我一直使用PHP内置的SimpleXML函数来解析XML文档。它是目前为数不多的具有直观结构的通用解析器之一，这使得为RSS提要等特定内容构建有意义的类非常容易。此外，它将检测XML警告和错误，找到任何内容后，您可以简单地通过HTML Tidy（如ceejayoz所述）之类的源来运行源以对其进行清理并再次尝试。
考虑一下使用SimpleXML的非常粗糙，简单的类：
class BlogPost{ var $date; var $ts; var $link; var $title; var $text;}class BlogFeed{ var $posts = array(); function __construct($file_or_url) { $file_or_url = $this->resolveFile($file_or_url); if (!($x = simplexml_load_file($file_or_url))) return; foreach ($x->channel->item as $item) { $post = new BlogPost(); $post->date = (string) $item->pubDate; $post->ts = strtotime($item->pubDate); $post->link = (string) $item->link; $post->title = (string) $item->title; $post->text = (string) $item->description; // Create summary as a shortened body and remove images, // extraneous line breaks, etc. $post->summary = $this->summarizeText($post->text); $this->posts[] = $post; } } private function resolveFile($file_or_url) { if (!preg_match('|^https?:|', $file_or_url)) $feed_uri = $_SERVER['document_ROOT'] .'/shared/xml/'. $file_or_url; else $feed_uri = $file_or_url; return $feed_uri; } private function summarizeText($summary) { $summary = strip_tags($summary); // Truncate summary line to 100 characters $max_len = 100; if (strlen($summary) > $max_len) $summary = substr($summary, 0, $max_len) . '...'; return $summary; }}
