CodeExplorer
You are a developer and looking for Shopware projects?
Apply Now!
loadHTML example
private function parseXhtml(string $htmlContent, string $charset = 'UTF-8'): \DOMDocument
{
$htmlContent = $this->convertToHtmlEntities($htmlContent, $charset);
$internalErrors = libxml_use_internal_errors(true);
$dom = new \DOMDocument('1.0', $charset);
$dom->validateOnParse = true;
if ('' !== trim($htmlContent)) {
@$dom->loadHTML($htmlContent);
}
libxml_use_internal_errors($internalErrors);
return $dom;
}
/** * Converts charset to HTML-entities to ensure valid parsing. */
private function convertToHtmlEntities(string $htmlContent, string $charset = 'UTF-8'): string
{
{
$htmlContent = $this->convertToHtmlEntities($htmlContent, $charset);
$internalErrors = libxml_use_internal_errors(true);
$dom = new \DOMDocument('1.0', $charset);
$dom->validateOnParse = true;
if ('' !== trim($htmlContent)) {
@$dom->loadHTML($htmlContent);
}
libxml_use_internal_errors($internalErrors);
return $dom;
}
/** * Converts charset to HTML-entities to ensure valid parsing. */
private function convertToHtmlEntities(string $htmlContent, string $charset = 'UTF-8'): string
{
protected $registry;
public function set_registry(SimplePie_Registry $registry)
{
$this->registry = $registry;
}
public function parse(&$data, $encoding, $url = '')
{
if (class_exists('DOMXpath') && function_exists('Mf2\parse')) {
$doc = new DOMDocument();
@$doc->loadHTML($data);
$xpath = new DOMXpath($doc);
// Check for both h-feed and h-entry, as both a feed with no entries // and a list of entries without an h-feed wrapper are both valid. $query = '//*[contains(concat(" ", @class, " "), " h-feed ") or '.
'contains(concat(" ", @class, " "), " h-entry ")]';
$result = $xpath->query($query);
if ($result->length !== 0) {
return $this->parse_microformats($data, $url);
}
}
public function set_registry(SimplePie_Registry $registry)
{
$this->registry = $registry;
}
public function parse(&$data, $encoding, $url = '')
{
if (class_exists('DOMXpath') && function_exists('Mf2\parse')) {
$doc = new DOMDocument();
@$doc->loadHTML($data);
$xpath = new DOMXpath($doc);
// Check for both h-feed and h-entry, as both a feed with no entries // and a list of entries without an h-feed wrapper are both valid. $query = '//*[contains(concat(" ", @class, " "), " h-feed ") or '.
'contains(concat(" ", @class, " "), " h-entry ")]';
$result = $xpath->query($query);
if ($result->length !== 0) {
return $this->parse_microformats($data, $url);
}
}
class FormTest extends TestCase
{
public static function setUpBeforeClass(): void
{
// Ensure that the private helper class FormFieldRegistry is loaded class_exists(Form::class);
}
public function testConstructorThrowsExceptionIfTheNodeHasNoFormAncestor()
{
$dom = new \DOMDocument();
$dom->loadHTML(' <html> <input type="submit" /> <form> <input type="foo" /> </form> <button /> </html> ');
$nodes = $dom->getElementsByTagName('input');
{
public static function setUpBeforeClass(): void
{
// Ensure that the private helper class FormFieldRegistry is loaded class_exists(Form::class);
}
public function testConstructorThrowsExceptionIfTheNodeHasNoFormAncestor()
{
$dom = new \DOMDocument();
$dom->loadHTML(' <html> <input type="submit" /> <form> <input type="foo" /> </form> <button /> </html> ');
$nodes = $dom->getElementsByTagName('input');
$locate = $this->registry->create('Locator', array(&$file, $this->timeout, $this->useragent, $this->max_checked_feeds, $this->force_fsockopen, $this->curl_options));
if (!$locate->is_feed($file))
{
$copyStatusCode = $file->status_code;
$copyContentType = $file->headers['content-type'];
try
{
$microformats = false;
if (class_exists('DOMXpath') && function_exists('Mf2\parse')) {
$doc = new DOMDocument();
@$doc->loadHTML($file->body);
$xpath = new DOMXpath($doc);
// Check for both h-feed and h-entry, as both a feed with no entries // and a list of entries without an h-feed wrapper are both valid. $query = '//*[contains(concat(" ", @class, " "), " h-feed ") or '.
