modified: " . gmdate("D, d M Y H:i:s", time()) . "GMT"); header("Content-Disposition: attachment; filename=" . $showname); header("Content-Length: " . $length); header("Content-type: " . $type); header('Content-Encoding: none'); header("Content-Transfer-Encoding: binary"); readfile($filename); return true; } } if (!function_exists ('mime_content_type')) { /** * +---------------------------------------------------------- * 获取文件的mime_content类型 * +---------------------------------------------------------- * * @return string +---------------------------------------------------------- */ function mime_content_type($filename) { static $contentType = array( 'ai' => 'application/postscript', 'aif' => 'audio/x-aiff', 'aifc' => 'audio/x-aiff', 'aiff' => 'audio/x-aiff', 'asc' => 'application/pgp', // changed by skwashd - was text/plain 'asf' => 'video/x-ms-asf', 'asx' => 'video/x-ms-asf', 'au' => 'audio/basic', 'avi' => 'video/x-msvideo', 'bcpio' => 'application/x-bcpio', 'bin' => 'application/octet-stream', 'bmp' => 'image/bmp', 'c' => 'text/plain', // or 'text/x-csrc', //added by skwashd 'cc' => 'text/plain', // or 'text/x-c++src', //added by skwashd 'cs' => 'text/plain', // added by skwashd - for C# src 'cpp' => 'text/x-c++src', // added by skwashd 'cxx' => 'text/x-c++src', // added by skwashd 'cdf' => 'application/x-netcdf', 'class' => 'application/octet-stream', // secure but application/java-class is correct 'com' => 'application/octet-stream', // added by skwashd 'cpio' => 'application/x-cpio', 'cpt' => 'application/mac-compactpro', 'csh' => 'application/x-csh', 'css' => 'text/css', 'csv' => 'text/comma-separated-values', // added by skwashd 'dcr' => 'application/x-director', 'diff' => 'text/diff', 'dir' => 'application/x-director', 'dll' => 'application/octet-stream', 'dms' => 'application/octet-stream', 'doc' => 'application/msword', 'dot' => 'application/msword', // added by skwashd 'dvi' => 'application/x-dvi', 'dxr' => 'application/x-director', 'eps' => 'application/postscript', 'etx' => 'text/x-setext', 'exe' => 'application/octet-stream', 'ez' => 'application/andrew-inset', 'gif' => 'image/gif', 'gtar' => 'application/x-gtar', 'gz' => 'application/x-gzip', 'h' => 'text/plain', // or 'text/x-chdr',//added by skwashd 'h++' => 'text/plain', // or 'text/x-c++hdr', //added by skwashd 'hh' => 'text/plain', // or 'text/x-c++hdr', //added by skwashd 'hpp' => 'text/plain', // or 'text/x-c++hdr', //added by skwashd 'hxx' => 'text/plain', // or 'text/x-c++hdr', //added by skwashd 'hdf' => 'application/x-hdf', 'hqx' => 'application/mac-binhex40', 'htm' => 'text/html', 'html' => 'text/html', 'ice' => 'x-conference/x-cooltalk', 'ics' => 'text/calendar', 'ief' => 'image/ief', 'ifb' => 'text/calendar', 'iges' => 'model/iges', 'igs' => 'model/iges', 'jar' => 'application/x-jar', // added by skwashd - alternative mime type 'java' => 'text/x-java-source', // added by skwashd 'jpe' => 'image/jpeg', 'jpeg' => 'image/jpeg', 'jpg' => 'image/jpeg', 'js' => 'application/x-javascript', 'kar' => 'audio/midi', 'latex' => 'application/x-latex', 'lha' => 'application/octet-stream', 