Last active
December 25, 2015 15:49
-
-
Save easychen/7001126 to your computer and use it in GitHub Desktop.
做了下title转码、对于文件链接只取前1k(服务器支持断点下载的情况下
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
function get_title_via_url( $url ) | |
{ | |
// 抓取前1024个字节 | |
$context=array('http' => array ('header'=> 'Range: bytes=0-1024' )); | |
$xcontext = stream_context_create($context); | |
$content = strtolower( file_get_contents( $url , FALSE,$xcontext ) ); | |
$reg = '/<title>(.+?)<\/title>/is'; | |
if( preg_match( $reg , $content , $out ) ) | |
{ | |
$title = $out[1]; | |
if(!is_utf8( $content )) $title = mb_convert_encoding( $title , 'UTF-8' , 'GBK' ); | |
return $title; | |
} | |
return basename( $url ); | |
} | |
function is_utf8( $content ) | |
{ | |
$content = strtolower($content); | |
$reg = '/<meta.+?charset=[\'"]?([a-z0-9\-]+)[\'"]/is'; | |
if(preg_match( $reg , $content , $out )) | |
{ | |
return $out[1] == 'utf-8'; | |
} | |
} | |
?> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment