网页抓取及下载
downAndroidApk.php
<?php
/*
命令行
d:
cd ApacheServer\php
php.exe D:\ApacheServer\web\crawl\downAndroidApk.php --appidFile=D:\ApacheServer\web\crawl\youxi.txt --newDir=D:\ApacheServer\web\crawl\requestNewDir
*/
// 判断必须在php-cli模式下运行，即命令行执行
if (strtolower(php_sapi_name()) != 'cli') {
echo " error : this script must run by php-cli mode.";
exit;
}
echo "\n\n\n =================== begin download =================== \n";
/*
* 分析参数
*/
//创建变量
$new_dir = $old_dir = $appid_file = '';
$sleep_time = 0;
//strpos() 函数返回字符串在另一个字符串中第一次出现的位置。如果没有找到该字符串，则返回 false。
//$argv存储命令行 php.exe 命令后面每一个用空格分割的字符串组成的数组，索引从0起
//DIRECTORY_SEPARATOR 根据不同的系统返回不同的路径分隔符。windows "\" 或 "/"，linux "/"
foreach ($argv as $k=>$v) { //根据命令行给定参数，设定相应变量值
if (!$new_dir && strpos($v, '-newDir=')===1) { // 设置新保存的APP目录
$new_dir = substr($v, 9);
if (substr($new_dir, -1)==DIRECTORY_SEPARATOR) {
$new_dir = substr($new_dir, 0, -1);
}
} elseif (!$old_dir && strpos($v, '-oldDir=')===1) { // 设置旧的APP存放目录
$old_dir = substr($v, 9);
if (substr($old_dir, -1)==DIRECTORY_SEPARATOR) {
$old_dir = substr($new_dir, 0, -1);
}
} elseif (!$appid_file && strpos($v, '-appidFile=')===1) { // 设置读取ID列表参数
$appid_file = substr($v, 12);
}elseif (!$sleep_time && strpos($v, '-sleep=')===1) { // 设置暂停时间
$sleep_time = intval(substr($v, 8));
$sleep_time<=0 ? $sleep_time=3 : 1;
}
}
/*
* 检测参数
*/
// 判断存储appid列表的文件是否存在
if (!$appid_file || !file_exists($appid_file)) {
echo 'error : --appidFile error. app id file is not exists!'."\n";
exit;
}
// 判断保存下载APP的目录是否创建
if (!$new_dir || !file_exists($new_dir)) {
echo 'error: --newDir error. new app downloaded directory is not exists, please create that.'."\n";
exit;
}
// 判断以前保持下载目录的目录是否存在
if (!$old_dir || !file_exists($old_dir)) {
echo '-----warong: --oldDir warong. old app downloaded directory is not exists, can not be compared.'."\n";
sleep(3);
}
// 引入页面抓取类
require('Snoopy.class.php');
// 引入下载类
require('dedehttpdown.class.php');
// 分析app列表文件
/*
存储appid的youxi.txt文件的存储格式为
appid1
appid2
appid3
$app_id_array通过file()函数获取的是每行字符串组成的数组，索引从0开始
*/
$app_id_array = file($appid_file);
//打开日志文件
$log = '';
$fp = fopen($new_dir.DIRECTORY_SEPARATOR.'log.txt', 'a');
foreach ($app_id_array as $k=>$appid) {
if (empty($appid)) {
$log = '-----error : appid "'.$v.'" is can not get info'."\n";
continue;
}
echo '--begin appid: '.$appid."\n";//打印显示开始下载的appid
$log = getAppInfo($appid);
echo $log[0]."\n";
// 打印log
fwrite($fp, date('Y-m-d H:i:s', time()).' '.$log[0]."\n");
// 如果下载失败，打印失败log
if (isset($log[1]) && !empty($log[1])) {
fwrite($fp, date('Y-m-d H:i:s', time()).' ----------'.$log[1]."----------\n");
}
echo '--end appid: '.$appid."\n";
if ($sleep_time) {
sleep($sleep_time);
}
}
fclose($fp);
echo "\n =================== end download =================== \n\n\n";
/*
* 获取某应用信息
*/
function getAppInfo($app_id) {
global $new_dir;
//创建抓取类对象
$snoopy = new Snoopy();
//0对应正常下载信息，1对应失败错误信息
$log = array(0=>'', 1=>'');
echo "1 get $app_id info start\n";
//初始化图片地址，应用名称，版本号
$bigicon_url = $title = $app_version ='';
//设置要抓取的网页路径
$url = 'http://www.wandoujia.com/apps/'.$app_id;
$snoopy->fetch($url); //将路径赋给抓取对象
$content = $snoopy->results; //获取所有内容
//通过正则查找将内容中回车换成空格，回车符两边的 //必须加，因为正则内容必须写在//中
$content = preg_replace("/\n/", ' ', $content);
//将内容中换行换成空格
$content = preg_replace("/\r/", ' ', $content);
// 获取图片地址 bigicon_url
//$imgs为搜索结果。 $imgs[0]将包含完整模式匹配到的文本， $imgs[1] 将包含第一个捕获子组(正则里第一个括号匹配到的内容)匹配到的文本，以此类推。
$i = preg_match('/class="app-icon".*?rc="(.*?)"/', $content, $imgs);
$bigicon_url = $imgs[1];
// 获取应用名称 title
if ($i) {
$i = preg_match('/class="app-name".*?itemprop="name">(.*?)</', $content, $title);
$title = trim($title[1]);
}
// 获取版本号 app_version
if ($i) {
$i = preg_match('/<dt>版本<\/dt>.*?<dd>(.*?)</', $content, $app_version);
$app_version = trim($app_version[1]);
}
// 获取APK包大小
if ($i) {
$i = preg_match('/<dt>大小<\/dt>.*?<dd>(.*?)</', $content, $apk_size);
$apk_size = trim($apk_size[1]);
}
//如果获取app信息成功则进行下载
if ($bigicon_url && $title && $app_version) {
$app_dir = $new_dir.DIRECTORY_SEPARATOR.$app_id;
if (!file_exists($app_dir)) {
mkdir($app_dir);
chmod($app_dir, 0777);
}
$log[0] = $app_id.'|'.$title.'|'.$app_version.'|';
// 开始下载图片和APK包
echo "2 get $app_id info finished\n";
echo "3 get $app_id image start\n";
$img_size = download($app_id, 'img', $bigicon_url); // 下载图片
echo "4 get $app_id image finished\n";
echo "5 get $app_id app start. size: $apk_size\n";
$apk_size = str_ireplace('M', '', $apk_size);
$app_size = download($app_id, 'app', '', $apk_size); // 下载APP
echo "6 get $app_id app finished\n";
//如果返回的文件大小为空则下载失败
if ($app_size=='B') {
$log[1] = '-----'. $app_id . ' downloaded apk failure.-----';
echo $log[1]."\n";
}
$log[0] .= $app_size;
//记录日志文件
file_put_contents($app_dir.DIRECTORY_SEPARATOR.'apkinfo.txt', $log[0]);
return $log;
} else {
$log[0] = $app_id.'|';
$log[1] = '-----'.$app_id .' get html failed. -----';
echo $log[1]."\n";
return $log;
}
}
/*
* 下载图片和应用
* $type = 'img/app' 图片或应用.
