Alle-Links-einer-Seite-in-array-schreiben.php

Quell Code

<?php 
/*
$file = "https://php.de";
$doc = new DOMDocument();
$doc->loadHTMLFile($file);
 
$tag_name = 'a';
$elements = $doc->getElementsByTagName($tag_name);
echo "<pre>";
if (!is_null($elements)) {
   foreach ($elements as $element) {
     echo "<br/>". $element->nodeName. ": ";

     $nodes = $element->childNodes;
     foreach ($nodes as $node) {
       echo $node->nodeValue;
     }
   }
 }
 */
?>


<?php
function getUrls( $url ){
    
    $content = file_get_contents( $url );
    
    @$document = new DOMDocument();
    @$document->loadHTML($content);

    $path = new DOMXPath($document);
    $urls = $path->evaluate("/html/body//a");

    for ($x = 0; $x < $urls->length; $x++) {
        $hrefs[$x] = $urls->item($x)->getAttribute('href');
    }

    return $hrefs;
    
}
 
@$link=getUrls('https://sebastian1012.bplaced.net/homepage-neu/');
 
 echo  "<pre>";
 print_r($link);
 echo  "<pre>";
 
 
 /*
@$doc = new DOMDocument();
@$doc->loadHTMLFile($link[33]);
 
@$tag_name = 'main';
@$tag2='article';
@$tag3='div';
 $elements = $doc->getElementById($tag_name);
 
 $elements = $doc->getElementsByTagName($tag2)[0];
 $brennen=$elements->ownerDocument->saveHTML($elements);
 
 
// $html = file_get_contents($link[33]);
// foreach($html->find('h1') as $element){
//       echo $element->innertext . '<br>'; 
// }
 //echo $brennen;
 
 
    $dom = new DOMDocument();
    libxml_use_internal_errors(true);
    $dom->loadHTML($brennen);
	libxml_clear_errors();
    $h1List = $dom->getElementsByTagName('h1');
    $article = $dom->getElementsByTagName('article');
    if($h1List->length == 0){
     
    }else{
	        foreach($h1List as $h1){
            print_r($h1->nodeValue);// h1 auslesen
        }
    }  
    
    
 */
?>