protected function FeedsXPathParserHTML::setup in Feeds XPath Parser 7
Same name and namespace in other branches
- 6 FeedsXPathParserHTML.inc \FeedsXPathParserHTML::setup()
Classes that use FeedsXPathParserBase must implement this.
Parameters
array $source_config: The configuration for the source.
FeedsFetcherResult $fetcher_result: A FeedsFetcherResult object.
Return value
DOMDocument The DOMDocument to perform XPath queries on.
Overrides FeedsXPathParserBase::setup
File
- ./
FeedsXPathParserHTML.inc, line 35 - s Contains FeedsXPathParserHTML.
Class
- FeedsXPathParserHTML
- XPath parsing for HTML.
Code
protected function setup($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;
}