* $img_url图片地址, 仅仅type为img时需要
* $apk_size在正常下载不好用时需要
*/
function download($app_id, $type='img', $img_url='', $apk_size=0) {
global $new_dir;
//创建下载对象
$httpdown = new DedeHttpDown();
//下载APP
if ($type == 'app') {
// 组建下载地址
$app_url = 'http://apps.wandoujia.com/apps/'.$app_id.'/download?pos=www/detail';
echo $app_url."\n";
// 设置文件保存完整路径
$app_file = $new_dir . DIRECTORY_SEPARATOR . $app_id . DIRECTORY_SEPARATOR . $app_id.'.apk';
$file_have = 0;
//有时候会下载不成功，重试两次，不成功则跳过
for ($i=1; $i<=2; $i++) {
echo 'downloaded times: '.$i."\n";
//设置下载路径
$httpdown->OpenUrl($app_url);
//设置保存路径，到保存文件的扩展名，完整路径
$httpdown->SaveToBin($app_file);
$httpdown->Close();
if (file_exists($app_file)) {
$file_have = 1;
break;
}
//等待三秒，防止下载太快网站封IP
sleep(3);
}
// 如果下载失败，使用snoopy尝试一次
if (!file_exists($app_file)) {
echo 'downloaded times: 3'."\n";
//获取php.ini的内存限制大小
$memory_limit = ini_get('memory_limit');
if ($apk_size && $memory_limit-2>$apk_size) {
$snoopy = new Snoopy();
$snoopy->fetch($app_url);
$content = $snoopy->results;//获取内容
file_put_contents($app_file, $content);
}
}
if (file_exists($app_file)) {
$file_have = 1;
}
unset($httpdown);
if ($file_have) {
//获取下载后文件的大小
return filesize($app_file).'B';
} else {
return 'B';
}
//否则下载图片
} elseif ($type == 'img') {
// 设置文件保存完整路径
$bigicon = $new_dir . DIRECTORY_SEPARATOR . $app_id . DIRECTORY_SEPARATOR . 'bigicon.png';
$httpdown->OpenUrl($img_url);
$httpdown->SaveToBin($bigicon);
$httpdown->Close();
unset($httpdown);
if (file_exists($bigicon)) {
return filesize($bigicon).'B';
} else {
return 'B';
}
}
}
?>
Snoopy.class.php
<?php
/*************************************************
Snoopy - the PHP net client
Author: Monte Ohrt <monte@ispi.net>
Copyright (c): 1999-2008 New Digital Group, all rights reserved
Version: 1.2.4
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
You may contact the author of Snoopy by e-mail at:
monte@ohrt.com
The latest version of Snoopy can be obtained from:
http://snoopy.sourceforge.net/
*************************************************/
class Snoopy
{
/**** Public variables ****/
/* user definable vars */
var $host = "www.php.net"; // host name we are connecting to
var $port = 80; // port we are connecting to
var $proxy_host = ""; // proxy host to use
var $proxy_port = ""; // proxy port to use
var $proxy_user = ""; // proxy user to use
var $proxy_pass = ""; // proxy password to use
var $agent = "Snoopy v1.2.4"; // agent we masquerade as
var $referer = ""; // referer info to pass
var $cookies = array(); // array of cookies to pass
// $cookies["username"]="joe";
var $rawheaders = array(); // array of raw headers to send
// $rawheaders["Content-type"]="text/html";
var $maxredirs = 5; // http redirection depth maximum. 0 = disallow
var $lastredirectaddr = ""; // contains address of last redirected address
var $offsiteok = true; // allows redirection off-site
var $maxframes = 0; // frame content depth maximum. 0 = disallow
var $expandlinks = true; // expand links to fully qualified URLs.
// this only applies to fetchlinks()
// submitlinks(), and submittext()
var $passcookies = true; // pass set cookies back through redirects
// NOTE: this currently does not respect
// dates, domains or paths.
var $user = ""; // user for http authentication
var $pass = ""; // password for http authentication
// http accept types
var $accept = "image/gif, image/x-xbitmap, image/jpeg, image/pjpeg, */*";
var $results = ""; // where the content is put
var $error = ""; // error messages sent here
var $response_code = ""; // response code returned from server
var $headers = array(); // headers returned from server sent here
var $maxlength = 500000; // max return data length (body)
var $read_timeout = 0; // timeout on read operations, in seconds
// supported only since PHP 4 Beta 4
// set to 0 to disallow timeouts
var $timed_out = false; // if a read operation timed out
var $status = 0; // http request status
var $temp_dir = "/tmp"; // temporary directory that the webserver
// has permission to write to.
// under Windows, this should be C:\temp
var $curl_path = "/usr/local/bin/curl";
// Snoopy will use cURL for fetching
// SSL content if a full system path to
// the cURL binary is supplied here.
// set to false if you do not have
// cURL installed. See http://curl.haxx.se
// for details on installing cURL.
// Snoopy does *not* use the cURL
// library functions built into php,
// as these functions are not stable
// as of this Snoopy release.
/**** Private variables ****/
var $_maxlinelen = 4096; // max line length (headers)
var $_httpmethod = "GET"; // default http request method
var $_httpversion = "HTTP/1.0"; // default http request version
var $_submit_method = "POST"; // default submit method
var $_submit_type = "application/x-www-form-urlencoded"; // default submit type
var $_mime_boundary = ""; // MIME boundary for multipart/form-data submit type
var $_redirectaddr = false; // will be set if page fetched is a redirect
var $_redirectdepth = 0; // increments on an http redirect
var $_frameurls = array(); // frame src urls
var $_framedepth = 0; // increments on frame depth
var $_isproxy = false; // set if using a proxy server
var $_fp_timeout = 30; // timeout for socket connection
/*======================================================================*\
Function: fetch
Purpose: fetch the contents of a web page
(and possibly other protocols in the
future like ftp, nntp, gopher, etc.)
