Javascript DOMDocument-从正文中获取脚本文本
我试图做的是从body标签中获取脚本，但只获取具有文本而不是脚本链接的脚本 例如，Javascript DOMDocument-从正文中获取脚本文本,javascript,php,jquery,domdocument,Javascript,Php,Jquery,Domdocument,我试图做的是从body标签中获取脚本，但只获取具有文本而不是脚本链接的脚本 例如，console.log（“用于测试运行”） 不是包含文件src的脚本 我想把这些脚本放在之前的页面末尾 到目前为止我有 echo "<pre>"; echo "reaches 1 <br />"; //work for inpage scripts $mainBody = @$dom-&g
console.log（“用于测试运行”）
不是包含文件src的脚本
我想把这些脚本放在
之前的页面末尾
到目前为止我有
echo "<pre>";
echo "reaches 1 <br />";
//work for inpage scripts
$mainBody = @$dom->getElementsByTagName('body')->item(0);
foreach (@$dom->getElementsByTagName('body') as $head) {
echo "reaches 2";
foreach (@$head->childNodes as $node) {
echo "reaches 3";
var_dump($node);
if ($node instanceof DOMComment) {
if (preg_match('/<script/i', $node->nodeValue)){
$src = $node->nodeValue;
echo "its a node";
var_dump($node);
}
}
if ($node->nodeName == 'script' && $node->attributes->getNamedItem('type')->nodeValue == 'text/javascript') {
if (@$src = $node->attributes->getNamedItem('src')->nodeValue) {
// yay - $src was true, so we don't do anything here
} else {
$src = $node->nodeValue;
}
echo "its a node2";
var_dump($node);
}
if (isset($src)) {
$move = ($this->params->get('exclude')) ? true : false;
foreach ($omit as $omitit) {
if (preg_match($omitit, $src) == 1) {
$move = ($this->params->get('exclude')) ? false : true;
break;
}
}
if ($move)
$moveme[] = $node;
unset($src);
}
}
}
foreach ($moveme as $moveit) {
echo "Moving";
print_r($moveit);
$mainBody->appendChild($moveit->cloneNode(true));
if ($pretty) {
$mainBody->appendChild($newline->cloneNode(false));
}
$moveit->parentNode->removeChild($moveit);
}
$mainBody = $xhtml ? $dom->saveXML() : $dom->saveHTML();
JResponse::setBody($sanitize?preg_replace($this->sanitizews['search'],$this->sanitizews['replace'],$mainBody):$mainBody);
function onAfterRender() {
$app = JFactory::getApplication();
$doc = JFactory::getDocument();
/* test that the page is not administrator && test that the document is HTML output */
if ($app->isAdmin() || $doc->getType() != 'html')
return;
$pretty = (int)$this->params->get('pretty', 0);
$stripcomments = (int)$this->params->get('stripcomments', 0);
$sanitize = (int)$this->params->get('sanitize',0);
$debug = (int)$app->getCfg('debug',0);
if($debug) $pretty = true;
$omit = array();
/* now we know this is a frontend page and it is html - begin processing */
/* first - prepare the omit array */
if (strlen(trim($this->params->get('omit'))) > 0) {
foreach (explode("\n", $this->params->get('omit')) as $omitme) {
$omit[] = '/' . str_replace(array('/', '\''), array('\/', '\\\''), trim($omitme)) . '/i';
}
unset($omitme);
}
$moveme = array();
$dom = new DOMDocument();
$dom->recover = true;
$dom->substituteEntities = true;
if ($pretty) {
$dom->formatOutput = true;
} else {
$dom->preserveWhiteSpace = false;
}
$source = JResponse::getBody();
/* DOMDocument can get quite vocal when malformed HTML/XHTML is loaded.
* First we grab the current level, and set the error reporting level
* to zero, afterwards, we return it to the original value. This trickery
* is used to keep the logs clear of DOMDocument protests while loading the source.
* I promise to set the level back as soon as I'm done loading source...
*/
if(!$debug) $erlevel = error_reporting(0);
$xhtml = (preg_match('/XHTML/', $source)) ? true : false;
switch ($xhtml) {
case true:
$dom->loadXML($source);
break;
case false:
$dom->loadHTML($source);
break;
}
if(!$debug) error_reporting($erlevel); /* You see, error_reporting is back to normal - just like I promised */
if ($pretty) {
$newline = $dom->createTextNode("\n");
}
if($sanitize && !$debug && !$pretty) {
$this->_sanitizeCSS($dom->getElementsByTagName('style'));
}
if ($stripcomments && !$debug) {
$comments = $this->_domComments($dom);
foreach ($comments as $node)
if (!preg_match('/\[endif]/i', $node->nodeValue)) // we don't remove IE conditionals
if ($node->parentNode->nodeName != 'script') // we also don't remove comments in javascript because some developers write JS inside of a comment
$node->parentNode->removeChild($node);
}
$body = @$dom->getElementsByTagName('footer')->item(0);
foreach (@$dom->getElementsByTagName('head') as $head) {
foreach (@$head->childNodes as $node) {
if ($node instanceof DOMComment) {
if (preg_match('/<script/i', $node->nodeValue))
$src = $node->nodeValue;
}
if ($node->nodeName == 'script' && $node->attributes->getNamedItem('type')->nodeValue == 'text/javascript') {
if (@$src = $node->attributes->getNamedItem('src')->nodeValue) {
// yay - $src was true, so we don't do anything here
} else {
$src = $node->nodeValue;
}
}
if (isset($src)) {
$move = ($this->params->get('exclude')) ? true : false;
foreach ($omit as $omitit) {
if (preg_match($omitit, $src) == 1) {
$move = ($this->params->get('exclude')) ? false : true;
break;
}
}
if ($move)
$moveme[] = $node;
unset($src);
}
}
}
foreach ($moveme as $moveit) {
$body->appendChild($moveit->cloneNode(true));
if ($pretty) {
$body->appendChild($newline->cloneNode(false));
}
$moveit->parentNode->removeChild($moveit);
}
//work for inpage scripts
$xpath = new DOMXPath($dom);
$script_tags = $xpath->query('//body//script[not(@src)]');
$mainBody = @$dom->getElementsByTagName('body')->item(0);
foreach ($script_tags as $tag) {
$mainBody->appendChild($tag->cloneNode(true));
$tag->parentNode->removeChild($tag);
}
$body = $xhtml ? $dom->saveXML() : $dom->saveHTML();
JResponse::setBody($sanitize?preg_replace($this->sanitizews['search'],$this->sanitizews['replace'],$body):$body);
}
";
foreach ($script_tags as $tag) {
var_dump($tag->nodeValue);
$moveme[] = $tag;
}
为了只获取不具有
src节点，最好使用DOMXPath
：
变量$script\u tags
现在是一个DOMNodeList
对象，它包含所有脚本标记。
现在，您可以在DOMNodeList
上循环以获取所有节点，并对它们执行任何操作：
那么这里发生了什么？错误在哪里？只是一大块code@RodrigoDuterte我更新了我的问题。事实上，我的代码在页面的body标记下找不到脚本标记。或者像下面一样使用xpath，或者只是$mainBody->getElementsByTagName（'*'）
，我更喜欢
$xpath = new DOMXPath($dom);
$script_tags = $xpath->query('//body//script[not(@src)]');
foreach ($script_tags as $tag) {
var_dump($tag->nodeValue);
$moveme[] = $tag;
}