gg-extract-links.php

<?php

function usage( $err=null ) {
  echo 'Usage: '.$_SERVER['argv'][0]." <source file>\n";
  if( $err ) {
    echo 'Error: '.$err."\n";
  }
  exit();
}

if( $_SERVER['argc'] != 2 ) {
  usage();
}

$src = $_SERVER['argv'][1];
if( !is_file($src) ) {
  usage( 'cannot find source file !' );
}
$content = file_get_contents( $_SERVER['argv'][1] );
$content = urldecode( html_entity_decode($content) );
//var_dump( $content );

$t_links = [];

$doc = new DOMDocument();
$doc->preserveWhiteSpace = false;
@$doc->loadHTML( $content );

$xpath = new DOMXPath( $doc );
//$t_result = $xpath->query("//*[@class='r']/a");
$t_result = $xpath->query("//h3//a[@href]");
//var_dump( $t_result );
//exit();

foreach( $t_result as $r )
{
    $lnk = $r->ownerDocument->saveHTML( $r );
    preg_match_all( '#href="([^"]*)"#', $lnk, $tmp );
    $full_url = str_ireplace( '/url?q=', '', $tmp[1][0] );
    //var_dump( $full_url );
    $t_info = parse_url( $full_url );
    //var_dump( $t_info );

    $t_links[] = $full_url;
    
    /*$a = preg_match( '#(.*)\.s3.amazonaws\.com#', $t_info['host'], $m );
    
    if( $a ) {
        $t_buckets[] = $m[1];
    } else {
        $tmp = explode( '/', $t_info['path'] );
        $t_buckets[] = $tmp[1];
        }*/
}


echo implode( "\n", $t_links )."\n";

exit();

?>