Input: $URI the location of the page to fetch
Output: $this->results the output text from the fetch
\*======================================================================*/
function fetch($URI)
{
//preg_match("|^([^:]+)://([^:/]+)(:[\d]+)*(.*)|",$URI,$URI_PARTS);
$URI_PARTS = parse_url($URI);
if (!empty($URI_PARTS["user"]))
$this->user = $URI_PARTS["user"];
if (!empty($URI_PARTS["pass"]))
$this->pass = $URI_PARTS["pass"];
if (empty($URI_PARTS["query"]))
$URI_PARTS["query"] = '';
if (empty($URI_PARTS["path"]))
$URI_PARTS["path"] = '';
switch(strtolower($URI_PARTS["scheme"]))
{
case "http":
$this->host = $URI_PARTS["host"];
if(!empty($URI_PARTS["port"]))
$this->port = $URI_PARTS["port"];
if($this->_connect($fp))
{
if($this->_isproxy)
{
// using proxy, send entire URI
$this->_httprequest($URI,$fp,$URI,$this->_httpmethod);
}
else
{
$path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : "");
// no proxy, send only the path
$this->_httprequest($path, $fp, $URI, $this->_httpmethod);
}
$this->_disconnect($fp);
if($this->_redirectaddr)
{
/* url was redirected, check if we've hit the max depth */
if($this->maxredirs > $this->_redirectdepth)
{
// only follow redirect if it's on this site, or offsiteok is true
if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok)
{
/* follow the redirect */
$this->_redirectdepth++;
$this->lastredirectaddr=$this->_redirectaddr;
$this->fetch($this->_redirectaddr);
}
}
}
if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0)
{
$frameurls = $this->_frameurls;
$this->_frameurls = array();
while(list(,$frameurl) = each($frameurls))
{
if($this->_framedepth < $this->maxframes)
{
$this->fetch($frameurl);
$this->_framedepth++;
}
else
break;
}
}
}
else
{
return false;
}
return true;
break;
case "https":
if(!$this->curl_path)
return false;
if(function_exists("is_executable"))
if (!is_executable($this->curl_path))
return false;
$this->host = $URI_PARTS["host"];
if(!empty($URI_PARTS["port"]))
$this->port = $URI_PARTS["port"];
if($this->_isproxy)
{
// using proxy, send entire URI
$this->_httpsrequest($URI,$URI,$this->_httpmethod);
}
else
{
$path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : "");
// no proxy, send only the path
$this->_httpsrequest($path, $URI, $this->_httpmethod);
}
if($this->_redirectaddr)
{
/* url was redirected, check if we've hit the max depth */
if($this->maxredirs > $this->_redirectdepth)
{
// only follow redirect if it's on this site, or offsiteok is true
if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok)
{
/* follow the redirect */
$this->_redirectdepth++;
$this->lastredirectaddr=$this->_redirectaddr;
$this->fetch($this->_redirectaddr);
}
}
}
if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0)
{
$frameurls = $this->_frameurls;
$this->_frameurls = array();
while(list(,$frameurl) = each($frameurls))
{
if($this->_framedepth < $this->maxframes)
{
$this->fetch($frameurl);
$this->_framedepth++;
}
else
break;
}
}
return true;
break;
default:
// not a valid protocol
$this->error = 'Invalid protocol "'.$URI_PARTS["scheme"].'"\n';
return false;
break;
}
return true;
}
/*======================================================================*\
Function: submit
Purpose: submit an http form
Input: $URI the location to post the data
$formvars the formvars to use.
format: $formvars["var"] = "val";
$formfiles an array of files to submit
format: $formfiles["var"] = "/dir/filename.ext";
Output: $this->results the text output from the post
\*======================================================================*/
function submit($URI, $formvars="", $formfiles="")
{
unset($postdata);
$postdata = $this->_prepare_post_body($formvars, $formfiles);
$URI_PARTS = parse_url($URI);
if (!empty($URI_PARTS["user"]))
$this->user = $URI_PARTS["user"];
if (!empty($URI_PARTS["pass"]))
$this->pass = $URI_PARTS["pass"];
if (empty($URI_PARTS["query"]))
$URI_PARTS["query"] = '';
if (empty($URI_PARTS["path"]))
$URI_PARTS["path"] = '';
switch(strtolower($URI_PARTS["scheme"]))
{
case "http":
$this->host = $URI_PARTS["host"];
if(!empty($URI_PARTS["port"]))
$this->port = $URI_PARTS["port"];
if($this->_connect($fp))
{
if($this->_isproxy)
{
// using proxy, send entire URI
$this->_httprequest($URI,$fp,$URI,$this->_submit_method,$this->_submit_type,$postdata);
}
else
{
$path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : "");
// no proxy, send only the path
$this->_httprequest($path, $fp, $URI, $this->_submit_method, $this->_submit_type, $postdata);
}
$this->_disconnect($fp);
if($this->_redirectaddr)
{
/* url was redirected, check if we've hit the max depth */
if($this->maxredirs > $this->_redirectdepth)
{
if(!preg_match("|^".$URI_PARTS["scheme"]."://|", $this->_redirectaddr))
$this->_redirectaddr = $this->_expandlinks($this->_redirectaddr,$URI_PARTS["scheme"]."://".$URI_PARTS["host"]);
// only follow redirect if it's on this site, or offsiteok is true
if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok)
{
/* follow the redirect */
$this->_redirectdepth++;
$this->lastredirectaddr=$this->_redirectaddr;
if( strpos( $this->_redirectaddr, "?" ) > 0 )
$this->fetch($this->_redirectaddr); // the redirect has changed the request method from post to get
else
$this->submit($this->_redirectaddr,$formvars, $formfiles);
}
}
}
if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0)
{
$frameurls = $this->_frameurls;
$this->_frameurls = array();
while(list(,$frameurl) = each($frameurls))
{
if($this->_framedepth < $this->maxframes)
{
$this->fetch($frameurl);
$this->_framedepth++;
}
else
break;
}
}
}
else
{
return false;
}
return true;
break;
case "https":
if(!$this->curl_path)
return false;
if(function_exists("is_executable"))
if (!is_executable($this->curl_path))
return false;
$this->host = $URI_PARTS["host"];
if(!empty($URI_PARTS["port"]))
$this->port = $URI_PARTS["port"];
if($this->_isproxy)
{
// using proxy, send entire URI
$this->_httpsrequest($URI, $URI, $this->_submit_method, $this->_submit_type, $postdata);
}
else
{
$path = $URI_PARTS["path"].($URI_PARTS["query"] ? "?".$URI_PARTS["query"] : "");
// no proxy, send only the path
$this->_httpsrequest($path, $URI, $this->_submit_method, $this->_submit_type, $postdata);
}
if($this->_redirectaddr)
{
/* url was redirected, check if we've hit the max depth */
if($this->maxredirs > $this->_redirectdepth)
{
if(!preg_match("|^".$URI_PARTS["scheme"]."://|", $this->_redirectaddr))
$this->_redirectaddr = $this->_expandlinks($this->_redirectaddr,$URI_PARTS["scheme"]."://".$URI_PARTS["host"]);
// only follow redirect if it's on this site, or offsiteok is true
if(preg_match("|^http://".preg_quote($this->host)."|i",$this->_redirectaddr) || $this->offsiteok)
{
/* follow the redirect */
$this->_redirectdepth++;
$this->lastredirectaddr=$this->_redirectaddr;
if( strpos( $this->_redirectaddr, "?" ) > 0 )
$this->fetch($this->_redirectaddr); // the redirect has changed the request method from post to get
else
