How can I extract structured text from an HTML list in PHP?

Question

I have this string:

  
Page 1
  
Page 2
    

      
Sub Page A         


        

Answer 1

I leave a second answer because this time this demonstrates how to do it with the single mapping (in pseudocode):

foreach //li ::
    ID       := string(./@id)
    ParentID := string(./ancestor::li[1]/@id)
    Label    := normalize-space(./text()[1])
    Order    := count(./preceding-sibling::li)+1
    Children := implode(",", ./ul/li/@id)

Because this can be done per each li node regardless in which order, this could be a perfect match for an Iterator, here the current function:

public function current() {

    return [
        'ID'       => $this->evaluate('number(./@id)'),
        'label'    => $this->evaluate('normalize-space(./text()[1])'),
        'order'    => $this->evaluate('count(./preceding-sibling::li)+1'),
        'parentID' => $this->evaluate('number(concat("0", ./ancestor::li[1]/@id))'),
        'children' => $this->implodeNodes(',', './ul/li/@id'),
    ];
}

Full example (Demo) output and code:

+----+----------------+-------+--------+----------+
| ID |     LABEL      | ORDER | PARENT | CHILDREN |
+----+----------------+-------+--------+----------+
|  1 | Page 1         |   1   |    0   |          |
|  2 | Page 2         |   2   |    0   | 3,4,5    |
|  3 | Sub Page A     |   1   |    2   |          |
|  4 | Sub Page B     |   2   |    2   |          |
|  5 | Sub Page C     |   3   |    2   | 6        |
|  6 | Sub Sub Page I |   1   |    5   |          |
|  7 | Page 3         |   3   |    0   | 8        |
|  8 | Sub Page D     |   1   |    7   |          |
|  9 | Page 4         |   4   |    0   |          |
+----+----------------+-------+--------+----------+


class HtmlListIterator extends IteratorIterator
{
    private $xpath;

    public function __construct($html) {

        $doc = new DOMDocument();
        $doc->loadHTML($html);
        $this->xpath = new DOMXPath($doc);
        parent::__construct($this->xpath->query('//li'));
    }

    private function evaluate($expression) {

        return $this->xpath->evaluate($expression, parent::current());
    }

    private function implodeNodes($glue, $expression) {

        return implode(
            $glue, array_map(function ($a) {

                return $a->nodeValue;
            }, iterator_to_array($this->evaluate($expression, parent::current())))
        );
    }

    public function current() {

        return [
            'ID'       => $this->evaluate('number(./@id)'),
            'label'    => $this->evaluate('normalize-space(./text()[1])'),
            'order'    => $this->evaluate('count(./preceding-sibling::li)+1'),
            'parentID' => $this->evaluate('number(concat("0", ./ancestor::li[1]/@id))'),
            'children' => $this->implodeNodes(',', './ul/li/@id'),
        ];
    }
}

print_result(new HtmlListIterator($html));

function print_result($result) {

    echo '+----+----------------+-------+--------+----------+
| ID |     LABEL      | ORDER | PARENT | CHILDREN |
+----+----------------+-------+--------+----------+
';
    foreach ($result as $line) {
        vprintf("| %' 2d | %' -14s |  %' 2d   |   %' 2d   | %-8s |\n", $line);
    }
    echo '+----+----------------+-------+--------+----------+
';
}