使用来自rss Feed的php抓取图像

Question

PHP

$rss = new DOMDocument();
$rss->load('http://www.autoexpress.co.uk/feeds/all');
$feed = array();
foreach ($rss->getElementsByTagName('item') as $node) {
  $item = array (
    'title' => $node->getElementsByTagName('title')->item(0)->nodeValue,
    'desc' => $node->getElementsByTagName('description')->item(0)->nodeValue,
    'link' => $node->getElementsByTagName('link')->item(0)->nodeValue,
    'date' => $node->getElementsByTagName('pubDate')->item(0)->nodeValue,
    'image' => $node->getElementsByTagName('whattagdoiaddhere')->item(0)->nodeValue,
  );
  array_push($feed, $item);
}
$limit = 3;
for($x=0;$x<$limit;$x++) {
  $title = str_replace(' & ', ' &amp; ', $feed[$x]['title']);
  $link = $feed[$x]['link'];
  $description = $feed[$x]['desc'];
  $date = date('l F d, Y', strtotime($feed[$x]['date']));
  echo '<div class="news-row-index">';
  echo '<div class="img"><a href="'.$link.'" target="_blank" title="'.$title.'"><img src="'.$image.'" height="79" width="89"></a></div>';
  echo '<div class="details-index"><p><h5><a href="'.$link.'" target="_blank" title="'.$title.'">'.$title.'</a></h5><br />';
  echo '<small><em>Posted on '.$date.'</em></small></p>';
  echo '<p>'.$description.'</p></div>';
  echo '</div>';
}

1. I am trying to get the images from this rss but don't know exactly how to get the image and add it into the <div class="img".
2. Also i have a problem because the image is being received but it's located in the $description variable.
3. Tried searching and found php rss feed show images but when i add the code from that answer I get nothing in the rss module. Please help me I really appreciate it.

Answer 1

You can make use of DomDocument loadHTML to parse the description field and grab the image tags.

foreach ($rss->getElementsByTagName('item') as $node) {
  $htmlStr = $node->getElementsByTagName('description')->item(0)->nodeValue;
  $html = new DOMDocument();        
  $html->loadHTML($htmlStr);
   //get the first image tag from the description HTML
   $img = $html->getElementsByTagName('img')->item(0)->getAttribute('src');
   $item = array (
    'title' => $node->getElementsByTagName('title')->item(0)->nodeValue,
    'desc' => $node->getElementsByTagName('description')->item(0)->nodeValue,
    'link' => $node->getElementsByTagName('link')->item(0)->nodeValue,
    'date' => $node->getElementsByTagName('pubDate')->item(0)->nodeValue,
    'image' => $img,
  );
  array_push($feed, $item);
}
  print_r($feed);

Also to check if the DOMNodeList is empty, try

foreach ($rss->getElementsByTagName('item') as $node) {
      $htmlStr = $node->getElementsByTagName('description')->item(0)->nodeValue;
      $html = new DOMDocument();        
      $html->loadHTML($htmlStr);
       //get the first image tag from the description HTML
        $imgTag = $html->getElementsByTagName('img');
        $img = ($imgTag->length==0)?'noimg.png':$imgTag->item(0)->getAttribute('src');
       $item = array (
        'title' => $node->getElementsByTagName('title')->item(0)->nodeValue,
        'desc' => $node->getElementsByTagName('description')->item(0)->nodeValue,
        'link' => $node->getElementsByTagName('link')->item(0)->nodeValue,
        'date' => $node->getElementsByTagName('pubDate')->item(0)->nodeValue,
        'image' => $img,
      );
      array_push($feed, $item);
    }