PHP DomDocument::getElementsByTagName方法代码示例

 public function recuperePodcast($url_flux, $nom_abonnement)
 {
     if (!empty($url_flux) && !empty($nom_abonnement)) {
         //On recupere le nom de l'abonnement
         $nom_abo = $nom_abonnement;
         //On recupère le flux RSS
         $flux = new DomDocument();
         $flux->load($url_flux);
         $flux->preservedWhiteSpace = false;
         $i = 0;
         $pc = $flux->getElementsByTagName('item')->item($i);
         while (!is_null($pc)) {
             $titre = mysql_real_escape_string($pc->getElementsByTagName('title')->item(0)->nodeValue);
             $date = mysql_real_escape_string($pc->getElementsByTagName('pubDate')->item(0)->nodeValue);
             $desc = mysql_real_escape_string($pc->getElementsByTagName('description')->item(0)->nodeValue);
             $auteur = mysql_real_escape_string($pc->getElementsByTagName('author')->item(0)->nodeValue);
             $categ = mysql_real_escape_string($pc->getElementsByTagName('category')->item(0)->nodeValue);
             $url = mysql_real_escape_string($pc->getElementsByTagName('enclosure')->item(0)->getAttribute('url'));
             //Ajout base
             $sql = "INSERT INTO podcast(titre,auteur,date,description,url,id_genre,comments) VALUES('{$titre}','{$auteur}', '{$date}', '{$desc}', '{$url}', '{$categ}',' rien ')";
             @mysql_query($sql) or die('Erreur requete SQL' . "  " . mysql_error());
             $id_podcast = mysql_insert_id();
             $sql2 = "INSERT INTO abonnement(id_util,id_pod,url,nom_abo) VALUES('1','{$id_podcast}', '{$url_flux}', '{$nom_abo}')";
             @mysql_query($sql2) or die('Erreur requete SQL' . "  " . mysql_error());
             $i = $i + 1;
             $pc = $flux->getElementsByTagName('item')->item($i);
         }
     }
 }

 /**
  * 
  * @param string $html
  */
 public function exec($html)
 {
     mb_language('Japanese');
     // 1.プリプロセス
     // scriptテキスト削除
     // script内に文字列リテラルの閉じタグがあるとDomDocumentがscriptのソースを#text扱いしてしまうので
     // script内の文字を削除する
     // 正規表現で削除しようとするとSegmentation faultが発生する（StackOverFlow?）ので
     // simple_html_domでscript内文字列を削除
     // MAX_FILE_SIZEの制限にひっかかったので、ソースを編集してデフォルトの3倍に変更している
     $simpleHtml = str_get_html($html);
     foreach ($simpleHtml->find('script') as $script) {
         $script->innertext = '';
     }
     $html = $simpleHtml->outertext;
     // トリム
     //		$html = preg_replace('/(\s|　)+/mi', ' ', $html);
     // 2. dom生成
     $doc = new DomDocument("1.0", "utf-8");
     @$doc->loadHTML(mb_convert_encoding($html, 'HTML-ENTITIES', 'UTF-8'));
     $node = $doc->getElementsByTagName('body')->item(0);
     $this->preProcessedInput = $node->textContent;
     // 3.プロパティを初期化
     $this->domXPath = new DomXPath($doc);
     $this->title = @$doc->getElementsByTagName('title')->item(0)->textContent;
     $text = $this->scan($node);
     $this->textAll = $text;
     $this->domCountAll = $this->domCount;
     $this->pancutuationCountAll = $this->calcKutenScore($text) + $this->calcTotenScore($text);
     $this->textLengthAll = mb_strlen($text);
     $this->highScore = -1000000;
     $this->extracedNode = null;
     // 4.実行
     $this->extract($node);
 }

 public function buildModel($model)
 {
     try {
         $dom = new DomDocument();
         $dom->Load($this->loadModel($model));
         $rooms_base = $dom->getElementsByTagName("roomdata");
         foreach ($rooms_base as $rooms_bases) {
             $roomtypes = $rooms_bases->getElementsByTagName("roomtype")->item(0)->nodeValue;
             $caption = $rooms_bases->getElementsByTagName("caption")->item(0)->nodeValue;
             $model_name = $rooms_bases->getElementsByTagName("model_name")->item(0)->nodeValue;
             $description = $rooms_bases->getElementsByTagName("description")->item(0)->nodeValue;
             if ($this->createRooms($roomtypes, $caption, $username, $description, $model_name)) {
                 echo 'Done rooms<br/>';
             }
         }
         foreach ($dom->getElementsByTagName("roomitem") as $room_items) {
             foreach ($room_items->getElementsByTagName("item") as $item) {
                 $base_item = $item->getElementsByTagName("base_item")->item(0)->nodeValue;
                 $x = $item->getElementsByTagName("x")->item(0)->nodeValue;
                 $y = $item->getElementsByTagName("y")->item(0)->nodeValue;
                 $z = $item->getElementsByTagName("z")->item(0)->nodeValue;
                 $rot = $item->getElementsByTagName("rot")->item(0)->nodeValue;
                 $coord = array('x' => $x, 'y' => $y, 'z' => $z);
                 if ($this->addItemsToRooms($user_id, null, $base_item, $coord, $rot)) {
                     echo 'Done ' . $base_item . '<br/>';
                 }
             }
         }
     } catch (Exception $e) {
         echo $e->getMessage();
     }
 }

