note 93340 modified in class.domelement by danbrown

From: Date: Fri, 04 Sep 2009 18:12:22 +0000
Subject: note 93340 modified in class.domelement by danbrown
References: 1  Groups: php.notes 
Request: Send a blank email to php-notes+get-160220@lists.php.net to get a copy of this message
The following code shows can text-only content be extracted from a document. <?php function getTextFromNode($Node, $Text = "") { if ($Node->tagName == null) return $Text.$Node->textContent; $Node = $Node->firstChild; if ($Node != null) $Text = getTextFromNode($Node, $Text); while($Node->nextSibling != null) { $Text = getTextFromNode($Node->nextSibling, $Text); $Node = $Node->nextSibling; } return $Text; } function getTextFromDocument($DOMDoc) { return getTextFromNode($DOMDoc->documentElement); } $Doc = new DOMDocument(); $Doc->loadHTMLFile("Test.html"); echo getTextFromDocument($Doc)."\n"; ?> --was-- The following code shows can text-only content be extracted from a document. function getTextFromNode($Node, $Text = "") { if ($Node->tagName == null) return $Text.$Node->textContent; $Node = $Node->firstChild; if ($Node != null) $Text = getTextFromNode($Node, $Text); while($Node->nextSibling != null) { $Text = getTextFromNode($Node->nextSibling, $Text); $Node = $Node->nextSibling; } return $Text; } function getTextFromDocument($DOMDoc) { return getTextFromNode($DOMDoc->documentElement); } $Doc = new DOMDocument(); $Doc->loadHTMLFile("Test.html"); echo getTextFromDocument($Doc)."\n"; http://php.net/manual/en/class.domelement.php

« previous php.notes (#160220) next »