PHP code example of gm314 / diavazo

1. Go to this page and download the library: Download gm314/diavazo library. Choose the download type require.

2. Extract the ZIP file and open the index.php.

3. Add this code to the index.php.

    
        
<?php
require_once('vendor/autoload.php');

/* Start to develop here. Best regards https://php-download.com/ */

gm314 / diavazo example snippets


use Diavazo\HTMLDocument;
$document = new HTMLDocument();

// load file
$document->loadFile("local.html");
$document->loadFile("http://mypage.com/test.html");

// load from string
$document->loadString("<html></html>");


$document = new HTMLDocument();
$document->loadFile(__DIR__ . "/assets/TableToArrayTest.html");

// get element by id
$table = $document->getElementById("associateArrayTest");

// get element by tag name
$elementList = $document->getElementByTagName("div");

// find all <p> elements, all elements with the class 'spanClass' and all <b class="bClass">  
$elementList = $document->getElement("p .spanClass b.bClass");

// xpath query
$title = $document->query("/html/head/title");

// get root (<html>)
$root = $document->getRootElement();


$document = new HTMLDocument();
$document->loadFile(__DIR__ . "/assets/TableToArrayTest.html");

$table = $document->getElementById("table");

// will return the first tr (Breadth-first search)
$table->getFirstDescendantByName("tr");

// will return all td and th elements
$tdList = $table->getDescendantByName("td th");

// will find all elements that have the class 'active'
$root = $document->getRootElement();
$elementsWithClass = $root->getDescendantWithClassName("active");

// will find all elements that have the class 'myClass' and are td or th elements
$elementsWithClass = $root->getDescendantWithClassName("myClass", "td th");

// will find all elements having only the class 'testClass'
$elementsWithExactClass = $root->getDescendantWithClassNameStrict("testClass");

// will find all elements having only the class 'testClass' and are td or th elements
$elementsWithExactClass = $root->getDescendantWithClassNameStrict("testClass", "td th");

// find all <p> elements, all elements with the class 'spanClass' and all <b class="bClass"> that are descendants of #myId  
$anyElement = $document-getElementById("myId");
$elementList = $document->getElement("p .spanClass b.bClass");


$document = new HTMLDocument();
$document->loadFile("myFile.html");

$table = $document->getElementBy("myTable");

// will return null if the attribute does not exist otherwise string
$table->getAttributeValue("align");


$document = new HTMLDocument();
$document->loadFile("tabletest.html");

$table = $document->getElementById("myTableID");

$arrayConverter = new TableToArrayConverter($table);
$array = $arrayConverter->getAsAssociativeArray();


<table id="myTableID">
    <tr>
        <td>Key1</td>
        <td>Key2</td>
    </tr>
    <tr>
        <td>Value 1</td>
        <td>Value 2</td>
    </tr>
    ...
</table>

will result in:

$array = [
    [
       "Key1" => "Value 1",
       "Key2" => "Value 2"
    ],
    ...
]


$document = $this->getDocument();
$table = $document->getElementById("extractorTest");

$arrayConverter = new TableToArrayConverter($table);
$arrayConverter->registerExtractor("columnName", function (HTMLElement $td) {
    $a = $td->getFirstDescendantByName("a");
    return $a->getAttributeValue("href");
});
$array = $arrayConverter->getAsAssociativeArray();