 /**
  * Break the MODS topic element text-node metadata on 
  * the specified character and put into seperate MODS topic elements.
  *
  * @param string $xmlsnippet The initial MODS topic element.
  *
  * @param string $breakOnCharacter The charcter break the string.
  *     The default character is the semicolon ';'.
  *
  * @return string
  *     An XML string containing one or more MODS topic elements.
  */
 public function breakTopicMetadaOnCharacter($xmlsnippet, $breakOnCharacter = ';')
 {
     // Break topic metadata on ; into seperate topic elements.
     $xml = new \DomDocument();
     $xml->loadxml($xmlsnippet, LIBXML_NSCLEAN);
     $topicNode = $xml->getElementsByTagName('topic')->item(0);
     if (!is_object($topicNode)) {
         $xmlstring = $xmlsnippet;
     } else {
         $topictext = $topicNode->nodeValue;
         $topics = explode($breakOnCharacter, $topictext);
         // remove old topic node.
         $topicNodeParent = $topicNode->parentNode;
         $topicNode->parentNode->removeChild($topicNode);
         $subjectNode = $xml->getElementsByTagName($this->topLevelNodeName)->item(0);
         foreach ($topics as $topic) {
             $topic = trim($topic);
             $newtopicElement = $xml->createElement('topic');
             $topictextNode = $xml->createTextNode($topic);
             $newtopicElement->appendChild($topictextNode);
             $subjectNode->appendChild($newtopicElement);
             unset($topictextNode);
             unset($newtopicElement);
         }
         $xmlstring = $xml->saveXML($subjectNode);
     }
     return $xmlstring;
 }

 /**
  *
  * @param DomDocument $index
  * @param DomDocument $sitemap
  */
 protected function storeSitemap($index, $sitemap)
 {
     // Записываем текущий файл
     $name = sprintf('sitemap_list_%d.xml', $index->getElementsByTagName('sitemap')->length);
     $result = $sitemap->saveXML();
     file_put_contents(FILE_PATH . $name, $result);
     //
     //
     $sitemapEl = $index->createElement('sitemap');
     $loc = $index->createElement('loc', 'http:' . \Extasy\CMS::getWWWRoot() . 'files/' . $name);
     $lastMod = $index->createElement('lastmod', date('Y-m-d'));
     $sitemapEl->appendChild($loc);
     $sitemapEl->appendChild($lastMod);
     $index->getElementsByTagName('sitemapindex')->item('0')->appendChild($sitemapEl);
 }

 public function getPreview($elements)
 {
     if (!isset($this->preview)) {
         if (!isset($elements)) {
             $elements = 2;
         }
         // Get just the text (no markup) from a node using $node->textContent.
         // Compare the textContent value to the one returned by $node->nodeValue.
         libxml_use_internal_errors(true);
         $dom = new DomDocument();
         $dom->preserveWhiteSpace = false;
         $dom->loadHTML('<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8" /></head><body>' . $this->Body . '</body></html>');
         $dom->normalize();
         $nodes = $dom->getElementsByTagName("body")->item(0)->childNodes;
         $elementCount = 0;
         $this->preview = '';
         foreach ($nodes as $node) {
             if ($node->nodeType === XML_ELEMENT_NODE) {
                 $this->preview .= $dom->saveXML($node);
                 $elementCount++;
                 if ($elementCount === $elements) {
                     break;
                 }
             }
         }
         // Carriage returns in the XML prevent the markup from validating. -- cwells
         $this->preview = str_replace('&#13;', '', $this->preview);
     }
     return $this->preview;
 }

