PHP DOMDocument::loadHtml方法代码示例

 function _testXPath($xpath_expression)
 {
     if (!class_exists('DOMDocument') || !class_exists('DOMXPath')) {
         if (function_exists('domxml_open_mem')) {
             $dom = domxml_open_mem($this->_response);
             if (!$dom) {
                 $this->fail('Error parsing doc');
                 return false;
             }
             var_dump($dom);
             $xpath = $dom->xpath_init();
             var_dump($xpath);
             $ctx = $dom->xpath_new_context();
             var_dump($xpath_expression);
             $result = $ctx->xpath_eval($xpath_expression);
             var_dump($result);
             $return = new stdClass();
             $return->length = count($result->nodeset);
             return $return;
         }
         $this->fail('No xpath support built in');
         return false;
     } else {
         if (extension_loaded('domxml')) {
             $this->fail('Please disable the domxml extension. Only php5 builtin domxml is supported');
             return false;
         }
     }
     $dom = new DOMDocument();
     $dom->loadHtml($this->_response);
     $xpath = new DOMXPath($dom);
     $node = $xpath->query($xpath_expression);
     return $node;
 }

 protected function __construct($url, $status, array $headers, $body)
 {
     parent::__construct($url, $status, $headers, $body);
     $this->_domDocument = new DOMDocument();
     $this->_domDocument->preserveWhiteSpace = true;
     // We have to silence this out because invalid documents
     // tend to throw allot of warnings
     @$this->_domDocument->loadHtml($body);
 }

 /**
  * @param  string $html
  * @return \DiDom\Element
  * @throws \InvalidArgumentException
  */
 public function loadHtml($html)
 {
     if (!is_string($html)) {
         throw new InvalidArgumentException(sprintf('%s expects parameter 1 to be string, %s given', __METHOD__, is_object($html) ? get_class($html) : gettype($html)));
     }
     libxml_use_internal_errors(true);
     libxml_disable_entity_loader(true);
     $this->document->loadHtml($html);
     libxml_clear_errors();
     libxml_disable_entity_loader(false);
     libxml_use_internal_errors(false);
     return $this;
 }

function get_members($url)
{
    $html = get_html($url);
    if ($html === false) {
        echo 'connection error';
    } else {
        $oldSetting = libxml_use_internal_errors(true);
        libxml_clear_errors();
        $dom = new DOMDocument();
        $dom->loadHtml($html);
        $tbody = $dom->getElementsByTagName('tbody');
        $trs = $tbody[0]->getElementsByTagName('tr');
        global $parteinameFilter;
        $members = array();
        foreach ($trs as $tr) {
            $tds = $tr->getElementsByTagName('td');
            $link = $tds[0]->getElementsByTagName('a');
            $member = array('name' => $link[0]->nodeValue, 'link' => $link[0]->getAttribute('href'), 'partei' => str_replace($parteinameFilter, '', $tds[1]->nodeValue));
            $aze = str_replace(' ', '', htmlentities($tds[2]->nodeValue));
            if ($aze) {
                $member['amtszeitende'] = $aze;
            }
            $members[] = $member;
        }
        libxml_clear_errors();
        libxml_use_internal_errors($oldSetting);
        return $members;
    }
    return false;
}

function get_commitees($url)
{
    $html = get_html($url);
    if ($html === false) {
        echo 'connection error';
    } else {
        $oldSetting = libxml_use_internal_errors(true);
        libxml_clear_errors();
        $dom = new DOMDocument();
        $dom->loadHtml($html);
        $tbody = $dom->getElementsByTagName('tbody');
        $trs = $tbody[0]->getElementsByTagName('tr');
        $commitees = array();
        foreach ($trs as $tr) {
            $tds = $tr->getElementsByTagName('td');
            $link = $tds[0]->getElementsByTagName('a');
            if ($link->length > 0) {
                $commitee = array('name' => $link[0]->nodeValue, 'link' => $link[0]->getAttribute('href'));
            }
            $commitees[] = $commitee;
        }
        libxml_clear_errors();
        libxml_use_internal_errors($oldSetting);
        return $commitees;
    }
    return false;
}

