php text html,HTML2Text.php

class HTML2Text {

private $htmlTextString = "";

/**

* @param $DOMNodeList

* @return bool

*/

private function traversalDOM($DOMNodeList)

{

// 判断传入的是否为nodeList

if (!is_iterable($DOMNodeList)) {

/* 传入的不是 NodeList */

return "";

} else {

foreach ($DOMNodeList as $DOMNode) {

// 判断 nodeList 的子元素是否为 nodeList

if (is_iterable($DOMNode)) {

/* 子元素还是 nodeList，递归，继续遍历 */

$this->traversalDOM($DOMNode);

}

else

{

/* 子元素不是 nodeList，而是 node */

// 判断该 node 是否有子元素

if ($DOMNode->hasChildNodes()) {

// 该 node 有子元素，取得所有所有子元素，存入一个 nodeList 中

$nodeList = $DOMNode->childNodes;

// 开始新一轮的 nodeList 遍历

$this->traversalDOM($nodeList);

}

else

{

// 该 node 没有子元素

if ($DOMNode->nodeValue != null) {

$this->htmlTextString .= $DOMNode->nodeValue . " ";

}

}

}

}

}

}

/**

* HTML2Text constructor.

* @param $htmlString

*/

public function getText($htmlString) {

$dom = new DOMDocument;

@$dom->loadHTML($htmlString);

$xpath = new DOMXPath($dom);

/* 移除 html 中的 script */

// 参考：https://stackoverflow.com/questions/7130867/remove-script-tag-from-html-content

$scripts = $dom->getElementsByTagName('script');

$elementsToRemove = [];

foreach($scripts as $script)

{

$elementsToRemove[] = $script;

}

foreach ($elementsToRemove as $element)

{

$element->parentNode->removeChild($element);

}

/* 移除HTML中的注释 */

// 参考：https://stackoverflow.com/questions/6305643/remove-comments-from-html-source-code

foreach ($xpath->query('//comment()') as $comment) {

$comment->parentNode->removeChild($comment);

}

/* html 转 text */

$nodes = $xpath->query("//body");

$this->traversalDOM($nodes);

return $this->htmlTextString;

}

}

一键复制

编辑

Web IDE

原始数据

按行查看

历史