本页文章导读:

    ▪php header Content-Type类型小结       代码如下: <?php $mimetypes = array( 'ez' => 'application/andrew-inset', 'hqx' => 'application/mac-binhex40', 'cpt' => 'application/mac-compactpro', 'doc' => 'application/msword', 'bin' => 'application/octet-stream', 'dms' =>.........

    ▪php中关于codeigniter的xmlrpc的类在进行数据交换时的类型问题       客户端发送的请求类似这样 代码如下: $request = array('parameters00','parameters01'); 在客户端的请求你可以制定参数的数据类型，你可以将每个参数单独的放进一个数组，在数组的第二个位置制定.........

    ▪PHP采集利器 Snoopy 试用心得       Snoopy是什么? （下载snoopy） Snoopy是一个php类，用来模仿web浏览器的功能，它能完成获取网页内容和发送表单的任务。 Snoopy的一些特点: * 方便抓取网页的内容 * 方便抓取网页的文本内容 (去除.........

代码如下:

<?php
$mimetypes = array(
'ez' => 'application/andrew-inset',
'hqx' => 'application/mac-binhex40',
'cpt' => 'application/mac-compactpro',
'doc' => 'application/msword',
'bin' => 'application/octet-stream',
'dms' => 'application/octet-stream',
'lha' => 'application/octet-stream',
'lzh' => 'application/octet-stream',
'exe' => 'application/octet-stream',
'class' => 'application/octet-stream',
'so' => 'application/octet-stream',
'dll' => 'application/octet-stream',
'oda' => 'application/oda',
'pdf' => 'application/pdf',
'ai' => 'application/postscript',
'eps' => 'application/postscript',
'ps' => 'application/postscript',
'smi' => 'application/smil',
'smil' => 'application/smil',
'mif' => 'application/vnd.mif',
'xls' => 'application/vnd.ms-excel',
'ppt' => 'application/vnd.ms-powerpoint',
'wbxml' => 'application/vnd.wap.wbxml',
'wmlc' => 'application/vnd.wap.wmlc',
'wmlsc' => 'application/vnd.wap.wmlscriptc',
'bcpio' => 'application/x-bcpio',
'vcd' => 'application/x-cdlink',
'pgn' => 'application/x-chess-pgn',
'cpio' => 'application/x-cpio',
'csh' => 'application/x-csh',
'dcr' => 'application/x-director',
'dir' => 'application/x-director',
'dxr' => 'application/x-director',
'dvi' => 'application/x-dvi',
'spl' => 'application/x-futuresplash',
'gtar' => 'application/x-gtar',
'hdf' => 'application/x-hdf',
'js' => 'application/x-javascript',
'skp' => 'application/x-koan',
'skd' => 'application/x-koan',
'skt' => 'application/x-koan',
'skm' => 'application/x-koan',
'latex' => 'application/x-latex',
'nc' => 'application/x-netcdf',
'cdf' => 'application/x-netcdf',
'sh' => 'application/x-sh',
'shar' => 'application/x-shar',
'swf' => 'application/x-shockwave-flash',
'sit' => 'application/x-stuffit',
'sv4cpio' => 'application/x-sv4cpio',
'sv4crc' => 'application/x-sv4crc',
'tar' => 'application/x-tar',
'tcl' => 'application/x-tcl',
'tex' => 'application/x-tex',
'texinfo' => 'application/x-texinfo',
'texi' => 'application/x-texinfo',
't' => 'application/x-troff',
'tr' => 'application/x-troff',
'roff' => 'application/x-troff',
'man' => 'application/x-troff-man',
'me' => 'application/x-troff-me',
'ms' => 'application/x-troff-ms',
'ustar' => 'application/x-ustar',