 static function fixChildrenAttribute($elementType, $name, $value)
 {
     var_dump('AbstractElement\\Helper::fixChildrenAttribute needs fixed');
     exit;
     $classPath = '\\AbstractElement\\' . $elementType;
     // each element in contents array for this object
     foreach ($this->contents as $index => $content) {
         // is this an object that extends AbstractElement?
         if (is_a($content, '\\Element')) {
             // is this of the right element type?
             if (is_a($content, $classPath)) {
                 $content->setAttribute($name, $value);
             }
             $content->fixChildrenAttribute($elementType, $name, $value);
         } elseif (is_string($content) && $fixRawHtml) {
             $dom = new \DOMDocument();
             $dom->loadHtml($content);
             $reflectionClass = new \ReflectionClass($classPath);
             $elements = $dom->getElementsByTagName($reflectionClass->getConstant('tag'));
             foreach ($elements as $element) {
                 $element->setAttribute($name, $value);
             }
             $this->contents[$index] = $dom->saveHTML();
         }
     }
 }

 public static function uploadTextarea($texto, $tipo_midia)
 {
     $nomeTipo = TipoMidia::findOrFail($tipo_midia)->descricao;
     // gravando imagem do corpo da noticia
     $dom = new \DOMDocument();
     $dom->loadHtml($texto, LIBXML_HTML_NOIMPLIED | LIBXML_HTML_NODEFDTD);
     $images = $dom->getElementsByTagName('img');
     // foreach <img> in the submited message
     foreach ($images as $img) {
         $src = $img->getAttribute('src');
         // if the img source is 'data-url'
         if (preg_match('/data:image/', $src)) {
             // get the mimetype
             preg_match('/data:image\\/(?<mime>.*?)\\;/', $src, $groups);
             $mimetype = $groups['mime'];
             // Generating a random filename
             $filename = md5(uniqid());
             $filepath = "uploads/" . $nomeTipo . "/" . $filename . '.' . $mimetype;
             // @see http://image.intervention.io/api/
             $image = Image::make($src)->encode($mimetype, 100)->save(public_path($filepath));
             $new_src = asset($filepath);
             $img->removeAttribute('src');
             $img->setAttribute('src', $new_src);
         }
     }
     return $dom->saveHTML();
 }

function remove_link_tags($content)
{
    $old_xml_err = libxml_use_internal_errors(true);
    $dom = new DOMDocument();
    $dom->loadHtml(mb_convert_encoding($content, 'HTML-ENTITIES', "UTF-8"));
    foreach ($dom->getElementsByTagName('link') as $link) {
        $link->parentNode->removeChild($link);
    }
    $content_out = '';
    $node = $dom->firstChild;
    while ($node) {
        $content_out .= $dom->saveHTML($node);
        /* repeat for all nodes at this level */
        $node = $node->nextSibling;
    }
    foreach (libxml_get_errors() as $error) {
        /* just ignore warnings */
        if ($error->level === LIBXML_ERR_WARNING) {
            continue;
        }
        fof_log(__FUNCTION__ . ': ' . $error->message);
    }
    libxml_clear_errors();
    libxml_use_internal_errors($old_xml_err);
    return $content_out;
}

 /**
  * Fetch conversation with 
  *
  * @access public
  * @var    string $gamertag
  * @var    string $region
  * @var    string $sender
  * @return array
  */
 public function fetchConversationWith($gamertag, $region, $sender)
 {
     $gamertag = trim($gamertag);
     $url = 'https://account.xbox.com/' . $region . '/Messages/UserConversation?senderGamerTag=' . $sender;
     $key = $this->version . ':getMessages.' . $gamertag;
     $data = $this->fetch_url($url);
     $doc = new DOMDocument();
     if (!empty($sender) && !empty($gamertag)) {
         $doc->loadHtml($data);
         $xpath = new DOMXPath($doc);
         $postThumbLinks = $xpath->query("//div[@class='messageContent']");
         $i = 0;
         $array = array();
         $last_sender = "";
         foreach ($postThumbLinks as $link) {
             $body = $this->find($link->ownerDocument->saveHTML($link), '<div class="messageBody">', '</div>');
             $time = $this->find($link->ownerDocument->saveHTML($link), '<div class="sentDate localTime">', '</div>');
             $sender = $this->find($link->ownerDocument->saveHTML($link), '<div class="senderGamertag">', '</div>');
             $array[$i]['message'] = $body;
             $array[$i]['time'] = $time;
             if ($sender) {
                 $array[$i]['sender'] = $sender;
                 $last_sender = $sender;
             } else {
                 $array[$i]['sender'] = $last_sender;
             }
             $i++;
         }
     } else {
         return false;
     }
     return $array;
 }

