XML; /* * CALL */ $parser = new HtmlParser($html, '[[delimiter]]'); //dump found //decode/encode to only show public values print_r(json_decode(json_encode($parser))); /* * ACTUAL CODE */ class HtmlParser { private $_html; private $_delimiter; private $_dom; public $Elements = array(); final public function __construct($html, $delimiter) { $this->_html = $html; $this->_delimiter = $delimiter; $this->_dom = str_get_html($this->_html); $this->getElements(); } final private function getElements() { //this will find all elements, including parent elements //it will also select the actual text as an element, without surrounding tags $elements = $this->_dom->find("[contains(text(),'".$this->_delimiter."')]"); //find the actual elements that start with the delimiter foreach($elements as $element) { //we want the element without tags, so we search for outertext if (strpos($element->outertext, $this->_delimiter)===0) { $this->Elements[] = new DelimiterTag($element); } } } } class DelimiterTag { private $_element; public $Content; public $MoreContent; final public function __construct($element) { $this->_element = $element; $this->COntent= $element->outertext; $this->findMore(); } final private function findMore() { //we need to traverse up until we find a parent that has a next sibling //we need to keep track of the child, to cleanup the last parent $child = $this->_element; $parent = $child->parent(); $next = null; while($parent) { $next = $parent->next_sibling(); if ($next) { break; } $child = $parent; $parent = $child->parent(); } if (!$next) { //no more content return; } //create empty element, to build the new data //go up one more element and clean the innertext $more = $parent->parent(); $more->innertext = ""; //add the parent, because this is where the actual content lies //but we only want to add the child to the parent, in case there are more delimiters $parent->innertext = $child->outertext; $more->innertext .= $parent->outertext; //add the next sibling, because this is where more content lies $more->innertext .= $next->outertext; //set the variables if ($more->tag=="body") { //Your section 3 works slightly different as it doesn't show the parent tag, where the first two do. //That's why i show the innertext for the root tag and the outer text for others. $this->MoreCOntent= $more->innertext; } else { $this->MoreCOntent= $more->outertext; } } } ?>

清理输出:

stdClass Object
(
  [Elements] => Array
  (
    [0] => stdClass Object
    (
        [Content] => [[delimiter]]Start of content section 1.
        [MoreContent] => 

                            
[[delimiter]]Start of content section 1.
                            
More content in section 1
                          
    )

    [1] => stdClass Object
    (
        [Content] => [[delimiter]]Start of section 2
        [MoreContent] => 

                            
[[delimiter]]Start of section 2
                            More content in section 2
                         
    )

    [2] => stdClass Object
    (
        [Content] => [[delimiter]]Start of section 3
        [MoreContent] => 

                            
[[delimiter]]Start of section 3
                         
                         

                            More content in section 3
                          
    )
  )
)

---

我已经决定这是一个有趣的理论练习,但却是一个实际的噩梦.您可能需要数百个示例来确保任何解决方案都能正常工作,然后正如您所说,有人带着示例101来再次破坏代码.

---

TBH - 没有OP的输入,甚至很难验证对该文档所做的基本假设.即使是"父母有下一个兄弟"逻辑的跟踪备份文档的基础也可能过于简单化了可能的组合.