FeedsXPathParserHTML.inc in Feeds XPath Parser 6

s Provides the FeedsXPathParserHTML class.

File

FeedsXPathParserHTML.inc

<?php

/**
 * @files
 * Provides the FeedsXPathParserHTML class.
 */

/**
 * Parse HTML using XPath.
 */
class FeedsXPathParserHTML extends FeedsXPathParserBase {

  /**
   * Implementation of FeedsXPathParserBase::setup().
   */
  protected function setup($source_config, FeedsImportBatch $batch) {
    if (!empty($source_config['exp']['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'];
      $raw = tidy_repair_string(trim($batch
        ->getRaw()), $config, $encoding);
    }
    else {
      $raw = $batch
        ->getRaw();
    }
    $doc = new DOMDocument();

    // Use our own error handling.
    $use = $this
      ->errorStart();
    $success = $doc
      ->loadHTML($raw);
    unset($raw);
    $this
      ->errorStop($use, $source_config['exp']['errors']);
    if (!$success) {
      throw new Exception(t('There was an error parsing the HTML document.'));
    }
    return $doc;
  }
  protected function getRaw(DOMNode $node) {

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

}

Classes

Name	Description
FeedsXPathParserHTML	Parse HTML using XPath.