'src' => 'application/x-wais-source',
'xhtml' => 'application/xhtml+xml',
'xht' => 'application/xhtml+xml',
'zip' => 'application/zip',
'au' => 'audio/basic',
'snd' => 'audio/basic',
'mid' => 'audio/midi',
'midi' => 'audio/midi',
'kar' => 'audio/midi',
'mpga' => 'audio/mpeg',
'mp2' => 'audio/mpeg',
'mp3' => 'audio/mpeg',
'aif' => 'audio/x-aiff',
'aiff' => 'audio/x-aiff',
'aifc' => 'audio/x-aiff',
'm3u' => 'audio/x-mpegurl',
'ram' => 'audio/x-pn-realaudio',
'rm' => 'audio/x-pn-realaudio',
'rpm' => 'audio/x-pn-realaudio-plugin',
'ra' => 'audio/x-realaudio',
'wav' => 'audio/x-wav',
'pdb' => 'chemical/x-pdb',
'xyz' => 'chemical/x-xyz',
'bmp' => 'image/bmp',
'gif' => 'image/gif',
'ief' => 'image/ief',
'jpeg' => 'image/jpeg',
'jpg' => 'image/jpeg',
'jpe' => 'image/jpeg',
'png' => 'image/png',
'tiff' => 'image/tiff',
'tif' => 'image/tiff',
'djvu' => 'image/vnd.djvu',
'djv' => 'image/vnd.djvu',
'wbmp' => 'image/vnd.wap.wbmp',
'ras' => 'image/x-cmu-raster',
'pnm' => 'image/x-portable-anymap',
'pbm' => 'image/x-portable-bitmap',
'pgm' => 'image/x-portable-graymap',
'ppm' => 'image/x-portable-pixmap',
'rgb' => 'image/x-rgb',
'xbm' => 'image/x-xbitmap',
'xpm' => 'image/x-xpixmap',
'xwd' => 'image/x-xwindowdump',
'igs' => 'model/iges',
'iges' => 'model/iges',
'msh' => 'model/mesh',
'mesh' => 'model/mesh',
'silo' => 'model/mesh',
'wrl' => 'model/vrml',
'vrml' => 'model/vrml',
'css' => 'text/css',
'html' => 'text/html',
'htm' => 'text/html',
'asc' => 'text/plain',
'txt' => 'text/plain',
'rtx' => 'text/richtext',
'rtf' => 'text/rtf',
'sgml' => 'text/sgml',
'sgm' => 'text/sgml',
'tsv' => 'text/tab-separated-values',
'wml' => 'text/vnd.wap.wml',
'wmls' => 'text/vnd.wap.wmlscript',
'etx' => 'text/x-setext',
'xsl' => 'text/xml',
'xml' => 'text/xml',
'mpeg' => 'video/mpeg',
'mpg' => 'video/mpeg',
'mpe' => 'video/mpeg',
'qt' => 'video/quicktime',
'mov' => 'video/quicktime',
'mxu' => 'video/vnd.mpegurl',
'avi' => 'video/x-msvideo',
'movie' => 'video/x-sgi-movie',
'ice' => 'x-conference/x-cooltalk',
);
?>

代码如下:

$request = array('parameters00','parameters01');

代码如下:

$request = array(
array('parameters00','string'),
array('parameters01','boolean'),
array('parameters02','struct'),
array('parameters03','int'),
);

代码如下:

$response = array(
array(parameters00 => array('para00','string'),
parameters01 => array('para01','struct'),
parameters02 => array('para02','boolean'),
),'struct');

代码如下:

$request = array(
array(
'parameters00' => array(array('paraoo' => 'value'),'struct'),
'parameters01' => array('para01','string'),
),'struct'
);

代码如下:

$url = "http://www.";
include("snoopy.php");
$snoopy = new Snoopy;
$snoopy->fetch($url); //获取所有内容
echo $snoopy->results; //显示结果
$snoopy->fetchtext //获取文本内容（去掉html代码）
$snoopy->fetchlinks //获取链接
$snoopy->fetchform //获取表单