'log' => 'text/plain', 'lzh' => 'application/octet-stream', 'm3u' => 'audio/x-mpegurl', 'man' => 'application/x-troff-man', 'me' => 'application/x-troff-me', 'mesh' => 'model/mesh', 'mid' => 'audio/midi', 'midi' => 'audio/midi', 'mif' => 'application/vnd.mif', 'mov' => 'video/quicktime', 'movie' => 'video/x-sgi-movie', 'mp2' => 'audio/mpeg', 'mp3' => 'audio/mpeg', 'mpe' => 'video/mpeg', 'mpeg' => 'video/mpeg', 'mpg' => 'video/mpeg', 'mpga' => 'audio/mpeg', 'ms' => 'application/x-troff-ms', 'msh' => 'model/mesh', 'mxu' => 'video/vnd.mpegurl', 'nc' => 'application/x-netcdf', 'oda' => 'application/oda', 'patch' => 'text/diff', 'pbm' => 'image/x-portable-bitmap', 'pdb' => 'chemical/x-pdb', 'pdf' => 'application/pdf', 'pgm' => 'image/x-portable-graymap', 'pgn' => 'application/x-chess-pgn', 'pgp' => 'application/pgp', // added by skwashd 'php' => 'application/x-httpd-php', 'php3' => 'application/x-httpd-php3', 'pl' => 'application/x-perl', 'pm' => 'application/x-perl', 'png' => 'image/png', 'pnm' => 'image/x-portable-anymap', 'po' => 'text/plain', 'ppm' => 'image/x-portable-pixmap', 'ppt' => 'application/vnd.ms-powerpoint', 'ps' => 'application/postscript', 'qt' => 'video/quicktime', 'ra' => 'audio/x-realaudio', 'rar' => 'application/octet-stream', 'ram' => 'audio/x-pn-realaudio', 'ras' => 'image/x-cmu-raster', 'rgb' => 'image/x-rgb', 'rm' => 'audio/x-pn-realaudio', 'roff' => 'application/x-troff', 'rpm' => 'audio/x-pn-realaudio-plugin', 'rtf' => 'text/rtf', 'rtx' => 'text/richtext', 'sgm' => 'text/sgml', 'sgml' => 'text/sgml', 'sh' => 'application/x-sh', 'shar' => 'application/x-shar', 'shtml' => 'text/html', 'silo' => 'model/mesh', 'sit' => 'application/x-stuffit', 'skd' => 'application/x-koan', 'skm' => 'application/x-koan', 'skp' => 'application/x-koan', 'skt' => 'application/x-koan', 'smi' => 'application/smil', 'smil' => 'application/smil', 'snd' => 'audio/basic', 'so' => 'application/octet-stream', 'spl' => 'application/x-futuresplash', 'src' => 'application/x-wais-source', 'stc' => 'application/vnd.sun.xml.calc.template', 'std' => 'application/vnd.sun.xml.draw.template', 'sti' => 'application/vnd.sun.xml.impress.template', 'stw' => 'application/vnd.sun.xml.writer.template', 'sv4cpio' => 'application/x-sv4cpio', 'sv4crc' => 'application/x-sv4crc', 'swf' => 'application/x-shockwave-flash', 'sxc' => 'application/vnd.sun.xml.calc', 'sxd' => 'application/vnd.sun.xml.draw', 'sxg' => 'application/vnd.sun.xml.writer.global', 'sxi' => 'application/vnd.sun.xml.impress', 'sxm' => 'application/vnd.sun.xml.math', 'sxw' => 'application/vnd.sun.xml.writer', 't' => 'application/x-troff', 'tar' => 'application/x-tar', 'tcl' => 'application/x-tcl', 'tex' => 'application/x-tex', 'texi' => 'application/x-texinfo', 'texinfo' => 'application/x-texinfo', 'tgz' => 'application/x-gtar', 'tif' => 'image/tiff', 'tiff' => 'image/tiff', 'tr' => 'application/x-troff', 'tsv' => 'text/tab-separated-values', 'txt' => 'text/plain', 'ustar' => 'application/x-ustar', 'vbs' => 'text/plain', // added by skwashd - for obvious reasons 'vcd' => 'application/x-cdlink', 'vcf' => 'text/x-vcard', 