 public function testUpdateOnLicenceChange()
 {
     $document = $this->createTestDocument();
     $document->store();
     $documentCacheTable = new Opus_Db_DocumentXmlCache();
     $docXmlCache = $documentCacheTable->find($document->getId(), '1')->current()->xml_data;
     $domDoc = new DomDocument();
     $domDoc->loadXML($docXmlCache);
     $licences = $domDoc->getElementsByTagName('Licence');
     $this->assertTrue($licences->length == 0, 'Expected no Licence element in dom.');
     $licence = new Opus_Licence();
     $licence->setNameLong('TestLicence');
     $licence->setLinkLicence('http://example.org/licence');
     $licenceId = $licence->store();
     $document->setServerState('published');
     $document->setLicence($licence);
     $docId = $document->store();
     $licence = new Opus_Licence($licenceId);
     $licence->setNameLong('TestLicenceAltered');
     $licence->store();
     $docXmlCacheResult = $documentCacheTable->find($document->getId(), '1');
     $this->assertTrue($docXmlCacheResult->count() == 0, 'Expected empty document xml cache');
     $this->executeScript('cron-update-document-cache.php');
     $docXmlCacheAfter = $documentCacheTable->find($docId, '1')->current()->xml_data;
     $domDocAfter = new DomDocument();
     $domDocAfter->loadXML($docXmlCacheAfter);
     $licencesAfter = $domDocAfter->getElementsByTagName('Licence');
     $this->assertTrue($licencesAfter->length == 1, 'Expected one Licence element in dom.');
     $licences = $document->getLicence();
     $licences[0]->delete();
 }

function capi_mkfeedtitle($feed)
{
    global $_SGLOBAL, $_SN, $_SCONFIG;
    $feed['title_data'] = empty($feed['title_data']) ? array() : unserialize($feed['title_data']);
    if (!is_array($feed['title_data'])) {
        $feed['title_data'] = array();
    }
    //title
    $searchs = $replaces = array();
    if ($feed['title_data'] && is_array($feed['title_data'])) {
        foreach (array_keys($feed['title_data']) as $key) {
            if ($key === "touser") {
                $dom = new DomDocument();
                @$dom->loadHTML($feed["title_data"]["touser"]);
                $urls = $dom->getElementsByTagName('a');
                $url = $urls->item(0);
                $value["title_data"]["touser"] = capi_fhtml($value["title_data"]["touser"]);
            }
            $searchs[] = '{' . $key . '}';
            $replaces[] = $feed['title_data'][$key];
        }
    }
    $searchs[] = '{actor}';
    $replaces[] = empty($actors) ? $_SN[$feed['uid']] : implode(lang('dot'), $actors);
    $feed['title_template'] = mktarget(str_replace($searchs, $replaces, $feed['title_template']));
    return $feed;
}

function get_xml_droits()
{
    if (!is_file(PATH_ROOT . 'inc/droits.xml')) {
        return array();
    }
    $dom = new DomDocument("1.0", "UTF-8");
    $dom->load(PATH_ROOT . 'inc/droits.xml');
    $elements = $dom->getElementsByTagName('droits');
    $arbre = $elements->item(0);
    $array_droit = array();
    $sections = $arbre->childNodes;
    foreach ($sections as $section) {
        if ($section->nodeName == "section") {
            $nom_section = $section->attributes->getNamedItem("name")->nodeValue;
            $array_droit[$nom_section] = array();
            $droits = $section->childNodes;
            foreach ($droits as $droit) {
                if ($droit->nodeName == "droit") {
                    $infos_droit = $droit->childNodes;
                    $nom_droit = $droit->getElementsByTagName("name")->item(0)->nodeValue;
                    $type_droit = $droit->getElementsByTagName("type")->item(0)->nodeValue;
                    $array_droit[$nom_section][$nom_droit] = array($type_droit);
                }
            }
        }
    }
    return $array_droit;
}

 public function call_success()
 {
     global $USER, $COURSE, $CFG;
     if (empty($this->_xmlresponse)) {
         if (is_siteadmin($USER->id)) {
             notice(get_string('adminemptyxml', 'adobeconnect'), $CFG->wwwroot . '/admin/settings.php?section=modsettingadobeconnect');
         } else {
             notice(get_string('emptyxml', 'adobeconnect'), '', $COURSE);
         }
     }
     $dom = new DomDocument();
     $dom->loadXML($this->_xmlresponse);
     $domnodelist = $dom->getElementsByTagName('status');
     if ($domnodelist->item(0)->hasAttributes()) {
         $domnode = $domnodelist->item(0)->attributes->getNamedItem('code');
         if (!is_null($domnode)) {
             if (0 == strcmp('ok', $domnode->nodeValue)) {
                 return true;
             } else {
                 return false;
             }
         } else {
             return false;
         }
     } else {
         return false;
     }
 }

