213月/10
//$url = "http://news.google.cn/news/section?pz=1&cf=all&ned=ccn&topic=i&ict=ln";
$url = "http://news.google.cn/news/section?pz=1&cf=all&ned=ccn&topic=t&ict=ln";
$lines_array = file($url);
$lines_string = implode('', $lines_array);
eregi('
(.*)', $lines_string, $head1);eregi('
', $lines_string, $head2);eregi('
echo $head1[0];
echo $head3[0];
?>
译者:limodou
首先,我首必须决定我们将
$url = 'http://www.php.net'; ?>
第二步,我们
$url = 'http://www.php.net'; $lines_array = file($url); ?>
好了,现在在数组里已经有了文件了。但是,我们想
$url = 'http://www.php.net'; $lines_array = file($url); $lines_string = implode('', $lines_array); ?>
现在,
$url = 'http://www.php.net'; $lines_array = file($url); $lines_string = implode('', $lines_array); eregi("
(.*)", $lines_string, $head); ?>让我们看一下代码。正如你所见,eregi()函数按下面的格式执行:
eregi("
(.*)", $lines_string, $head);"(.*)"表示所有东西,可以解释为,"
$url = 'http://www.php.net'; $lines_array = file($url); $lines_string = implode('', $lines_array); eregi("
(.*)", $lines_string, $head); echo $head[0]; ?>这就是全部的代码了。
//获取所有内容url保存到文件
function get_index ( $save_file , $prefix = "index_" ){
$count = 68 ;
$i = 1 ;
if ( file_exists ( $save_file )) @ unlink ( $save_file );
$fp = fopen ( $save_file , "a+" ) or die( "Open " . $save_file . " failed" );
while( $i < $count ){
$url = $prefix . $i . ".htm" ;
echo "Get " . $url . "..." ;
$url_str = get_content_url ( get_url ( $url ));
echo " OK/n" ;
fwrite ( $fp , $url_str );
++ $i ;
}
fclose ( $fp );
}
//获取目标多媒体对象
function get_object ( $url_file , $save_file , $split = "|--:**:--|" ){
if (! file_exists ( $url_file )) die( $url_file . " not exist" );
$file_arr = file ( $url_file );
if (! is_array ( $file_arr ) || empty( $file_arr )) die( $url_file . " not content" );
$url_arr = array_unique ( $file_arr );
if ( file_exists ( $save_file )) @ unlink ( $save_file );
$fp = fopen ( $save_file , "a+" ) or die( "Open save file " . $save_file . " failed" );
foreach( $url_arr as $url ){
if (empty( $url )) continue;
echo "Get " . $url . "..." ;
$html_str = get_url ( $url );
echo $html_str ;
echo $url ;
exit;
$obj_str = get_content_object ( $html_str );
echo " OK/n" ;
fwrite ( $fp , $obj_str );
}
fclose ( $fp );
}
//遍历目录获取文件内容
function get_dir ( $save_file , $dir ){
$dp = opendir ( $dir );
if ( file_exists ( $save_file )) @ unlink ( $save_file );
$fp = fopen ( $save_file , "a+" ) or die( "Open save file " . $save_file . " failed" );
while(( $file = readdir ( $dp )) != false ){
if ( $file != "." && $file != ".." ){
echo "Read file " . $file . "..." ;
$file_content = file_get_contents ( $dir . $file );
$obj_str = get_content_object ( $file_content );
echo " OK/n" ;
fwrite ( $fp , $obj_str );
}
}
fclose ( $fp );
}
//获取指定url内容
function get_url ( $url ){
$reg = '/^http:[^//].+$/' ;
if (! preg_match ( $reg , $url )) die( $url . " invalid" );
$fp = fopen ( $url , "r" ) or die( "Open url: " . $url . " failed." );
while( $fc = fread ( $fp , 8192 )){
$content .= $fc ;
}
fclose ( $fp );
if (empty( $content )){
die( "Get url: " . $url . " content failed." );
}
return $content ;
}
//使用socket获取指定
fwrite ( $fp , $header );
while (! feof ( $fp )) {
$contents .= fgets ( $fp , 8192 );
}
fclose ( $fp );
return $contents ;
}
//获取指定内容里的url
function get_content_url ( $host_url , $file_contents ){
//$reg = '/^(#|JavaScript.*?|ftp:.+|http:.+|.*?href.*?|play.*?|index.*?|.*?asp)+$/i';
//$reg = '/^(down.*?/.html|/d+_/d+/.htm.*?)$/i';
$rex = "/([hH][rR][eE][Ff])/s*=/s*['/"]*([^>'/"/s]+)[/"'>]*/s*/i" ;
$reg = '/^(down.*?/.html)$/i' ;
preg_match_all ( $rex , $file_contents , $r );
$result = "" ; //array();
foreach( $r as $c ){
if ( is_array ( $c )){
foreach( $c as $d ){
if ( preg_match ( $reg , $d )){ $result .= $host_url . $d . "/n" ; }
}
}
}
return $result ;
}
//获取指定内容中的多媒体文件
function get_content_object ( $str , $split = "|--:**:--|" ){
$regx = "/href/s*=/s*['/"]*([^>'/"/s]+)[/"'>]*/s*(.*?/b>)/i" ;
preg_match_all ( $regx , $str , $result );
if ( count ( $result ) == 3 ){
$result [ 2 ] = str_replace ( "多媒体: " , "" , $result [ 2 ]);
$result [ 2 ] = str_replace ( " " , "" , $result [ 2 ]);
$result = $result [ 1 ][ 0 ] . $split . $result [ 2 ][ 0 ] . "/n" ;
}
return $result ;
}
?>
邵珠庆推荐文章
博文加载中...
发布在 邵珠庆