$this->submit($this->_redirectaddr,$formvars, $formfiles);
}
}
}
if($this->_framedepth < $this->maxframes && count($this->_frameurls) > 0)
{
$frameurls = $this->_frameurls;
$this->_frameurls = array();
while(list(,$frameurl) = each($frameurls))
{
if($this->_framedepth < $this->maxframes)
{
$this->fetch($frameurl);
$this->_framedepth++;
}
else
break;
}
}
return true;
break;
default:
// not a valid protocol
$this->error = 'Invalid protocol "'.$URI_PARTS["scheme"].'"\n';
return false;
break;
}
return true;
}
/*======================================================================*\
Function: fetchlinks
Purpose: fetch the links from a web page
Input: $URI where you are fetching from
Output: $this->results an array of the URLs
\*======================================================================*/
function fetchlinks($URI)
{
if ($this->fetch($URI))
{
if($this->lastredirectaddr)
$URI = $this->lastredirectaddr;
if(is_array($this->results))
{
for($x=0;$x<count($this->results);$x++)
$this->results[$x] = $this->_striplinks($this->results[$x]);
}
else
$this->results = $this->_striplinks($this->results);
if($this->expandlinks)
$this->results = $this->_expandlinks($this->results, $URI);
return true;
}
else
return false;
}
/*======================================================================*\
Function: fetchform
Purpose: fetch the form elements from a web page
Input: $URI where you are fetching from
Output: $this->results the resulting html form
\*======================================================================*/
function fetchform($URI)
{
if ($this->fetch($URI))
{
if(is_array($this->results))
{
for($x=0;$x<count($this->results);$x++)
$this->results[$x] = $this->_stripform($this->results[$x]);
}
else
$this->results = $this->_stripform($this->results);
return true;
}
else
return false;
}
/*======================================================================*\
Function: fetchtext
Purpose: fetch the text from a web page, stripping the links
Input: $URI where you are fetching from
Output: $this->results the text from the web page
\*======================================================================*/
function fetchtext($URI)
{
if($this->fetch($URI))
{
if(is_array($this->results))
{
for($x=0;$x<count($this->results);$x++)
$this->results[$x] = $this->_striptext($this->results[$x]);
}
else
$this->results = $this->_striptext($this->results);
return true;
}
else
return false;
}
/*======================================================================*\
Function: submitlinks
Purpose: grab links from a form submission
Input: $URI where you are submitting from
Output: $this->results an array of the links from the post
\*======================================================================*/
function submitlinks($URI, $formvars="", $formfiles="")
{
if($this->submit($URI,$formvars, $formfiles))
{
if($this->lastredirectaddr)
$URI = $this->lastredirectaddr;
if(is_array($this->results))
{
for($x=0;$x<count($this->results);$x++)
{
$this->results[$x] = $this->_striplinks($this->results[$x]);
if($this->expandlinks)
$this->results[$x] = $this->_expandlinks($this->results[$x],$URI);
}
}
else
{
$this->results = $this->_striplinks($this->results);
if($this->expandlinks)
$this->results = $this->_expandlinks($this->results,$URI);
}
return true;
}
else
return false;
}
/*======================================================================*\
Function: submittext
Purpose: grab text from a form submission
Input: $URI where you are submitting from
Output: $this->results the text from the web page
\*======================================================================*/
function submittext($URI, $formvars = "", $formfiles = "")
{
if($this->submit($URI,$formvars, $formfiles))
{
if($this->lastredirectaddr)
$URI = $this->lastredirectaddr;
if(is_array($this->results))
{
for($x=0;$x<count($this->results);$x++)
{
$this->results[$x] = $this->_striptext($this->results[$x]);
if($this->expandlinks)
$this->results[$x] = $this->_expandlinks($this->results[$x],$URI);
}
}
else
{
$this->results = $this->_striptext($this->results);
if($this->expandlinks)
$this->results = $this->_expandlinks($this->results,$URI);
}
return true;
}
else
return false;
}
/*======================================================================*\
Function: set_submit_multipart
Purpose: Set the form submission content type to
multipart/form-data
\*======================================================================*/
function set_submit_multipart()
{
$this->_submit_type = "multipart/form-data";
}
/*======================================================================*\
Function: set_submit_normal
Purpose: Set the form submission content type to
application/x-www-form-urlencoded
\*======================================================================*/
function set_submit_normal()
{
$this->_submit_type = "application/x-www-form-urlencoded";
}
/*======================================================================*\
Private functions
\*======================================================================*/
/*======================================================================*\
Function: _striplinks
Purpose: strip the hyperlinks from an html document
Input: $document document to strip.
Output: $match an array of the links
\*======================================================================*/
function _striplinks($document)
{
preg_match_all("'<\s*a\s.*?href\s*=\s* # find <a href=
([\"\'])? # find single or double quote
(?(1) (.*?)\\1 | ([^\s\>]+)) # if quote found, match up to next matching
# quote, otherwise match up to next space
'isx",$document,$links);
// catenate the non-empty matches from the conditional subpattern
while(list($key,$val) = each($links[2]))
{
if(!empty($val))
$match[] = $val;
}
while(list($key,$val) = each($links[3]))
{
if(!empty($val))
$match[] = $val;
}
// return the links
return $match;
}
/*======================================================================*\
Function: _stripform
Purpose: strip the form elements from an html document
Input: $document document to strip.
Output: $match an array of the links
\*======================================================================*/
function _stripform($document)
{
preg_match_all("'<\/?(FORM|INPUT|SELECT|TEXTAREA|(OPTION))[^<>]*>(?(2)(.*(?=<\/?(option|select)[^<>]*>[\r\n]*)|(?=[\r\n]*))|(?=[\r\n]*))'Usi",$document,$elements);
// catenate the matches
$match = implode("\r\n",$elements[0]);
// return the links
return $match;
}
/*======================================================================*\
Function: _striptext
Purpose: strip the text from an html document
Input: $document document to strip.
Output: $text the resulting text
\*======================================================================*/
function _striptext($document)
{
// I didn't use preg eval (//e) since that is only available in PHP 4.0.
// so, list your entities one by one here. I included some of the
// more common ones.
