PHP采集库-Snoopy.class.php
Snoopy是一个php类，用来模拟浏览器的功能，可以获取网页内容，发送表单。
Snoopy的特点：
1、抓取网页的内容 fetch
2、抓取网页的文本内容 (去除HTML标签) fetchtext
3、抓取网页的链接，表单 fetchlinks fetchform
4、支持代理主机
5、支持基本的用户名/密码验证
6、支持设置 user_agent, referer(来路), cookies 和 header content(头文件)
7、支持浏览器重定向，并能控制重定向深度
8、能把网页中的链接扩展成高质量的url(默认)
9、提交数据并且获取返回值
10、支持跟踪HTML框架
11、支持重定向的时候传递cookies
要求php4以上就可以了，由于本身是php一个类，无需扩支持，服务器不支持curl时候的最好选择。
<?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;
}
} ?>
PHP采集库-Snoopy.class.php的更多相关文章
- PHP采集利器 Snoopy 试用心得
Snoopy是什么? 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 ...
- PHP简单爬虫 基于QueryList采集库 和 ezsql数据库操作类
QueryList是一个基于phpQuery的PHP通用列表采集类,得益于phpQuery,让使用QueryList几乎没有任何学习成本,只要会CSS3选择器就可以轻松使用QueryList了,它让P ...
- golang的采集库
goquery https://github.com/PuerkitoBio/goquery 例子 aa.html <html> <body> <div id=" ...
- 单独编译使用WebRTC的音频处理模块
块,每块个点,(12*64=768采样)即AEC-PC仅能处理48ms的单声道16kHz延迟的数据,而 - 加载编译好的NS模块动态库 接下来只需要按照 此文 的描述在 android 的JAVA代码 ...
- snort-2.9.7.0源码安装过程
2015/02/15,centos6.5-64-minimal,初始205个包 [root@localhost snort]# yum install wget[root@localhost snor ...
- MongoDB,HDFS, Spark to 电影推荐
http://www.infoq.com/cn/news/2014/12/mongdb-spark-movie-recommend MovieWeb是一个电影相关的网站,它提供的功能包括搜索电影信息. ...
- 使用django+mysql+scrapy制作的一个小说网站
小说网站用的程序都是千篇一律的,jieqi + guanguang,无聊时间学习python+django,也做了一个小说网站,下面说一说做这个网站一些过程, 制作这种采集站,最要紧的是要有一个好的采 ...
- Ambari架构源码解析
1. Ambari介绍 Apache Ambari是一种基于Web的工具,支持Apache Hadoop集群的供应.管理和监控.Ambari已支持大多数Hadoop组件,包括HDFS.MapReduc ...
- Ambari架构及安装
不多说,直接上干货! 1.什么是Ambari? 2.Ambari项目是由哪几部分构成的? 3.Ambari系统架构是如何组成的? 前言 Hadoop集群的管控一直是一个热门的话题,对于这样的一个应用场 ...
随机推荐
- select设置高度的兼容问题
在IE678下,我们给select设置高度的话,里面的option无法居中,折中的兼容方式就是,我们给select的border:0:外面套一层div,这个div给他设置padding,让select ...
- ZH奶酪：JavaScript清空数组的三种方法
参考链接:http://snandy.iteye.com/blog/893955 方式1,length赋值为0 目前 Prototype中数组的 clear 方法和mootools库中数组的 empt ...
- JavaScript match()方法使用
1.JavaScript match() 方法说明http://www.w3school.com.cn/jsref/jsref_match.asp 写法: stringObject.match(sea ...
- mac SVN 设置代理
1. 设置代理一种方法:Finder 菜单里面 -> 前往 -> 前往文件夹 -> /Users/username/.subversion -> 编辑文件 servers 在文 ...
- C10K——千万级并发实现的秘密：内核不是解决方案，而是问题所在！（转）
既然我们已经解决了 C10K并发连接问题,应该如何提高水平支持千万级并发连接?你可能会说不可能.不,现在系统已经在用你可能不熟悉甚至激进的方式支持千万级别的并发连接. 要知道它是如何做到的,我们首先要 ...
- Codeforces554C:Kyoya and Colored Balls(组合数学+费马小定理)
Kyoya Ootori has a bag with n colored balls that are colored with k different colors. The colors are ...
- 如何让bat,cmd文件后台运行？如何把文件打包成EXE？
方法1:在“运行”中输入IEXPRESS 这是WINDOWS自带的打包程序,好像也可以生成安装包. 下一步-下一步-随便填个名字(下一步)-下一步-下一步-ADD(选好你的BAT文件 继 ...
- 小程序四：视图之WXSS
WXSS(WeiXin Style Sheets)是MINA设计的一套样式语言,用于描述WXML的组件样式. WXSS用来决定WXML的组件应该怎么显示. 为了适应广大的前端开发者,我们的WXSS具有 ...
- tomcat部署war包访问显示404
在eclipse导出的maven项目war包,放到tomcat下启动,顺利启动且无报错,但是浏览器访问该项目时显示404 原因:未在server.xml中配置这几个项目,导致服务器查找不到 解决方法: ...
- redis通过json方案存取对象com.alibaba.fastjson.JSONException: syntax error, expect
问题描述: redis基于json方案存取对象时报错:com.alibaba.fastjson.JSONException: syntax error, expect com.alibaba.fast ...