'contains(concat(" ", @class, " "), " h-entry ")]';
$result = $xpath->query($query);
$microformats = $result->length !== 0;
}
// Now also do feed discovery, but if microformats were found don't // overwrite the current value of file. $discovered = $locate->find($this->autodiscovery,
if (!$locate->is_feed($file))
{
$copyStatusCode = $file->status_code;
$copyContentType = $file->headers['content-type'];
try
{
$microformats = false;
if (class_exists('DOMXpath') && function_exists('Mf2\parse')) {
$doc = new DOMDocument();
@$doc->loadHTML($file->body);
$xpath = new DOMXpath($doc);
// Check for both h-feed and h-entry, as both a feed with no entries // and a list of entries without an h-feed wrapper are both valid. $query = '//*[contains(concat(" ", @class, " "), " h-feed ") or '.
'contains(concat(" ", @class, " "), " h-entry ")]';
$result = $xpath->query($query);
$microformats = $result->length !== 0;
}
// Now also do feed discovery, but if microformats were found don't // overwrite the current value of file. $discovered = $locate->find($this->autodiscovery,
// PHP's \DOMDocument::saveXML() encodes carriage returns as so
// normalize all newlines to line feeds.
$html = str_replace(["\r\n", "\r"], "\n", $html);
// PHP's \DOMDocument serialization adds extra whitespace when the markup // of the wrapping document contains newlines, so ensure we remove all // newlines before injecting the actual HTML body to be processed. $document = strtr($document, ["\n" => '', '!html' => $html]);
$dom = new \DOMDocument();
// Ignore warnings during HTML soup loading. @$dom->loadHTML($document, LIBXML_NOBLANKS);
return $dom;
}
/** * Converts the body of a \DOMDocument back to an HTML snippet. * * The function serializes the body part of a \DOMDocument back to an (X)HTML * snippet. The resulting (X)HTML snippet will be properly formatted to be * compatible with HTML user agents. * * @param \DOMDocument $document * A \DOMDocument object to serialize, only the tags below the first <body> * node will be converted. * * @return string * A valid (X)HTML snippet, as a string. */
// PHP's \DOMDocument serialization adds extra whitespace when the markup // of the wrapping document contains newlines, so ensure we remove all // newlines before injecting the actual HTML body to be processed. $document = strtr($document, ["\n" => '', '!html' => $html]);
$dom = new \DOMDocument();
// Ignore warnings during HTML soup loading. @$dom->loadHTML($document, LIBXML_NOBLANKS);
return $dom;
}
/** * Converts the body of a \DOMDocument back to an HTML snippet. * * The function serializes the body part of a \DOMDocument back to an (X)HTML * snippet. The resulting (X)HTML snippet will be properly formatted to be * compatible with HTML user agents. * * @param \DOMDocument $document * A \DOMDocument object to serialize, only the tags below the first <body> * node will be converted. * * @return string * A valid (X)HTML snippet, as a string. */
private function getParts(string $originalTrans): array
{
if (!$this->parseHTML) {
return [[true, true, $originalTrans]];
}
$html = mb_encode_numericentity($originalTrans, [0x80, 0xFFFF, 0, 0xFFFF], mb_detect_encoding($originalTrans, null, true) ?: 'UTF-8');
$useInternalErrors = libxml_use_internal_errors(true);
$dom = new \DOMDocument();
$dom->loadHTML('<trans>'.$html.'</trans>');
libxml_clear_errors();
libxml_use_internal_errors($useInternalErrors);
return $this->parseNode($dom->childNodes->item(1)->childNodes->item(0)->childNodes->item(0));
}
private function parseNode(\DOMNode $node): array
{
$parts = [];
{
if (!$this->parseHTML) {
return [[true, true, $originalTrans]];
}
$html = mb_encode_numericentity($originalTrans, [0x80, 0xFFFF, 0, 0xFFFF], mb_detect_encoding($originalTrans, null, true) ?: 'UTF-8');
$useInternalErrors = libxml_use_internal_errors(true);
$dom = new \DOMDocument();
$dom->loadHTML('<trans>'.$html.'</trans>');
libxml_clear_errors();
libxml_use_internal_errors($useInternalErrors);
return $this->parseNode($dom->childNodes->item(1)->childNodes->item(0)->childNodes->item(0));
}
private function parseNode(\DOMNode $node): array
{
$parts = [];
}
/** * Returns a view output as SimpleXMLElement. * * @return \SimpleXMLElement|null * The HTML DOM. */
protected function getHtmlDom($output) {
$html_dom = new \DOMDocument();
@$html_dom->loadHTML($output);
if ($html_dom) {
// It's much easier to work with simplexml than DOM, luckily enough // we can just simply import our DOM tree. return simplexml_import_dom($html_dom);
}
return NULL;
}
}
/**
* Parse a content and return the html element.