$search = array("'<script[^>]*?>.*?</script>'si", // strip out javascript
"'<[\/\!]*?[^<>]*?>'si", // strip out html tags
"'([\r\n])[\s]+'", // strip out white space
"'&(quot|#34|#034|#x22);'i", // replace html entities
"'&(amp|#38|#038|#x26);'i", // added hexadecimal values
"'&(lt|#60|#060|#x3c);'i",
"'&(gt|#62|#062|#x3e);'i",
"'&(nbsp|#160|#xa0);'i",
"'&(iexcl|#161);'i",
"'&(cent|#162);'i",
"'&(pound|#163);'i",
"'&(copy|#169);'i",
"'&(reg|#174);'i",
"'&(deg|#176);'i",
"'&(#39|#039|#x27);'",
"'&(euro|#8364);'i", // europe
"'&a(uml|UML);'", // german
"'&o(uml|UML);'",
"'&u(uml|UML);'",
"'&A(uml|UML);'",
"'&O(uml|UML);'",
"'&U(uml|UML);'",
"'ß'i",
);
$replace = array( "",
"",
"\\1",
"\"",
"&",
"<",
">",
" ",
chr(161),
chr(162),
chr(163),
chr(169),
chr(174),
chr(176),
chr(39),
chr(128),
"�",
"�",
"�",
"�",
"�",
"�",
"�",
);
$text = preg_replace($search,$replace,$document);
return $text;
}
/*======================================================================*\
Function: _expandlinks
Purpose: expand each link into a fully qualified URL
Input: $links the links to qualify
$URI the full URI to get the base from
Output: $expandedLinks the expanded links
\*======================================================================*/
function _expandlinks($links,$URI)
{
preg_match("/^[^\?]+/",$URI,$match);
$match = preg_replace("|/[^\/\.]+\.[^\/\.]+$|","",$match[0]);
$match = preg_replace("|/$|","",$match);
$match_part = parse_url($match);
$match_root =
$match_part["scheme"]."://".$match_part["host"];
$search = array( "|^http://".preg_quote($this->host)."|i",
"|^(\/)|i",
"|^(?!http://)(?!mailto:)|i",
"|/\./|",
"|/[^\/]+/\.\./|"
);
$replace = array( "",
$match_root."/",
$match."/",
"/",
"/"
);
$expandedLinks = preg_replace($search,$replace,$links);
return $expandedLinks;
}
/*======================================================================*\
Function: _httprequest
Purpose: go get the http data from the server
Input: $url the url to fetch
$fp the current open file pointer
$URI the full URI
$body body contents to send if any (POST)
Output:
\*======================================================================*/
function _httprequest($url,$fp,$URI,$http_method,$content_type="",$body="")
{
$cookie_headers = '';
if($this->passcookies && $this->_redirectaddr)
$this->setcookies();
$URI_PARTS = parse_url($URI);
if(empty($url))
$url = "/";
$headers = $http_method." ".$url." ".$this->_httpversion."\r\n";
if(!empty($this->agent))
$headers .= "User-Agent: ".$this->agent."\r\n";
if(!empty($this->host) && !isset($this->rawheaders['Host'])) {
$headers .= "Host: ".$this->host;
if(!empty($this->port))
$headers .= ":".$this->port;
$headers .= "\r\n";
}
if(!empty($this->accept))
$headers .= "Accept: ".$this->accept."\r\n";
if(!empty($this->referer))
$headers .= "Referer: ".$this->referer."\r\n";
if(!empty($this->cookies))
{
if(!is_array($this->cookies))
$this->cookies = (array)$this->cookies;
reset($this->cookies);
if ( count($this->cookies) > 0 ) {
$cookie_headers .= 'Cookie: ';
foreach ( $this->cookies as $cookieKey => $cookieVal ) {
$cookie_headers .= $cookieKey."=".urlencode($cookieVal)."; ";
}
$headers .= substr($cookie_headers,0,-2) . "\r\n";
}
}
if(!empty($this->rawheaders))
{
if(!is_array($this->rawheaders))
$this->rawheaders = (array)$this->rawheaders;
while(list($headerKey,$headerVal) = each($this->rawheaders))
$headers .= $headerKey.": ".$headerVal."\r\n";
}
if(!empty($content_type)) {
$headers .= "Content-type: $content_type";
if ($content_type == "multipart/form-data")
$headers .= "; boundary=".$this->_mime_boundary;
$headers .= "\r\n";
}
if(!empty($body))
$headers .= "Content-length: ".strlen($body)."\r\n";
if(!empty($this->user) || !empty($this->pass))
$headers .= "Authorization: Basic ".base64_encode($this->user.":".$this->pass)."\r\n";
//add proxy auth headers
if(!empty($this->proxy_user))
$headers .= 'Proxy-Authorization: ' . 'Basic ' . base64_encode($this->proxy_user . ':' . $this->proxy_pass)."\r\n";
$headers .= "\r\n";
// set the read timeout if needed
if ($this->read_timeout > 0)
socket_set_timeout($fp, $this->read_timeout);
$this->timed_out = false;
fwrite($fp,$headers.$body,strlen($headers.$body));
$this->_redirectaddr = false;
unset($this->headers);
while($currentHeader = fgets($fp,$this->_maxlinelen))
{
if ($this->read_timeout > 0 && $this->_check_timeout($fp))
{
$this->status=-100;
return false;
}
if($currentHeader == "\r\n")
break;
// if a header begins with Location: or URI:, set the redirect
if(preg_match("/^(Location:|URI:)/i",$currentHeader))
{
// get URL portion of the redirect
preg_match("/^(Location:|URI:)[ ]+(.*)/i",chop($currentHeader),$matches);
// look for :// in the Location header to see if hostname is included
if(!preg_match("|\:\/\/|",$matches[2]))
{
// no host in the path, so prepend
$this->_redirectaddr = $URI_PARTS["scheme"]."://".$this->host.":".$this->port;
// eliminate double slash
if(!preg_match("|^/|",$matches[2]))
$this->_redirectaddr .= "/".$matches[2];
else
$this->_redirectaddr .= $matches[2];
}
else
$this->_redirectaddr = $matches[2];
}
if(preg_match("|^HTTP/|",$currentHeader))
{
if(preg_match("|^HTTP/[^\s]*\s(.*?)\s|",$currentHeader, $status))
{
$this->status= $status[1];
}
$this->response_code = $currentHeader;
}
$this->headers[] = $currentHeader;
}
$results = '';
do {
$_data = fread($fp, $this->maxlength);
if (strlen($_data) == 0) {
break;
}
$results .= $_data;
} while(true);
if ($this->read_timeout > 0 && $this->_check_timeout($fp))
{
$this->status=-100;
return false;
}
// check if there is a a redirect meta tag
if(preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$results,$match))
{
$this->_redirectaddr = $this->_expandlinks($match[1],$URI);
}
// have we hit our frame depth and is there frame src to fetch?
if(($this->_framedepth < $this->maxframes) && preg_match_all("'<frame\s+.*src[\s]*=[\'\"]?([^\'\"\>]+)'i",$results,$match))
{
$this->results[] = $results;
for($x=0; $x<count($match[1]); $x++)
$this->_frameurls[] = $this->_expandlinks($match[1][$x],$URI_PARTS["scheme"]."://".$this->host);
}
// have we already fetched framed content?
