IndianWapmasters. Powered by Blogger.

Create Grabber Using With Curl


Create Grabber Using With Curl
<?
function html_to_array( $url, $element = null )
{
    if( !( $data = file_get_contents( $url ) ) )
        return false;
   
    preg_match_all( '~<img.*?>(</img>)?~si', $data, $page['img'] );
    preg_match_all( '~<div.*?>.*?[^<]</div>~', $data, $page['div'] );
    preg_match_all( '~<style.*?>.*?[^<]</style>~', $data, $page['Inline_Css'] );
    preg_match_all( '~<link.*?>~', $data, $page['Linked_Css'] );
    preg_match_all( '~<meta.*?[^>]>~', $data, $page['Meta'] );
    preg_match_all( '~<a.*?[^>].*[^<]</a>~', $data, $page['Link'] );
    return !is_null( $element ) ? $page[ $element ] : $page ;
}
function display_links( $links, $htmlentities = true )
{
    foreach( $links as $number => $link )
    {
        printf("Link number %d : [ %s ]<br />\n", $number + 1, $htmlentities ? htmlentities( $link ) : $link );
    }  
}
foreach( html_to_array( 'http://forums.digitalpoint.com' ) as $element => $html )
{
    printf( "I see %d %s tags<br />\n",
            count( $html[0] ),
            str_replace('_', ' ', $element )
    );
}
foreach( html_to_array( 'http://forums.digitalpoint.com', 'Link' ) as $links )
{
    printf("I found %d links, here they are :<br />\n%s",
           count( $links ),
           display_links( $links )
    );
}
?>

0 comments

Post a Comment