class XPathHTMLParser in Feeds XPath Parser 8

Defines an HTML feed parser.

Plugin annotation

@Plugin(
  id = "feeds_xpathparser_html",
  title = @Translation("XPath HTML parser"),
  description = @Translation("Parse HTML files using XPath.")
)

Hierarchy

• class \Drupal\feeds_xpathparser\ParserBase extends \Drupal\feeds\Plugin\ParserBase implements \Drupal\feeds\FeedPluginFormInterface, FormInterface
  • class \Drupal\feeds_xpathparser\Plugin\feeds\Parser\XPathHTMLParser

File

lib/Drupal/feeds_xpathparser/Plugin/feeds/Parser/XPathHTMLParser.php, line 24

Contains \Drupal\feeds_xpathparser\Plugin\feeds\Parser\XPathHTMLParser.

Namespace

Drupal\feeds_xpathparser\Plugin\feeds\Parser

class XPathHTMLParser extends ParserBase {

  /**
   * {@inheritdoc}
   */
  protected function setup(array $feed_config, FetcherResultInterface $fetcher_result) {
    if (!empty($feed_config['tidy'])) {
      $config = array(
        'merge-divs' => FALSE,
        'merge-spans' => FALSE,
        'join-styles' => FALSE,
        'drop-empty-paras' => FALSE,
        'wrap' => 0,
        'tidy-mark' => FALSE,
        'escape-cdata' => TRUE,
        'word-2000' => TRUE,
      );

      // Default tidy encoding is UTF8.
      $encoding = $feed_config['tidy_encoding'];
      $raw = tidy_repair_string(trim($fetcher_result
        ->getRaw()), $config, $encoding);
    }
    else {
      $raw = $fetcher_result
        ->getRaw();
    }
    $doc = new \DOMDocument();

    // Use our own error handling.
    $use = $this
      ->errorStart();
    $success = $doc
      ->loadHTML($raw);
    unset($raw);
    $this
      ->errorStop($use, $feed_config['errors']);
    if (!$success) {
      throw new \RuntimeException(t('There was an error parsing the HTML document.'));
    }
    return $doc;
  }

  /**
   * {@inheritdoc}
   */
  protected function getRaw(\DOMNode $node) {
    return $this->doc
      ->saveHTML($node);
  }

}

Members

Name	Modifiers	Type	Description	Overrides
FormInterface::getFormId	public	function	Returns a unique string identifying the form.	236
FormInterface::submitForm	public	function	Form submission handler.	192
ParserBase::$doc	protected	property	The DOMDocument to parse.
ParserBase::$rawXML	protected	property	The mappings to return raw XML for.
ParserBase::$xpath	protected	property	The DOMXpath object to use for XPath queries.
ParserBase::baseForm	protected	function
ParserBase::buildForm	public	function	Form constructor. Overrides FormInterface::buildForm
ParserBase::configDefaults	public	function
ParserBase::errorStart	protected	function	Starts custom error handling.
ParserBase::errorStop	protected	function	Stops custom error handling.
ParserBase::feedForm	public	function
ParserBase::feedFormValidate	public	function	Overrides parent::feedFormValidate().
ParserBase::filterMappings	protected	function	Filters mappings, returning the ones that belong to us.
ParserBase::getMappingSources	public	function
ParserBase::getOwnMappings	protected	function	Gets the mappings that are defined by this parser.
ParserBase::getUniques	protected	function	Gets the unique mappings targets that are used by this parser.
ParserBase::kSort	protected	function	Recursivly sorts an array.
ParserBase::parse	public	function
ParserBase::parseSourceElement	protected	function	Parses one item from the context array.
ParserBase::sourceDefaults	public	function
ParserBase::validateForm	public	function	Form validation handler. Overrides FormInterface::validateForm
XPathHTMLParser::getRaw	protected	function	Returns the raw node value. Overrides ParserBase::getRaw
XPathHTMLParser::setup	protected	function	Classes that use ParserBase must implement this. Overrides ParserBase::setup