elseif(is_array($this->results))
$this->results[] = $results;
// no framed content
else
$this->results = $results;
return true;
}
/*======================================================================*\
Function: _httpsrequest
Purpose: go get the https data from the server using curl
Input: $url the url to fetch
$URI the full URI
$body body contents to send if any (POST)
Output:
\*======================================================================*/
function _httpsrequest($url,$URI,$http_method,$content_type="",$body="")
{
if($this->passcookies && $this->_redirectaddr)
$this->setcookies();
$headers = array();
$URI_PARTS = parse_url($URI);
if(empty($url))
$url = "/";
// GET ... header not needed for curl
//$headers[] = $http_method." ".$url." ".$this->_httpversion;
if(!empty($this->agent))
$headers[] = "User-Agent: ".$this->agent;
if(!empty($this->host))
if(!empty($this->port))
$headers[] = "Host: ".$this->host.":".$this->port;
else
$headers[] = "Host: ".$this->host;
if(!empty($this->accept))
$headers[] = "Accept: ".$this->accept;
if(!empty($this->referer))
$headers[] = "Referer: ".$this->referer;
if(!empty($this->cookies))
{
if(!is_array($this->cookies))
$this->cookies = (array)$this->cookies;
reset($this->cookies);
if ( count($this->cookies) > 0 ) {
$cookie_str = 'Cookie: ';
foreach ( $this->cookies as $cookieKey => $cookieVal ) {
$cookie_str .= $cookieKey."=".urlencode($cookieVal)."; ";
}
$headers[] = substr($cookie_str,0,-2);
}
}
if(!empty($this->rawheaders))
{
if(!is_array($this->rawheaders))
$this->rawheaders = (array)$this->rawheaders;
while(list($headerKey,$headerVal) = each($this->rawheaders))
$headers[] = $headerKey.": ".$headerVal;
}
if(!empty($content_type)) {
if ($content_type == "multipart/form-data")
$headers[] = "Content-type: $content_type; boundary=".$this->_mime_boundary;
else
$headers[] = "Content-type: $content_type";
}
if(!empty($body))
$headers[] = "Content-length: ".strlen($body);
if(!empty($this->user) || !empty($this->pass))
$headers[] = "Authorization: BASIC ".base64_encode($this->user.":".$this->pass);
for($curr_header = 0; $curr_header < count($headers); $curr_header++) {
$safer_header = strtr( $headers[$curr_header], "\"", " " );
$cmdline_params .= " -H \"".$safer_header."\"";
}
if(!empty($body))
$cmdline_params .= " -d \"$body\"";
if($this->read_timeout > 0)
$cmdline_params .= " -m ".$this->read_timeout;
$headerfile = tempnam($temp_dir, "sno");
exec($this->curl_path." -k -D \"$headerfile\"".$cmdline_params." \"".escapeshellcmd($URI)."\"",$results,$return);
if($return)
{
$this->error = "Error: cURL could not retrieve the document, error $return.";
return false;
}
$results = implode("\r\n",$results);
$result_headers = file("$headerfile");
$this->_redirectaddr = false;
unset($this->headers);
for($currentHeader = 0; $currentHeader < count($result_headers); $currentHeader++)
{
// if a header begins with Location: or URI:, set the redirect
if(preg_match("/^(Location: |URI: )/i",$result_headers[$currentHeader]))
{
// get URL portion of the redirect
preg_match("/^(Location: |URI:)\s+(.*)/",chop($result_headers[$currentHeader]),$matches);
// look for :// in the Location header to see if hostname is included
if(!preg_match("|\:\/\/|",$matches[2]))
{
// no host in the path, so prepend
$this->_redirectaddr = $URI_PARTS["scheme"]."://".$this->host.":".$this->port;
// eliminate double slash
if(!preg_match("|^/|",$matches[2]))
$this->_redirectaddr .= "/".$matches[2];
else
$this->_redirectaddr .= $matches[2];
}
else
$this->_redirectaddr = $matches[2];
}
if(preg_match("|^HTTP/|",$result_headers[$currentHeader]))
$this->response_code = $result_headers[$currentHeader];
$this->headers[] = $result_headers[$currentHeader];
}
// check if there is a a redirect meta tag
if(preg_match("'<meta[\s]*http-equiv[^>]*?content[\s]*=[\s]*[\"\']?\d+;[\s]*URL[\s]*=[\s]*([^\"\']*?)[\"\']?>'i",$results,$match))
{
$this->_redirectaddr = $this->_expandlinks($match[1],$URI);
}
// have we hit our frame depth and is there frame src to fetch?
if(($this->_framedepth < $this->maxframes) && preg_match_all("'<frame\s+.*src[\s]*=[\'\"]?([^\'\"\>]+)'i",$results,$match))
{
$this->results[] = $results;
for($x=0; $x<count($match[1]); $x++)
$this->_frameurls[] = $this->_expandlinks($match[1][$x],$URI_PARTS["scheme"]."://".$this->host);
}
// have we already fetched framed content?
elseif(is_array($this->results))
$this->results[] = $results;
// no framed content
else
$this->results = $results;
unlink("$headerfile");
return true;
}
/*======================================================================*\
Function: setcookies()
Purpose: set cookies for a redirection
\*======================================================================*/
function setcookies()
{
for($x=0; $x<count($this->headers); $x++)
{
if(preg_match('/^set-cookie:[\s]+([^=]+)=([^;]+)/i', $this->headers[$x],$match))
$this->cookies[$match[1]] = urldecode($match[2]);
}
}
/*======================================================================*\
Function: _check_timeout
Purpose: checks whether timeout has occurred
Input: $fp file pointer
\*======================================================================*/
function _check_timeout($fp)
{
if ($this->read_timeout > 0) {
$fp_status = socket_get_status($fp);
if ($fp_status["timed_out"]) {
$this->timed_out = true;
return true;
}
}
return false;
}
/*======================================================================*\
Function: _connect
Purpose: make a socket connection
Input: $fp file pointer
\*======================================================================*/
function _connect(&$fp)
{
if(!empty($this->proxy_host) && !empty($this->proxy_port))
{
$this->_isproxy = true;
$host = $this->proxy_host;
$port = $this->proxy_port;
}
else
{
$host = $this->host;
$port = $this->port;
}
$this->status = 0;
if($fp = fsockopen(
$host,
$port,
$errno,
$errstr,
$this->_fp_timeout
))
{
// socket connection succeeded
return true;
}
else
{
// socket connection failed
$this->status = $errno;
switch($errno)
{
case -3:
$this->error="socket creation failed (-3)";
case -4:
$this->error="dns lookup failure (-4)";
case -5:
$this->error="connection refused or timed out (-5)";
default:
$this->error="connection failed (".$errno.")";
}
return false;
}
}
/*======================================================================*\
Function: _disconnect
Purpose: disconnect a socket connection
Input: $fp file pointer
\*======================================================================*/
function _disconnect($fp)
{
return(fclose($fp));
}
/*======================================================================*\
Function: _prepare_post_body
Purpose: Prepare post body according to encoding type
Input: $formvars - form variables
$formfiles - form upload files
Output: post body
\*======================================================================*/
function _prepare_post_body($formvars, $formfiles)
{
settype($formvars, "array");
settype($formfiles, "array");
$postdata = '';
if (count($formvars) == 0 && count($formfiles) == 0)
return;
switch ($this->_submit_type) {
case "application/x-www-form-urlencoded":
reset($formvars);
while(list($key,$val) = each($formvars)) {
if (is_array($val) || is_object($val)) {
while (list($cur_key, $cur_val) = each($val)) {
$postdata .= urlencode($key)."[]=".urlencode($cur_val)."&";
}
} else
$postdata .= urlencode($key)."=".urlencode($val)."&";
}
break;
case "multipart/form-data":
$this->_mime_boundary = "Snoopy".md5(uniqid(microtime()));
reset($formvars);
while(list($key,$val) = each($formvars)) {
if (is_array($val) || is_object($val)) {
while (list($cur_key, $cur_val) = each($val)) {
$postdata .= "--".$this->_mime_boundary."\r\n";
$postdata .= "Content-Disposition: form-data; name=\"$key\[\]\"\r\n\r\n";
$postdata .= "$cur_val\r\n";
}
} else {
$postdata .= "--".$this->_mime_boundary."\r\n";
$postdata .= "Content-Disposition: form-data; name=\"$key\"\r\n\r\n";
$postdata .= "$val\r\n";
}
}
reset($formfiles);
while (list($field_name, $file_names) = each($formfiles)) {
settype($file_names, "array");
while (list(, $file_name) = each($file_names)) {
if (!is_readable($file_name)) continue;
$fp = fopen($file_name, "r");
$file_content = fread($fp, filesize($file_name));
fclose($fp);
$base_name = basename($file_name);
$postdata .= "--".$this->_mime_boundary."\r\n";
$postdata .= "Content-Disposition: form-data; name=\"$field_name\"; filename=\"$base_name\"\r\n\r\n";
$postdata .= "$file_content\r\n";
}
}
$postdata .= "--".$this->_mime_boundary."--\r\n";
break;
}
return $postdata;
}
}
?>
dedehttpdown.class.php
<?php
/**
* 织梦HTTP下载类
*
* @version $Id: dedehttpdown.class.php 1 11:42 2010年7月6日Z tianya $
* @package DedeCMS.Libraries
* @copyright Copyright (c) 2007 - 2010, DesDev, Inc.
