<?php
function get_url_content($Url,$Method = 'c') {
//Introduce the required language encoding. If not, it will default to utf-8, don't worry.
global $Charset;
$Urlarr = parse_url($Url);
//If the domain name cannot be detected, return.
if (!isset($Urlarr['host'])) {
return false;
}
//We define header multiple information in a smart way.
foreach (@getallheaders() as $key => $val){
$key==='Host' && $val = $Urlarr['host'];
$key==='Referer' && $val ='http://'.$Urlarr['host'];
$str .= "'$key:$val', n";
}
//Virtual origin.
!eregi('Referer',$str) && $str .="'Referer:http://{$Urlarr['host']}', n";
//After correction, basically, the source is also that site, and the host is also the Url site.
$Header = array(trim($str));
//The following is just to choose which program to use for collection.
if($Method === 'f'&&function_exists('file_get_contents')) {
$opts = array(
'http'=>array(
'method'=>"GET",
'header'=>$Header,
)
);
$cxContext = stream_context_create($opts);
$file_contents = @file_get_contents($Url, false, $cxContext);
} elseif ($Method === 'c'&&function_exists('curl_init')) {
$Ch = curl_init();
$Timeout = 5;
curl_setopt($Ch,CURLOPT_HTTPHEADER,$Header);
curl_setopt ($Ch, CURLOPT_URL, $Url);
curl_setopt ($Ch, CURLOPT_RETURNTRANSFER,1);
curl_setopt ($Ch, CURLOPT_CONNECTTIMEOUT, $Timeout);
$file_contents = curl_exec($Ch);
curl_close($Ch);
}
//In order to make the style display beautifully, we add a target guide to it.
$file_contents = str_replace('</title>',"</title>n<base href=" http://{$Urlarr['host']}/ " />",$file_contents);
//Process the most common encodings. If the target website does not have encoding, it will default to GBK.
!preg_match('/charset=([^<>"]*)"/isU',$file_contents,$lang) && $lang[1]='GBK';
function_exists('mb_convert_encoding') && $file_contents = mb_convert_encoding($file_contents,empty($Charset)?'UTF-8':$Charset,$lang[1]);
//Log out part of the code;
unset($Url,$lang,$Timeout,$Urlarr,$Charset);
return $file_contents;
}
//Start testing using file_get_contents method
HEADER("CONTENT-TYPE:TEXT/HTML; CHARSET=UTF-8");
//http://www.xtzj.com/read-htm-tid-347550.html This cannot be collected.
$file = get_url_content(" http://www.hao123.com",'f' );
$file = strip_tags($file,'<a>');
preg_match_all('/(http:[^"<>]*)>/isU',$file,$link);unset($link[0]);
$link = $link[1];
//Let's simulate obtaining data. Change the numbers yourself. 0-151 The following is using curl.
$x = 10;
$file = get_url_content($link[$x]);
echo $file;
?>
Write all explanations and comments.
If there are any replies that you don’t understand... I will spread the knowledge about the collection.
Original address: http://bbs.phpchina.com/viewthread.php?tid=99263