 /**
  * Load HTML or XML.
  * 
  * @param string $string HTML or XML string or file path
  * @param bool   $isFile Indicates that in first parameter was passed to the file path
  * @param string $type Type of document
  * @param int    $options Additional parameters
  */
 public function load($string, $isFile = false, $type = 'html', $options = 0)
 {
     if (!is_string($string)) {
         throw new InvalidArgumentException(sprintf('%s expects parameter 1 to be string, %s given', __METHOD__, is_object($string) ? get_class($string) : gettype($string)));
     }
     if (!in_array(strtolower($type), ['xml', 'html'])) {
         throw new InvalidArgumentException(sprintf('Document type must be "xml" or "html", %s given', __METHOD__, is_object($type) ? get_class($type) : gettype($type)));
     }
     if (!is_integer($options)) {
         throw new InvalidArgumentException(sprintf('%s expects parameter 4 to be integer, %s given', __METHOD__, is_object($options) ? get_class($options) : gettype($options)));
     }
     $string = trim($string);
     if ($isFile) {
         $string = $this->loadFile($string);
     }
     if (substr($string, 0, 5) !== '<?xml') {
         $prolog = sprintf('<?xml version="1.0" encoding="%s"?>', $this->document->encoding);
         $string = $prolog . $string;
     }
     $this->type = strtolower($type);
     Errors::disable();
     $this->type === 'xml' ? $this->document->loadXml($string, $options) : $this->document->loadHtml($string, $options);
     Errors::restore();
     return $this;
 }

 public static function fix($html)
 {
     if (empty($html)) {
         return $html;
     }
     $html = self::xss($html);
     if (substr($html, 0, 2) !== '<p') {
         $html = '<p>' . implode('</p><p>', preg_split('/[\\n\\r]/', $html)) . '</p>';
     }
     $html = trim(str_replace(["\n", "\r"], ' ', self::xss($html)));
     $html = preg_replace('#\\s{2,}#', ' ', $html);
     $valid = 'class|src|target|alt|title|href|rel';
     $html = preg_replace('#<(font|span) style="font-weight[^"]+">([^<]+)</(font|span)>#i', '<strong>$2</strong>', $html);
     $html = preg_replace('#<(font|span) style="font-style:\\s*italic[^"]+">([^<]+)</(font|span)>#i', '<i>$2</i>', $html);
     $html = preg_replace('# (' . $valid . ')=#i', ' |$1|', $html);
     $html = preg_replace('# [a-z]+=["\'][^"\']*["\']#i', '', $html);
     $html = preg_replace('#\\|(' . $valid . ')\\|#i', ' $1=', $html);
     $html = preg_replace('#</?(font|span)[^>]*>#', '', $html);
     $html = preg_replace('#<(/?)div#', '<$1p', $html);
     $html = preg_replace('#<(/?)b>#', '<$1strong>', $html);
     $html = preg_replace('#<br\\s*/?>#', '</p><p>', $html);
     libxml_use_internal_errors(true);
     $DOM = new \DOMDocument();
     $DOM->recover = true;
     $DOM->preserveWhiteSpace = false;
     $DOM->substituteEntities = false;
     $DOM->loadHtml(mb_convert_encoding($html, 'HTML-ENTITIES', 'UTF-8'), LIBXML_NOBLANKS | LIBXML_ERR_NONE);
     $DOM->encoding = 'utf-8';
     $html = $DOM->saveHTML();
     libxml_use_internal_errors(false);
     $html = preg_replace('~<(?:!DOCTYPE|/?(?:\\?xml|html|head|body))[^>]*>\\s*~i', '', $html);
     $html = preg_replace('#<([^\\s]+)[^>]*>\\s*</\\1>#', '', $html);
     $html = preg_replace('#</p>\\s+<p#', '</p><p', $html);
     return trim(str_replace('&nbsp;', ' ', $html));
 }