* @license http://help.dedecms.com/usersguide/license.html
* @link http://www.dedecms.com
*/
@set_time_limit(0);
class DedeHttpDown
{
var $m_url = '';
var $m_urlpath = '';
var $m_scheme = 'http';
var $m_host = '';
var $m_port = '80';
var $m_user = '';
var $m_pass = '';
var $m_path = '/';
var $m_query = '';
var $m_fp = '';
var $m_error = '';
var $m_httphead = '';
var $m_html = '';
var $m_puthead = '';
var $BaseUrlPath = '';
var $HomeUrl = '';
var $reTry = 0;
var $JumpCount = 0;
/**
* 初始化系统
*
* @access public
* @param string $url 需要下载的地址
* @return string
*/
function PrivateInit($url)
{
if($url=='') {
return ;
}
$urls = '';
$urls = @parse_url($url);
$this->m_url = $url;
if(is_array($urls))
{
$this->m_host = $urls["host"];
if(!empty($urls["scheme"]))
{
$this->m_scheme = $urls["scheme"];
}
if(!empty($urls["user"]))
{
$this->m_user = $urls["user"];
}
if(!empty($urls["pass"]))
{
$this->m_pass = $urls["pass"];
}
if(!empty($urls["port"]))
{
$this->m_port = $urls["port"];
}
if(!empty($urls["path"]))
{
$this->m_path = $urls["path"];
}
$this->m_urlpath = $this->m_path;
if(!empty($urls["query"]))
{
$this->m_query = $urls["query"];
$this->m_urlpath .= "?".$this->m_query;
}
$this->HomeUrl = $urls["host"];
$this->BaseUrlPath = $this->HomeUrl.$urls["path"];
$this->BaseUrlPath = preg_replace("/\/([^\/]*)\.(.*)$/","/",$this->BaseUrlPath);
$this->BaseUrlPath = preg_replace("/\/$/","",$this->BaseUrlPath);
}
}
/**
* 重设各参数
*
* @access public
* @return void
*/
function ResetAny()
{
$this->m_url = "";
$this->m_urlpath = "";
$this->m_scheme = "http";
$this->m_host = "";
$this->m_port = "80";
$this->m_user = "";
$this->m_pass = "";
$this->m_path = "/";
$this->m_query = "";
$this->m_error = "";
}
/**
* 打开指定网址
*
* @access public
* @param string $url 地址
* @param string $requestType 请求类型
* @return string
*/
function OpenUrl($url,$requestType="GET")
{
$this->ResetAny();
$this->JumpCount = 0;
$this->m_httphead = Array() ;
$this->m_html = '';
$this->reTry = 0;
$this->Close();
//初始化系统
$this->PrivateInit($url);
$this->PrivateStartSession($requestType);
}
/**
* 转到303重定向网址
*
* @access public
* @param string $url 地址
* @return string
*/
function JumpOpenUrl($url)
{
$this->ResetAny();
$this->JumpCount++;
$this->m_httphead = Array() ;
$this->m_html = "";
$this->Close();
//初始化系统
$this->PrivateInit($url);
$this->PrivateStartSession('GET');
}
/**
* 获得某操作错误的原因
*
* @access public
* @return void
*/
function printError()
{
echo "错误信息：".$this->m_error;
echo "<br/>具体返回头：<br/>";
foreach($this->m_httphead as $k=>$v){ echo "$k => $v <br/>\r\n"; }
}
/**
* 判别用Get方法发送的头的应答结果是否正确
*
* @access public
* @return bool
*/
function IsGetOK()
{
if( preg_match("/^2/",$this->GetHead("http-state")) )
{
return TRUE;
}
else
{
$this->m_error .= $this->GetHead("http-state")." - ".$this->GetHead("http-describe")."<br/>";
return FALSE;
}
}
/**
* 看看返回的网页是否是text类型
*
* @access public
* @return bool
*/
function IsText()
{
if( preg_match("/^2/",$this->GetHead("http-state")) && preg_match("/text|xml/i",$this->GetHead("content-type")) )
{
return TRUE;
}
else
{
$this->m_error .= "内容为非文本类型或网址重定向<br/>";
return FALSE;
}
}
/**
* 判断返回的网页是否是特定的类型
*
* @access public
* @param string $ctype 内容类型
* @return string
*/
function IsContentType($ctype)
{
if(preg_match("/^2/",$this->GetHead("http-state"))
&& $this->GetHead("content-type")==strtolower($ctype))
{ return TRUE; }
else
{
$this->m_error .= "类型不对 ".$this->GetHead("content-type")."<br/>";
return FALSE;
}
}
/**
* 用Http协议下载文件
*
* @access public
* @param string $savefilename 保存文件名称
* @return string
*/
function SaveToBin($savefilename)
{
if(!$this->IsGetOK())
{
return FALSE;
}
if(@feof($this->m_fp))
{
$this->m_error = "连接已经关闭！"; return FALSE;
}
$fp = fopen($savefilename,"w");
while(!feof($this->m_fp))
{
fwrite($fp, fread($this->m_fp, 1024));
}
fclose($this->m_fp);
fclose($fp);
return TRUE;
}
/**
* 保存网页内容为Text文件
*
* @access public
* @param string $savefilename 保存文件名称
* @return string
*/
function SaveToText($savefilename)
{
if($this->IsText())
{
$this->SaveBinFile($savefilename);
}
else
{
return "";
}
}
/**
* 用Http协议获得一个网页的内容
*
* @access public
* @return string
*/
function GetHtml()
{
if(!$this->IsText())
{
return '';
}
if($this->m_html!='')
{
return $this->m_html;
}
if(!$this->m_fp||@feof($this->m_fp))
{
return '';
}
while(!feof($this->m_fp))
{
$this->m_html .= fgets($this->m_fp,256);
}
@fclose($this->m_fp);
return $this->m_html;
}
/**
* 开始HTTP会话
*
* @access public
* @param string $requestType 请求类型
* @return string
*/
function PrivateStartSession($requestType="GET")
{
if(!$this->PrivateOpenHost())
{
$this->m_error .= "打开远程主机出错!";
return FALSE;
}
$this->reTry++;