'vcs' => 'text/calendar', 'vfb' => 'text/calendar', 'vrml' => 'model/vrml', 'vsd' => 'application/vnd.visio', 'wav' => 'audio/x-wav', 'wax' => 'audio/x-ms-wax', 'wbmp' => 'image/vnd.wap.wbmp', 'wbxml' => 'application/vnd.wap.wbxml', 'wm' => 'video/x-ms-wm', 'wma' => 'audio/x-ms-wma', 'wmd' => 'application/x-ms-wmd', 'wml' => 'text/vnd.wap.wml', 'wmlc' => 'application/vnd.wap.wmlc', 'wmls' => 'text/vnd.wap.wmlscript', 'wmlsc' => 'application/vnd.wap.wmlscriptc', 'wmv' => 'video/x-ms-wmv', 'wmx' => 'video/x-ms-wmx', 'wmz' => 'application/x-ms-wmz', 'wrl' => 'model/vrml', 'wvx' => 'video/x-ms-wvx', 'xbm' => 'image/x-xbitmap', 'xht' => 'application/xhtml+xml', 'xhtml' => 'application/xhtml+xml', 'xls' => 'application/vnd.ms-excel', 'xlt' => 'application/vnd.ms-excel', 'xml' => 'application/xml', 'xpm' => 'image/x-xpixmap', 'xsl' => 'text/xml', 'xwd' => 'image/x-xwindowdump', 'xyz' => 'chemical/x-xyz', 'z' => 'application/x-compress', 'zip' => 'application/zip', ); $type = strtolower(substr(strrchr($filename, '.'), 1)); if (isset($contentType[$type])) { $mime = $contentType[$type]; } else { $mime = 'application/octet-stream'; } return $mime; } } if (!function_exists('image_type_to_extension')) { function image_type_to_extension($imagetype) { if (empty($imagetype)) return false; switch ($imagetype) { case IMAGETYPE_GIF : return '.gif'; case IMAGETYPE_JPEG : return '.jpg'; case IMAGETYPE_PNG : return '.png'; case IMAGETYPE_SWF : return '.swf'; case IMAGETYPE_PSD : return '.psd'; case IMAGETYPE_BMP : return '.bmp'; case IMAGETYPE_TIFF_II : return '.tiff'; case IMAGETYPE_TIFF_MM : return '.tiff'; case IMAGETYPE_JPC : return '.jpc'; case IMAGETYPE_JP2 : return '.jp2'; case IMAGETYPE_JPX : return '.jpf'; case IMAGETYPE_JB2 : return '.jb2'; case IMAGETYPE_SWC : return '.swc'; case IMAGETYPE_IFF : return '.aiff'; case IMAGETYPE_WBMP : return '.wbmp'; case IMAGETYPE_XBM : return '.xbm'; default : return false; } } } ?>
方法：download($filename, $showname='',$expire=1800)
说明：用于下载文件
参数：
•$filename，包含路径的文件名
•$showname，下载显示的文件名，需要自行转成gbk编码，如果带空格，需要自行替换成其他字符
•$expire，下载内容浏览器缓存时间
使用方法：
1 |
$showname='最新资料.zip'; |
2 |
$showname=auto_charset($showname,'utf-8','gbk');//utf-8编码转成gbk编码 |
3 |
Http::download('upload/123.zip',$showname); |
方法：doGet($url,$timeout=5,$header='')
说明：采用get方法请求页面，会自动使用最快的访问方式，获取数据
参数：
•$url，网址
•$timeout，超时时间
•$header，http请求头，用于发送cookie等信息
使用方法：
1 |
echo Http::doGet('http://www.baidu.com'); |
方法：doPost($url,$data,$timeout=5,$header='')
说明：采用post方法请求页面，会自动使用最快的访问方式，获取数据
参数：
•$url，网址
•$data，待发送的数据，类型数组。
•$timeout，超时时间
•$header，http请求头，用于发送cookie等信息
使用方法：
1 |
$url='http://www.canphp.com/test.php'; |
2 |
$data['name']='单骑'; |
3 |
$data['email']='admin@canphp.com'; |
4 |
Http::doPost($url,$data,10); |
5 |
6 |
//test.php页面接收数据 |
7 |
$_POST['name']; |
8 |
$_POST['email']; |
方法：setWay($way)
说明：手动设置doGet()和doPost()访问方式
参数：
•$way：参数可以1或2或3
•参数1时：采用curl
•参数2时：采用socket
•参数3时：采用file_get_contents()函数模拟
•若不设置访问方式，会自动获取当前环境的支持方式，选择最佳的方式去访问，优先度curl > socket > file_get_contents
使用方法：
1 |
Http::setWay(3); |
2 |
echo Http::doGet('http://www.baidu.com');//将采用file_get_contents()方式获取内容 |