FeedsXPathParserHTML.inc in Feeds XPath Parser 7

s Contains FeedsXPathParserHTML.

File

FeedsXPathParserHTML.inc

<?php

/**
 * @files
 * Contains FeedsXPathParserHTML.
 */

/**
 * XPath parsing for HTML.
 */
class FeedsXPathParserHTML extends FeedsXPathParserBase {

  /**
   * Whether this version of PHP has a useable saveHTML() method.
   *
   * @var bool
   */
  protected $hasSaveHTML = FALSE;

  /**
   * {@inheritdoc}
   */
  public function __construct($id) {
    parent::__construct($id);

    // DOMDocument::saveHTML() cannot take $node as an argument prior to 5.3.6.
    if (version_compare(phpversion(), '5.3.6', '>=')) {
      $this->hasSaveHTML = TRUE;
    }
  }

  /**
   * {@inheritdoc}
   */
  protected function setup($source_config, FeedsFetcherResult $fetcher_result) {
    if (!empty($source_config['exp']['tidy']) && extension_loaded('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 = $source_config['exp']['tidy_encoding'];
      $raw = tidy_repair_string($fetcher_result
        ->getRaw(), $config, $encoding);
    }
    else {
      $raw = $fetcher_result
        ->getRaw();
    }

    // Some versions of PHP do not handle null bytes.
    $raw = str_replace("\0", '', $raw);
    $document = new DOMDocument();
    $document->strictErrorChecking = FALSE;
    $document->recover = TRUE;

    // Use our own error handling.
    $use = $this
      ->errorStart();
    if (version_compare(PHP_VERSION, '5.4.0', '>=')) {
      $options = LIBXML_NONET;
      $options |= defined('LIBXML_COMPACT') ? LIBXML_COMPACT : 0;
      $options |= defined('LIBXML_PARSEHUGE') ? LIBXML_PARSEHUGE : 0;
      $success = $document
        ->loadHTML($raw, $options);
    }
    else {
      $success = $document
        ->loadHTML($raw);
    }
    $this
      ->errorStop($use, $source_config['exp']['errors']);
    if (!$success) {
      throw new Exception(t('There was an error parsing the HTML document.'));
    }
    return $document;
  }

  /**
   * {@inheritdoc}
   */
  protected function getRaw(DOMNode $node) {
    if ($this->hasSaveHTML) {
      return $this->doc
        ->saveHTML($node);
    }
    return $this->doc
      ->saveXML($node, LIBXML_NOEMPTYTAG);
  }

}

Classes

Name	Description
FeedsXPathParserHTML	XPath parsing for HTML.