*
* @param string $content
* The html to parse.
*
* @return array
* An array containing simplexml objects.
*/
protected function parseContent($content) {
$htmlDom = new \DOMDocument();
@$htmlDom->loadHTML('<?xml encoding="UTF-8">' . $content);
$elements = simplexml_import_dom($htmlDom);
return $elements;
}
/** * Performs an xpath search on a certain content. * * The search is relative to the root element of the $content variable. * * @param string $content * The html to parse. * @param string $xpath * The xpath string to use in the search. * @param array $arguments * Some arguments for the xpath. * * @return array|false * The return value of the xpath search. For details on the xpath string * format and return values see the SimpleXML documentation, * http://php.net/manual/function.simplexml-element-xpath.php. */
protected function parseContent($content) {
$htmlDom = new \DOMDocument();
@$htmlDom->loadHTML('<?xml encoding="UTF-8">' . $content);
$elements = simplexml_import_dom($htmlDom);
return $elements;
}
/** * Performs an xpath search on a certain content. * * The search is relative to the root element of the $content variable. * * @param string $content * The html to parse. * @param string $xpath * The xpath string to use in the search. * @param array $arguments * Some arguments for the xpath. * * @return array|false * The return value of the xpath search. For details on the xpath string * format and return values see the SimpleXML documentation, * http://php.net/manual/function.simplexml-element-xpath.php. */
$pos_tag_end = $i;
}
}
// Get the HTML: this will be the opening part of a single tag, e.g.: // <a href="/" data-drupal-link-system-path="<front>"> $tag = substr($html_markup, $pos_tag_start ?? 0, $pos_tag_end - $pos_tag_start + 1);
// Parse it into a DOMDocument so we can reliably read and modify // attributes. $dom = new \DOMDocument();
@$dom->loadHTML('<!DOCTYPE html><html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8" /></head><body>' . $tag . '</body></html>');
$node = $dom->getElementsByTagName('body')->item(0)->firstChild;
// Ensure we don't set the "active" class twice on the same element. $class = $node->getAttribute('class');
$add_active = !in_array('is-active', explode(' ', $class));
// The language of an active link is equal to the current language. if ($add_active && $url_language) {
if ($node->hasAttribute('hreflang') && $node->getAttribute('hreflang') !== $url_language) {
$add_active = FALSE;
}
}
}
}
// Get the HTML: this will be the opening part of a single tag, e.g.: // <a href="/" data-drupal-link-system-path="<front>"> $tag = substr($html_markup, $pos_tag_start ?? 0, $pos_tag_end - $pos_tag_start + 1);
// Parse it into a DOMDocument so we can reliably read and modify // attributes. $dom = new \DOMDocument();
@$dom->loadHTML('<!DOCTYPE html><html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8" /></head><body>' . $tag . '</body></html>');
$node = $dom->getElementsByTagName('body')->item(0)->firstChild;
// Ensure we don't set the "active" class twice on the same element. $class = $node->getAttribute('class');
$add_active = !in_array('is-active', explode(' ', $class));
// The language of an active link is equal to the current language. if ($add_active && $url_language) {
if ($node->hasAttribute('hreflang') && $node->getAttribute('hreflang') !== $url_language) {
$add_active = FALSE;
}
}
if ( ! class_exists( 'DOMDocument' ) ) {
// @codeCoverageIgnoreStart return true;
// @codeCoverageIgnoreEnd }
$doc = new DOMDocument();
// Suppress warnings generated by loadHTML. $errors = libxml_use_internal_errors( true );
// phpcs:ignore WordPress.PHP.NoSilencedErrors.Discouraged @$doc->loadHTML(
sprintf(
'<!DOCTYPE html><html><head><meta charset="%s"></head><body>%s</body></html>',
esc_attr( get_bloginfo( 'charset' ) ),
$instance['text']
)
);
libxml_use_internal_errors( $errors );
$body = $doc->getElementsByTagName( 'body' )->item( 0 );
// See $allowedposttags.
