fork download
  1. <?php
  2.  
  3. $html = <<<HTML
  4. <!doctype html>
  5. <html lang="en-US">
  6. <head>
  7.   <meta charset="UTF-8">
  8.   <title></title>
  9. </head>
  10. <body>
  11. <div class="localImage">
  12.   <a href="/Electronic-Deals/b/ref=amb_link_185249707_2?ie=UTF8&amp;node=4192584031&amp;pf_rd_m=A1VBAL9TL5WCBF&amp;pf_rd_s=center-new-12&amp;pf_rd_r=07C4YQ4KZ15MZJQBT2PD&amp;pf_rd_t=701&amp;pf_rd_p=736512207&amp;pf_rd_i=20">
  13.   <img src="http://g...content-available-to-author-only...n.com/images/G/31/rcx-events/cat-navs-electronics1._V335880105_.png"
  14.   alt="Electronics" border="0" height="140" width="170">
  15.   </a>
  16. </div>
  17. <div class="localImage">
  18.   <a href="/Electronic-Deals/b/ref=amb_link_185249707_2?ie=UTF8&amp;node=4192584031&amp;pf_rd_m=A1VBAL9TL5WCBF&amp;pf_rd_s=center-new-12&amp;pf_rd_r=07C4YQ4KZ15MZJQBT2PD&amp;pf_rd_t=701&amp;pf_rd_p=736512207&amp;pf_rd_i=20">
  19.   <img src="http://g...content-available-to-author-only...n.com/images/G/31/rcx-events/cat-navs-electronics1._V335880105_.png"
  20.   alt="Electronics" border="0" height="140" width="170">
  21.   </a>
  22. </div>
  23. </body>
  24. </html>
  25. HTML;
  26.  
  27. //correct way to avoid XML-errors (HTML is not valid XML, except valid XHTML)
  28. //instead of usage @$dom->loadHTML
  29. libxml_disable_entity_loader(true);
  30.  
  31. $dom = new DOMDocument('1.0');
  32. $dom->loadHTML($html);
  33. $xpath = new DOMXpath($dom);
  34. /**
  35.  * @var $domImage DOMElement IDE hint
  36.  */
  37. //xpath representation of CSS selector div.localImage>a>img
  38. $domImages = $xpath->query('//div[contains(@class, "localImage")]/a/img');
  39. for ($i = 0; $i < $domImages->length; $i++) {
  40. $domImage = $domImages->item($i);
  41. print("img[$i].src = " . $domImage->getAttribute('src'));
  42. print("\n");
  43. print("img[$i].alt = " . $domImage->getAttribute('alt'));
  44. print("\n\n");
  45. }
  46.  
  47.  
Success #stdin #stdout 0.02s 52480KB
stdin
Standard input is empty
stdout
img[0].src = http://g...content-available-to-author-only...n.com/images/G/31/rcx-events/cat-navs-electronics1._V335880105_.png
img[0].alt = Electronics

img[1].src = http://g...content-available-to-author-only...n.com/images/G/31/rcx-events/cat-navs-electronics1._V335880105_.png
img[1].alt = Electronics