代码如下:

$formvars["username"] = "admin";
$formvars["pwd"] = "admin";
$action = "http://www.";//表单提交地址
$snoopy->submit($action,$formvars);//$formvars为提交的数组
echo $snoopy->results; //获取表单提交后的 返回的结果
$snoopy->submittext; //提交后只返回 去除html的 文本
$snoopy->submitlinks;//提交后只返回 链接

代码如下:

$formvars["username"] = "admin";
$formvars["pwd"] = "admin";
$action = "http://www.";
include "snoopy.php";
$snoopy = new Snoopy;
$snoopy->cookies["PHPSESSID"] = 'fc106b1918bd522cc863f36890e6fff7'; //伪装sessionid
$snoopy->agent = "(compatible; MSIE 4.01; MSN 2.5; AOL 4.0; Windows 98)"; //伪装浏览器
$snoopy->referer = "http://s."; //伪装来源页地址 http_referer
$snoopy->rawheaders["Pragma"] = "no-cache"; //cache 的http头信息
$snoopy->rawheaders["X_FORWARDED_FOR"] = "127.0.0.101"; //伪装ip
$snoopy->submit($action,$formvars);
echo $snoopy->results;

代码如下:

$snoopy->proxy_host = "www.";
$snoopy->proxy_port = "8080"; //使用代理
$snoopy->maxredirs = 2; //重定向次数
$snoopy->expandlinks = true; //是否补全链接 在采集的时候经常用到
// 例如链接为 /images/taoav.gif 可改为它的全链接 http://www./images/taoav.gif，这个地方其实可以在最后输出的时候用ereg_replace函数自己替换
$snoopy->maxframes = 5 //允许的最大框架数
//注意抓取框架的时候 $snoopy->results 返回的是一个数组
$snoopy->error //返回报错信息

代码如下:

<?
//echo var_dump($_SERVER);
include("Snoopy.class.php");
$snoopy = new Snoopy;
$snoopy->agent = "Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-
CN; rv:1.9.0.5) Gecko/2008120122 Firefox/3.0.5 FirePHP/0.2.1";//这项是浏览器信
息，前面你用什么浏览器查看cookie，就用那个浏览器的信息(ps:$_SERVER可以查看到浏览器的信息)
$snoopy->referer = "http://bbs./index.php";
$snoopy->expandlinks = true;
$snoopy->rawheaders["COOKIE"]="__utmz=17229162.1227682761.29.7.utmccn=(referral)|utmcsr=|utmcct=/html/index.html|utmcmd=referral; cdbphpchina_smile=1D2D0D1; cdbphpchina_cookietime=2592000; __utma=233700831.1562900865.1227113506.1229613449.1231233266.16; __utmz=233700831.1231233266.16.8.utmccn=(referral)|utmcsr=localhost:8080|utmcct=/test3.php|utmcmd=referral; __utma=17229162.1877703507.1227113568.1231228465.1231233160.58; uchome_loginuser=sinopf; xscdb_cookietime=2592000; __utmc=17229162; __utmb=17229162; cdbphpchina_sid=EX5w1V; __utmc=233700831; cdbphpchina_visitedfid=17; cdbphpchinaO766uPYGK6OWZaYlvHSuzJIP22VpwEMGnPQAuWCFL9Fd6CHp2e%2FKw0x4bKz0N9lGk; xscdb_auth=8106rAyhKpQL49eMs%2FyhLBf3C6ClZ%2B2idSk4bExJwbQr%2BHSZrVKgqPOttHVr%2B6KLPg3DtWpTMUI4ttqNNVpukUj6ElM; cdbphpchina_onlineusernum=3721";
$snoopy->fetch("http://bbs.");
$n=ereg_replace("href=/index.html"","href=/index.html"http://bbs./",$snoopy->results );
echo ereg_replace("src=/index.html"","src=/index.html"http://bbs./",$n);
?>