// @codeCoverageIgnoreStart return true;
// @codeCoverageIgnoreEnd }
$doc = new DOMDocument();
// Suppress warnings generated by loadHTML. $errors = libxml_use_internal_errors( true );
// phpcs:ignore WordPress.PHP.NoSilencedErrors.Discouraged @$doc->loadHTML(
sprintf(
'<!DOCTYPE html><html><head><meta charset="%s"></head><body>%s</body></html>',
esc_attr( get_bloginfo( 'charset' ) ),
$instance['text']
)
);
libxml_use_internal_errors( $errors );
$body = $doc->getElementsByTagName( 'body' )->item( 0 );
// See $allowedposttags.
namespace Symfony\Component\DomCrawler\Tests;
use PHPUnit\Framework\TestCase;
use Symfony\Component\DomCrawler\Link;
class LinkTest extends TestCase
{
public function testConstructorWithANonATag()
{
$this->expectException(\LogicException::class);
$dom = new \DOMDocument();
$dom->loadHTML('<html><div><div></html>');
new Link($dom->getElementsByTagName('div')->item(0), 'http://www.example.com/');
}
public function testBaseUriIsOptionalWhenLinkUrlIsAbsolute()
{
$dom = new \DOMDocument();
$dom->loadHTML('<html><a href="https://example.com/foo">foo</a></html>');
$link = new Link($dom->getElementsByTagName('a')->item(0));
$this->assertSame('https://example.com/foo', $link->getUri());
}
use PHPUnit\Framework\TestCase;
use Symfony\Component\DomCrawler\Link;
class LinkTest extends TestCase
{
public function testConstructorWithANonATag()
{
$this->expectException(\LogicException::class);
$dom = new \DOMDocument();
$dom->loadHTML('<html><div><div></html>');
new Link($dom->getElementsByTagName('div')->item(0), 'http://www.example.com/');
}
public function testBaseUriIsOptionalWhenLinkUrlIsAbsolute()
{
$dom = new \DOMDocument();
$dom->loadHTML('<html><a href="https://example.com/foo">foo</a></html>');
$link = new Link($dom->getElementsByTagName('a')->item(0));
$this->assertSame('https://example.com/foo', $link->getUri());
}
namespace Symfony\Component\DomCrawler\Tests;
use PHPUnit\Framework\TestCase;
use Symfony\Component\DomCrawler\Image;
class ImageTest extends TestCase
{
public function testConstructorWithANonImgTag()
{
$this->expectException(\LogicException::class);
$dom = new \DOMDocument();
$dom->loadHTML('<html><div><div></html>');
new Image($dom->getElementsByTagName('div')->item(0), 'http://www.example.com/');
}
public function testBaseUriIsOptionalWhenImageUrlIsAbsolute()
{
$dom = new \DOMDocument();
$dom->loadHTML('<html><img alt="foo" src="https://example.com/foo" /></html>');
$image = new Image($dom->getElementsByTagName('img')->item(0));
$this->assertSame('https://example.com/foo', $image->getUri());
}
use PHPUnit\Framework\TestCase;
use Symfony\Component\DomCrawler\Image;
class ImageTest extends TestCase
{
public function testConstructorWithANonImgTag()
{
$this->expectException(\LogicException::class);
$dom = new \DOMDocument();
$dom->loadHTML('<html><div><div></html>');
new Image($dom->getElementsByTagName('div')->item(0), 'http://www.example.com/');
}
public function testBaseUriIsOptionalWhenImageUrlIsAbsolute()
{
$dom = new \DOMDocument();
$dom->loadHTML('<html><img alt="foo" src="https://example.com/foo" /></html>');
$image = new Image($dom->getElementsByTagName('img')->item(0));
$this->assertSame('https://example.com/foo', $image->getUri());
}
$predicates[] = "@$attribute='$value'";
}
if (!empty($properties['content'])) {
$predicates[] = "contains(.,'{$properties['content']}')";
}
if (!empty($predicates)) {
$query .= '[' . implode(' and ', $predicates) . ']';
}
// Execute the query. $document = new \DOMDocument();
$document->loadHTML($html);
$xpath = new \DOMXPath($document);
self::assertEquals($count, $xpath->query($query)->length);
}
/** * Checks that the given XPath query has no results in a given HTML snippet. * * @param string $query * The XPath query to execute. * @param string $html * The HTML snippet to check. * * @internal */
}
if (!empty($properties['content'])) {
$predicates[] = "contains(.,'{$properties['content']}')";
}
if (!empty($predicates)) {
$query .= '[' . implode(' and ', $predicates) . ']';
}
// Execute the query. $document = new \DOMDocument();
$document->loadHTML($html);
$xpath = new \DOMXPath($document);
self::assertEquals($count, $xpath->query($query)->length);
}
/** * Checks that the given XPath query has no results in a given HTML snippet. * * @param string $query * The XPath query to execute. * @param string $html * The HTML snippet to check. * * @internal */