 /**
  * General manipulate wrapper method.
  *
  * @param string $input An XML snippet to be manipulated. We are only interested
  *    in <abstract> snippets.
  *
  * @return string
  *     Manipulated string
  */
 public function manipulate($input)
 {
     $dom = new \DomDocument();
     $dom->loadxml($input, LIBXML_NSCLEAN);
     $abstracts = $dom->getElementsByTagName('abstract');
     if ($abstracts->length == 1) {
         $abstract = $abstracts->item(0);
         // Use Guzzle to hit the API.
         $client = new Client();
         try {
             $original_text = urlencode($abstract->nodeValue);
             $query = "?text={$original_text}&format=json";
             $response = $client->get($this->arrpiUrl . $query);
             // If there is a Guzzle error, log it and return the original snippet.
         } catch (Exception $e) {
             $this->log->addWarning("PiratizeAbstract", array('HTTP request error' => $e->getMessage()));
             return $input;
         }
         $body = $response->getBody();
         $translation = json_decode($body, true);
         $abstract->nodeValue = urldecode($translation['translation']['pirate']);
         // Log any instances where the translation differs from the original text.
         if (urldecode($original_text) != $abstract->nodeValue) {
             $this->log->addInfo("PiratizeAbstract", array('Record key' => $this->record_key, 'Source abstract text' => urldecode($original_text), 'Piratized abstract text' => $abstract->nodeValue));
         }
         // We're done, so return the modified snippet.
         return $dom->saveXML($dom->documentElement);
     } else {
         return $input;
     }
 }

 /**
  * return the document as string.
  *
  * @access public
  * @return string
  */
 public function __toString()
 {
     $this->document->formatOutput = true;
     $this->document->preserveWhitespace = false;
     $title = $this->document->createElement('title', $this->getFullTitle());
     $this->head->appendChild($title);
     if (!empty($this->favicon)) {
         $favicon = $this->document->createElement('link');
         $favicon->setAttribute('rel', 'shortcut icon');
         $favicon->setAttribute('href', $this->favicon);
         $this->head->appendChild($favicon);
         $favicon = $this->document->createElement('link');
         $favicon->setAttribute('rel', 'icon');
         $favicon->setAttribute('href', $this->favicon);
         $this->head->appendChild($favicon);
     }
     if (!empty($this->keywords)) {
         $keywords = $this->document->createElement('meta');
         $keywords->setAttribute('name', 'keywords');
         $keywords->setAttribute('content', $this->keywords);
         $this->head->appendChild($keywords);
     }
     $html = $this->document->getElementsByTagName('html')->item(0);
     $html->appendChild($this->head);
     $html->appendChild($this->body);
     return $this->document->saveXML();
 }

 function get_input_tags($html)
 {
     $post_data = array();
     // a new dom object
     $dom = new DomDocument();
     //load the html into the object
     $dom->loadHTML($html);
     //discard white space
     $dom->preserveWhiteSpace = false;
     //all input tags as a list
     $input_tags = $dom->getElementsByTagName('input');
     //get all rows from the table
     for ($i = 0; $i < $input_tags->length; $i++) {
         if (is_object($input_tags->item($i))) {
             $name = $value = '';
             $name_o = $input_tags->item($i)->attributes->getNamedItem('name');
             if (is_object($name_o)) {
                 $name = $name_o->value;
                 $value_o = $input_tags->item($i)->attributes->getNamedItem('value');
                 if (is_object($value_o)) {
                     $value = $input_tags->item($i)->attributes->getNamedItem('value')->value;
                 }
                 $post_data[$name] = $value;
             }
         }
     }
     return $post_data;
 }

function areXmlSame($xmlString1, $xmlString2)
{
    $document1 = new DomDocument();
    $document2 = new DomDocument();
    $document1->loadXML($xmlString1);
    $document2->loadXML($xmlString2);
    $allNodes1 = $document1->getElementsByTagName("*");
    $allNodes2 = $document2->getElementsByTagName("*");
    $length1 = $allNodes1->length;
    $length2 = $allNodes2->length;
    if ($length1 != $length2) {
        return false;
    }
    for ($i = 0; $i < $length1; $i++) {
        $node1 = $allNodes1->item($i);
        $node2 = $allNodes2->item($i);
        if (!compareAttributes($node1, $node2)) {
            return false;
        }
        if ($node1->nodeName != $node2->nodeName) {
            return false;
        }
    }
    return true;
}

 public static function getMetaTags($url)
 {
     $rc = null;
     try {
         $settings[CURLOPT_URL] = $url;
         $contents = self::runCurl($settings);
         if (!empty($contents)) {
             libxml_use_internal_errors(true);
             $doc = new \DomDocument();
             $doc->loadHTML($contents);
             $metas = $doc->getElementsByTagName('meta');
             $rc = array();
             foreach ($metas as $meta) {
                 $name = $meta->getAttribute('name');
                 if (empty($name)) {
                     $name = $meta->getAttribute('property');
                 }
                 $content = $meta->getAttribute('content');
                 if (empty($content)) {
                     $content = $meta->getAttribute('value');
                 }
                 if (!empty($name) && !empty($content)) {
                     $rc[$name] = $content;
                 }
             }
         }
         return $rc;
     } catch (Exception $e) {
         return $rc;
     }
 }