class FeedsExHtml in Feeds extensible parsers 7.2
Same name and namespace in other branches
- 7 src/FeedsExHtml.inc \FeedsExHtml
Parses HTML documents with XPath.
Hierarchy
- class \FeedsExBase extends \FeedsParser
- class \FeedsExXml
- class \FeedsExHtml
- class \FeedsExXml
Expanded class hierarchy of FeedsExHtml
6 string references to 'FeedsExHtml'
- FeedsExHtmlTests::setUp in src/
Tests/ FeedsExHtml.test - FeedsExHtmlUnitTests::testCP866Encoded in src/
Tests/ FeedsExHtml.test - Tests parsing a CP866 (Russian) encoded file.
- FeedsExHtmlUnitTests::testEUCJPEncodedNoDeclaration in src/
Tests/ FeedsExHtml.test - Tests a EUC-JP (Japanese) encoded file without the encoding declaration.
- FeedsExHtmlUnitTests::testLinkIsSet in src/
Tests/ FeedsExHtml.test - Tests that the link propery is set.
- FeedsExHtmlUnitTests::testSimpleParsing in src/
Tests/ FeedsExHtml.test - Tests simple parsing.
File
- src/
FeedsExHtml.inc, line 11 - Contains FeedsExHtml.
View source
class FeedsExHtml extends FeedsExXml {
/**
* Whether this version of PHP has the correct saveHTML() method.
*
* @var bool
*/
protected $useSaveHTML;
/**
* {@inheritdoc}
*/
public function __construct($id) {
parent::__construct($id);
// DOMDocument::saveHTML() cannot take $node as an argument prior to 5.3.6.
$this->useSaveHTML = version_compare(PHP_VERSION, '5.3.6', '>=');
}
/**
* {@inheritdoc}
*/
protected function convertEncoding($data, $encoding = 'UTF-8') {
// Check for an encoding declaration.
$matches = FALSE;
if (preg_match('/<meta[^>]+charset\\s*=\\s*["\']?([\\w-]+)\\b/i', $data, $matches)) {
$encoding = $matches[1];
}
elseif ($detected = parent::detectEncoding($data)) {
$encoding = $detected;
}
// Unsupported encodings are converted here into UTF-8.
$php_supported = array(
'utf-8',
'us-ascii',
'ascii',
);
if (in_array(strtolower($encoding), $php_supported)) {
return $data;
}
$data = parent::convertEncoding($data, $encoding);
if ($matches) {
$data = preg_replace('/(<meta[^>]+charset\\s*=\\s*["\']?)([\\w-]+)\\b/i', '$1UTF-8', $data, 1);
}
return $data;
}
/**
* {@inheritdoc}
*/
protected function prepareDocument(FeedsSource $source, FeedsFetcherResult $fetcher_result) {
$raw = $fetcher_result
->getRaw();
if (!strlen(trim($raw))) {
throw new FeedsExEmptyException();
}
$raw = $this
->convertEncoding($raw);
if ($this->config['use_tidy'] && extension_loaded('tidy')) {
$raw = tidy_repair_string($raw, $this
->getTidyConfig(), 'utf8');
}
return FeedsExXmlUtility::createHtmlDocument($raw);
}
/**
* {@inheritdoc}
*/
protected function getRaw(DOMNode $node) {
if ($this->useSaveHTML) {
return $node->ownerDocument
->saveHTML($node);
}
return $node->ownerDocument
->saveXML($node, LIBXML_NOEMPTYTAG);
}
/**
* {@inheritdoc}
*/
protected function getTidyConfig() {
return 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,
);
}
}
Members
Name | Modifiers | Type | Description | Overrides |
---|---|---|---|---|
FeedsExBase:: |
protected | property | Whether the current system handles mb_* functions. | |
FeedsExBase:: |
protected | property | The object used to display messages to the user. | |
FeedsExBase:: |
public | function | ||
FeedsExBase:: |
protected | function | Renders our debug messages into a list. | |
FeedsExBase:: |
protected | function | Delegates parsing to the subclass. | |
FeedsExBase:: |
protected | function | Detects the encoding of a string. | |
FeedsExBase:: |
protected | function | Executes the source expressions. | |
FeedsExBase:: |
protected | function | Returns the configuration form table header. | |
FeedsExBase:: |
public | function | ||
FeedsExBase:: |
public | function | Returns the messenger. | |
FeedsExBase:: |
public | function | ||
FeedsExBase:: |
protected | function | Returns whether or not this parser uses a context query. | 2 |
FeedsExBase:: |
public | function | ||
FeedsExBase:: |
protected | function | Loads the necessary library. | 2 |
FeedsExBase:: |
protected | function | Logs errors. | |
FeedsExBase:: |
public | function | ||
FeedsExBase:: |
protected | function | Prepares the expressions for parsing. | |
FeedsExBase:: |
protected | function | Prepares the variable map used to substitution. | |
FeedsExBase:: |
protected | function | Prints errors to the screen. | |
FeedsExBase:: |
public | function | Sets the messenger to be used to display messages. | |
FeedsExBase:: |
public | function | Sets the multibyte handling. | |
FeedsExBase:: |
public | function | ||
FeedsExBase:: |
public | function | ||
FeedsExBase:: |
public | function | ||
FeedsExBase:: |
public | function | ||
FeedsExHtml:: |
protected | property | Whether this version of PHP has the correct saveHTML() method. | |
FeedsExHtml:: |
protected | function |
Converts a string to UTF-8. Overrides FeedsExXml:: |
|
FeedsExHtml:: |
protected | function |
Returns the raw XML of a DOM node. Overrides FeedsExXml:: |
|
FeedsExHtml:: |
protected | function |
Returns the options for phptidy. Overrides FeedsExXml:: |
|
FeedsExHtml:: |
protected | function |
Prepares the DOM document. Overrides FeedsExXml:: |
|
FeedsExHtml:: |
public | function |
Overrides FeedsExBase:: |
|
FeedsExXml:: |
protected | property | The previous value for the entity loader. | |
FeedsExXml:: |
protected | property | The previous value for XML error handling. | |
FeedsExXml:: |
protected | property | The FeedsExXpathDomXpath object used for parsing. | |
FeedsExXml:: |
protected | function |
Allows subclasses to cleanup after parsing. Overrides FeedsExBase:: |
|
FeedsExXml:: |
public | function |
Overrides FeedsExBase:: |
|
FeedsExXml:: |
public | function |
Overrides FeedsExBase:: |
|
FeedsExXml:: |
protected | function |
Returns a form element for a specific column. Overrides FeedsExBase:: |
1 |
FeedsExXml:: |
protected | function |
Reuturns the list of table headers. Overrides FeedsExBase:: |
1 |
FeedsExXml:: |
protected | function |
Returns rows to be parsed. Overrides FeedsExBase:: |
1 |
FeedsExXml:: |
protected | function |
Executes a single source expression. Overrides FeedsExBase:: |
1 |
FeedsExXml:: |
protected | function |
Returns the errors after parsing. Overrides FeedsExBase:: |
|
FeedsExXml:: |
protected | function |
Allows subclasses to prepare for parsing. Overrides FeedsExBase:: |
1 |
FeedsExXml:: |
protected | function |
Starts internal error handling. Overrides FeedsExBase:: |
|
FeedsExXml:: |
protected | function |
Stops internal error handling. Overrides FeedsExBase:: |
|
FeedsExXml:: |
protected | function |
Validates an expression. Overrides FeedsExBase:: |
1 |