 /**
  * Returns array, containing detailed results for any Google search.
  *
  * @access       private
  * @param        string        $query      String, containing the search query.
  * @param        string        $tld        String, containing the desired Google top level domain.
  * @return       array                     Returns array, containing the keys 'URL', 'Title' and 'Description'.
  */
 public static function googleArray($query)
 {
     $result = array();
     $pages = 1;
     $delay = 0;
     for ($start = 0; $start < $pages; $start++) {
         $url = 'http://www.google.' . GOOGLE_TLD . '/custom?q=' . $query . '&filter=0' . '&num=100' . ($start == 0 ? '' : '&start=' . $start . '00');
         $str = SEOstats::cURL($url);
         if (preg_match("#answer=86640#i", $str)) {
             $e = 'Please read: http://www.google.com/support/websearch/' . 'bin/answer.py?&answer=86640&hl=en';
             throw new SEOstatsException($e);
         } else {
             $html = new DOMDocument();
             @$html->loadHtml($str);
             $xpath = new DOMXPath($html);
             $links = $xpath->query("//div[@class='g']//a");
             $descs = $xpath->query("//td[@class='j']//div[@class='std']");
             $i = 0;
             foreach ($links as $link) {
                 if (!preg_match('#cache#si', $link->textContent) && !preg_match('#similar#si', $link->textContent)) {
                     $result[] = array('url' => $link->getAttribute('href'), 'title' => utf8_decode($link->textContent), 'descr' => utf8_decode($descs->item($i)->textContent));
                     $i++;
                 }
             }
             if (preg_match('#<div id="nn"><\\/div>#i', $str) || preg_match('#<div id=nn><\\/div>#i', $str)) {
                 $pages += 1;
                 $delay += 200000;
                 usleep($delay);
             } else {
                 $pages -= 1;
             }
         }
     }
     return $result;
 }

 function testRequestToOutputFile()
 {
     $client = new ProxyClient();
     $client->URL = df_absolute_url('tests/test_ProxyClient/test1.html');
     $outputFile = tempnam(sys_get_temp_dir(), 'test_ProxyClient');
     $client->outputFile = $outputFile;
     $client->process();
     $this->assertEquals(null, $client->content, 'Content should be written to output file, not saved to variable.');
     $expected = file_get_contents('tests/test_ProxyClient/test1.html');
     $doc = new DOMDocument();
     @$doc->loadHtml($expected);
     $expected = $doc->saveHtml();
     $actual = file_get_contents($outputFile);
     $actual = '';
     $fh = fopen($outputFile, 'r');
     while (!feof($fh) and trim($line = fgets($fh, 1024))) {
         // We skip the headers
     }
     ob_start();
     fpassthru($fh);
     fclose($fh);
     $actual = ob_get_contents();
     ob_end_clean();
     unset($doc);
     $doc = new DOMDocument();
     @$doc->loadHtml($actual);
     $actual = $doc->saveHtml();
     unset($doc);
     $this->assertEquals($expected, $actual);
 }

 public function it_should_remove_filtered_file_names()
 {
     $domDoc = new \DOMDocument();
     $domDoc->loadHtml('<html><body><img src="img/spacer.gif" /><img src="img/sprite.png" /><img src="img/cat.jpg" /></body></html>');
     $document = UrlDocument::build($domDoc, 'http://simplegifts.co');
     $analyzer = new StubFileSizeAnalyzer();
     $this->beConstructedThrough('load', [$document, $analyzer]);
     $this->process()->shouldHaveCount(1);
 }

 public function getPageMetrics($url = false)
 {
     $url = false != $url ? $url : self::getUrl();
     $dataUrl = sprintf(services::OPENSITEEXPLORER_URL, 'links', '1', $url);
     $html = HttpRequest::sendRequest($dataUrl);
     $doc = new DOMDocument();
     @$doc->loadHtml($html);
     $data = $doc->getElementsByTagName('td');
     return array('domainAuthority' => trim(strip_tags($data->item(0)->textContent)), 'pageAuthority' => trim(strip_tags($data->item(1)->textContent)), 'linkingRootDomains' => trim(strip_tags($data->item(2)->textContent)), 'totalInboundLinks' => trim(strip_tags($data->item(3)->textContent)));
 }