if($this->GetHead("http-edition")=="HTTP/1.1")
{
$httpv = "HTTP/1.1";
}
else
{
$httpv = "HTTP/1.0";
}
$ps = explode('?',$this->m_urlpath);
$headString = '';
//发送固定的起始请求头GET、Host信息
if($requestType=="GET")
{
$headString .= "GET ".$this->m_urlpath." $httpv\r\n";
}
else
{
$headString .= "POST ".$ps[0]." $httpv\r\n";
}
$this->m_puthead["Host"] = $this->m_host;
//发送用户自定义的请求头
if(!isset($this->m_puthead["Accept"]))
{
$this->m_puthead["Accept"] = "*/*";
}
if(!isset($this->m_puthead["User-Agent"]))
{
$this->m_puthead["User-Agent"] = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.2)";
}
if(!isset($this->m_puthead["Refer"]))
{
$this->m_puthead["Refer"] = "http://".$this->m_puthead["Host"];
}
foreach($this->m_puthead as $k=>$v)
{
$k = trim($k);
$v = trim($v);
if($k!=""&&$v!="")
{
$headString .= "$k: $v\r\n";
}
}
fputs($this->m_fp, $headString);
if($requestType=="POST")
{
$postdata = "";
if(count($ps)>1)
{
for($i=1;$i<count($ps);$i++)
{
$postdata .= $ps[$i];
}
}
else
{
$postdata = "OK";
}
$plen = strlen($postdata);
fputs($this->m_fp,"Content-Type: application/x-www-form-urlencoded\r\n");
fputs($this->m_fp,"Content-Length: $plen\r\n");
}
//发送固定的结束请求头
//HTTP1.1协议必须指定文档结束后关闭链接,否则读取文档时无法使用feof判断结束
if($httpv=="HTTP/1.1")
{
fputs($this->m_fp,"Connection: Close\r\n\r\n");
}
else
{
fputs($this->m_fp,"\r\n");
}
if($requestType=="POST")
{
fputs($this->m_fp,$postdata);
}
//获取应答头状态信息
$httpstas = explode(" ",fgets($this->m_fp,256));
$this->m_httphead["http-edition"] = trim($httpstas[0]);
$this->m_httphead["http-state"] = trim($httpstas[1]);
$this->m_httphead["http-describe"] = "";
for($i=2;$i<count($httpstas);$i++)
{
$this->m_httphead["http-describe"] .= " ".trim($httpstas[$i]);
}
//获取详细应答头
while(!feof($this->m_fp))
{
$line = trim(fgets($this->m_fp,256));
if($line == "")
{
break;
}
$hkey = "";
$hvalue = "";
$v = 0;
for($i=0;$i<strlen($line);$i++)
{
if($v==1)
{
$hvalue .= $line[$i];
}
if($line[$i]==":")
{
$v = 1;
}
if($v==0)
{
$hkey .= $line[$i];
}
}
$hkey = trim($hkey);
if($hkey!="")
{
$this->m_httphead[strtolower($hkey)] = trim($hvalue);
}
}
//如果连接被不正常关闭，重试
if(feof($this->m_fp))
{
if($this->reTry > 10)
{
return FALSE;
}
$this->PrivateStartSession($requestType);
}
//判断是否是3xx开头的应答
if(preg_match("/^3/",$this->m_httphead["http-state"]))
{
if($this->JumpCount > 3)
{
return;
}
if(isset($this->m_httphead["location"]))
{
$newurl = $this->m_httphead["location"];
if(preg_match("/^http/i",$newurl))
{
$this->JumpOpenUrl($newurl);
}
else
{
$newurl = $this->FillUrl($newurl);
$this->JumpOpenUrl($newurl);
}
}
else
{
$this->m_error = "无法识别的答复！";
}
}
}
/**
* 获得一个Http头的值
*
* @access public
* @param string $headname 头文件名称
* @return string
*/
function GetHead($headname)
{
$headname = strtolower($headname);
return isset($this->m_httphead[$headname]) ? $this->m_httphead[$headname] : '';
}
/**
* 设置Http头的值
*
* @access public
* @param string $skey 键
* @param string $svalue 值
* @return string
*/
function SetHead($skey,$svalue)
{
$this->m_puthead[$skey] = $svalue;
}
/**
* 打开连接
*
* @access public
* @return bool
*/
function PrivateOpenHost()
{
if($this->m_host=="")
{
return FALSE;
}
$errno = "";
$errstr = "";
$this->m_fp = @fsockopen($this->m_host, $this->m_port, $errno, $errstr,10);
if(!$this->m_fp)
{
$this->m_error = $errstr;
return FALSE;
}
else
{
return TRUE;
}
}
/**
* 关闭连接
*
* @access public
* @return void
*/
function Close()
{
@fclose($this->m_fp);
}
/**
* 补全相对网址
*
* @access public
* @param string $surl 需要不全的地址
* @return string
*/
function FillUrl($surl)
{
$i = 0;
$dstr = "";
$pstr = "";
$okurl = "";
$pathStep = 0;
$surl = trim($surl);
if($surl=="")
{
return "";
}
$pos = strpos($surl,"#");
if($pos>0)
{
$surl = substr($surl,0,$pos);
}
if($surl[0]=="/")
{
$okurl = "http://".$this->HomeUrl.$surl;
}
else if($surl[0]==".")
{
if(strlen($surl)<=1)
{
return "";
}
else if($surl[1]=="/")
{
$okurl = "http://".$this->BaseUrlPath."/".substr($surl,2,strlen($surl)-2);
}
else
{
$urls = explode("/",$surl);
foreach($urls as $u)
{
if($u=="..")
{
$pathStep++;
}
else if($i<count($urls)-1)
{
$dstr .= $urls[$i]."/";
}
else
{
$dstr .= $urls[$i];
}
$i++;
}
$urls = explode("/",$this->BaseUrlPath);
if(count($urls) <= $pathStep)
{
return "";
}
else
{
$pstr = "http://";
for($i=0;$i<count($urls)-$pathStep;$i++)
{
$pstr .= $urls[$i]."/";
}
$okurl = $pstr.$dstr;
}
}
}
else
{
if(strlen($surl)<7)
{
$okurl = "http://".$this->BaseUrlPath."/".$surl;
}
else if(strtolower(substr($surl,0,7))=="http://")
{
$okurl = $surl;
}
else
{
$okurl = "http://".$this->BaseUrlPath."/".$surl;
}
}
$okurl = preg_replace("/^(http:\/\/)/i","",$okurl);
$okurl = preg_replace("/\/{1,}/", "/", $okurl);
return "http://".$okurl;
}
}//End Class
