class FeedsXPathParserHTML in Feeds XPath Parser 6

Parse HTML using XPath.

Hierarchy

• class \FeedsConfigurable
  • class \FeedsPlugin implements FeedsSourceInterface
    • class \FeedsParser
      • class \FeedsXPathParserBase
        • class \FeedsXPathParserHTML

2 string references to 'FeedsXPathParserHTML'

FeedsXPathParseHTMLTestCase::test in tests/feeds_xpathparser_parser_html.test

Run tests.

feeds_xpathparser_feeds_plugins in ./feeds_xpathparser.module

Implementation of hook_feeds_plugins().

File

./FeedsXPathParserHTML.inc, line 11

s Provides the FeedsXPathParserHTML class.

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);
  }

}

Members

Name	Modifiers	Type	Description	Overrides
FeedsConfigurable::$config	protected	property
FeedsConfigurable::$disabled	protected	property	CTools export enabled status of this object.
FeedsConfigurable::$export_type	protected	property
FeedsConfigurable::$id	protected	property
FeedsConfigurable::addConfig	public	function	Similar to setConfig but adds to existing configuration.	1
FeedsConfigurable::configFormSubmit	public	function	Submission handler for configForm().	3
FeedsConfigurable::copy	public	function	Copy a configuration.	1
FeedsConfigurable::existing	public	function	Determine whether this object is persistent and enabled. I. e. it is defined either in code or in the database and it is enabled.	1
FeedsConfigurable::getConfig	public	function	Implementation of getConfig().	1
FeedsConfigurable::instance	public static	function	Instantiate a FeedsConfigurable object.	1
FeedsConfigurable::setConfig	public	function	Set configuration.	1
FeedsConfigurable::__get	public	function	Override magic method __get(). Make sure that $this->config goes through getConfig()
FeedsConfigurable::__isset	public	function	Override magic method __isset(). This is needed due to overriding __get().
FeedsParser::clear	public	function	Clear all caches for results for given source.
FeedsParser::getSourceElement	public	function	Get an element identified by $element_key of the given item. The element key corresponds to the values in the array returned by FeedsParser::getMappingSources().	1
FeedsPlugin::hasSourceConfig	public	function	Returns TRUE if $this->sourceForm() returns a form. Overrides FeedsSourceInterface::hasSourceConfig
FeedsPlugin::loadMappers	protected static	function	Loads on-behalf implementations from mappers/ directory.
FeedsPlugin::save	public	function	Save changes to the configuration of this object. Delegate saving to parent (= Feed) which will collect information from this object by way of getConfig() and store it. Overrides FeedsConfigurable::save
FeedsPlugin::sourceDelete	public	function	A source is being deleted. Overrides FeedsSourceInterface::sourceDelete	1
FeedsPlugin::sourceSave	public	function	A source is being saved. Overrides FeedsSourceInterface::sourceSave	1
FeedsPlugin::__construct	protected	function	Constructor. Overrides FeedsConfigurable::__construct
FeedsXPathParserBase::$doc	protected	property
FeedsXPathParserBase::$modified_queries	protected	property
FeedsXPathParserBase::$rawXML	protected	property
FeedsXPathParserBase::$xpath	protected	property
FeedsXPathParserBase::configDefaults	public	function	Define defaults. Overrides FeedsConfigurable::configDefaults
FeedsXPathParserBase::configForm	public	function	Override parent::configForm(). Overrides FeedsConfigurable::configForm
FeedsXPathParserBase::configFormValidate	public	function	Override parent::sourceFormValidate(). Overrides FeedsConfigurable::configFormValidate
FeedsXPathParserBase::errorStart	protected	function
FeedsXPathParserBase::errorStop	protected	function
FeedsXPathParserBase::filterMappings	protected	function	Filters mappings, returning the ones that belong to us.
FeedsXPathParserBase::getMappingSources	public	function	Override parent::getMappingSources(). Overrides FeedsParser::getMappingSources
FeedsXPathParserBase::getOwnMappings	protected	function
FeedsXPathParserBase::parse	public	function	Implements FeedsParser::parse(). Overrides FeedsParser::parse
FeedsXPathParserBase::parseSourceElement	protected	function	Parses one item from the context array.
FeedsXPathParserBase::sourceDefaults	public	function	Define defaults. Overrides FeedsPlugin::sourceDefaults
FeedsXPathParserBase::sourceForm	public	function	Source form. Overrides FeedsPlugin::sourceForm
FeedsXPathParserBase::sourceFormValidate	public	function	Override parent::sourceFormValidate(). Overrides FeedsPlugin::sourceFormValidate
FeedsXPathParserHTML::getRaw	protected	function	Overrides FeedsXPathParserBase::getRaw
FeedsXPathParserHTML::setup	protected	function	Implementation of FeedsXPathParserBase::setup(). Overrides FeedsXPathParserBase::setup