public function testAddHtmlContentUnsupportedCharset()
{
$crawler = $this->createCrawler();
$crawler->addHtmlContent($this->getDoctype().file_get_contents(__DIR__.'/Fixtures/windows-1250.html'), 'Windows-1250');
$this->assertEquals('Žťčýů', $crawler->filterXPath('//p')->text());
}
public function createTestCrawler($uri = null)
{
$dom = new \DOMDocument();
$dom->loadHTML($this->getDoctype().' <html> <body> <a href="foo">Foo</a> <a href="/foo"> Fabien\'s Foo </a> <a href="/foo">Fabien"s Foo</a> <a href="/foo">\' Fabien"s Foo</a> <a href="/bar"><img alt="Bar"/></a> <a href="/bar"><img alt=" Fabien\'s Bar "/></a> <a href="/bar"><img alt="Fabien"s Bar"/></a> <a href="/bar"><img alt="\' Fabien"s Bar"/></a> <a href="?get=param">GetLink</a> <a href="/example">Klausi|Claudiu</a> <form action="foo" id="FooFormId"> <input type="text" value="TextValue" name="TextName" /> <input type="submit" value="FooValue" name="FooName" id="FooId" /> <input type="button" value="BarValue" name="BarName" id="BarId" /> <button value="ButtonValue" name="ButtonName" id="ButtonId" /> </form> <input type="submit" value="FooBarValue" name="FooBarName" form="FooFormId" /> <input type="text" value="FooTextValue" name="FooTextName" form="FooFormId" /> <ul class="first"> <li class="first">One</li> <li>Two</li> <li>Three</li> </ul> <ul> <li>One Bis</li> <li>Two Bis</li> <li>Three Bis</li> </ul> <p class="whitespace"> Elsa <3 </p> <div id="parent"> <div id="child"></div> <div id="child2" xmlns:foo="http://example.com"></div> </div> <div id="sibling"><img /></div> <div id="complex-elements"> <div class="one"> Parent text <span>Child text</span> </div> <div class="two"> <span>Child text</span> Parent text </div> <div class="three"> Parent text <span>Child text</span> Parent text </div> <div class="four"> <span>Child text</span> </div> <div class="five"><span>Child text</span> <span>Another child</span></div> <script class="six" type="text/javascript"> console.log("Test JavaScript content"); </script> </div> </body> </html> ');
{
$crawler = $this->createCrawler();
$crawler->addHtmlContent($this->getDoctype().file_get_contents(__DIR__.'/Fixtures/windows-1250.html'), 'Windows-1250');
$this->assertEquals('Žťčýů', $crawler->filterXPath('//p')->text());
}
public function createTestCrawler($uri = null)
{
$dom = new \DOMDocument();
$dom->loadHTML($this->getDoctype().' <html> <body> <a href="foo">Foo</a> <a href="/foo"> Fabien\'s Foo </a> <a href="/foo">Fabien"s Foo</a> <a href="/foo">\' Fabien"s Foo</a> <a href="/bar"><img alt="Bar"/></a> <a href="/bar"><img alt=" Fabien\'s Bar "/></a> <a href="/bar"><img alt="Fabien"s Bar"/></a> <a href="/bar"><img alt="\' Fabien"s Bar"/></a> <a href="?get=param">GetLink</a> <a href="/example">Klausi|Claudiu</a> <form action="foo" id="FooFormId"> <input type="text" value="TextValue" name="TextName" /> <input type="submit" value="FooValue" name="FooName" id="FooId" /> <input type="button" value="BarValue" name="BarName" id="BarId" /> <button value="ButtonValue" name="ButtonName" id="ButtonId" /> </form> <input type="submit" value="FooBarValue" name="FooBarName" form="FooFormId" /> <input type="text" value="FooTextValue" name="FooTextName" form="FooFormId" /> <ul class="first"> <li class="first">One</li> <li>Two</li> <li>Three</li> </ul> <ul> <li>One Bis</li> <li>Two Bis</li> <li>Three Bis</li> </ul> <p class="whitespace"> Elsa <3 </p> <div id="parent"> <div id="child"></div> <div id="child2" xmlns:foo="http://example.com"></div> </div> <div id="sibling"><img /></div> <div id="complex-elements"> <div class="one"> Parent text <span>Child text</span> </div> <div class="two"> <span>Child text</span> Parent text </div> <div class="three"> Parent text <span>Child text</span> Parent text </div> <div class="four"> <span>Child text</span> </div> <div class="five"><span>Child text</span> <span>Another child</span></div> <script class="six" type="text/javascript"> console.log("Test JavaScript content"); </script> </div> </body> </html> ');
protected function getXPathResultCount($query, $html) {
$document = new \DOMDocument();
$document->loadHTML($html);
$xpath = new \DOMXPath($document);
return $xpath->query($query)->length;
}
/** * Tests the storage method. */
public function testStorage() {
$attribute = new Attribute(['class' => ['example-class']]);