Last active
January 15, 2016 15:12
-
-
Save tap52384/60cc27fd0a76869cc38b to your computer and use it in GitHub Desktop.
Uses the official w3c validator to validate HTML snippets. The results are returned as a JSON string. Could be refactored, but it works as is.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| /** | |
| * Sends an HTML snippet to the W3C validator and returns the result as JSON. | |
| * @param string $html HTML code | |
| * @return string | |
| * @link https://github.com/validator/validator/wiki/Service:-Input:-POST-body | |
| * @link https://gist.github.com/tap52384/60cc27fd0a76869cc38b#file-php_html_validator-php | |
| */ | |
| public static function validateHtml($html = '') | |
| { | |
| $default = array( | |
| 'messages' => array(), | |
| 'source' => array( | |
| 'type' => 'text/html', | |
| 'encoding' => 'utf-8', | |
| 'code' => '' | |
| ) | |
| ); | |
| $default = json_encode($default); | |
| // replace special characters | |
| $html = str_replace("\r", "", $html); | |
| $html = str_replace("\n", "", $html); | |
| if (!is_string($html) || empty($html) || strlen(trim($html)) === 0) { | |
| return $default; | |
| } | |
| // insert the code within a complete HTML document | |
| $html = '<!DOCTYPE html><html><head><title>Test Document</title></head><body>' | |
| . $html . '</body></html>'; | |
| // set the headers, including the required multipart boundary | |
| $headers = array( | |
| 'Content-Type: multipart/form-data; boundary=---------------------------' . | |
| strlen($html), | |
| 'User-Agent: ' . getenv('HTTP_USER_AGENT') | |
| ); | |
| // url for the validator | |
| $url = 'https://validator.w3.org/nu/?out=json&parser=html5'; | |
| // options for the validator | |
| $content = array( | |
| 'parser' => 'html5', | |
| 'out' => 'json', | |
| 'showsource' => 'yes', | |
| 'asciiquotes' => 'yes', | |
| 'content' => $html | |
| ); | |
| // send the html to the w3c validator via curl and return the result | |
| // initiate cURL (a cURL handle) | |
| $ch = curl_init($url); | |
| curl_setopt($ch, CURLOPT_HEADER, 0); | |
| curl_setopt($ch, CURLOPT_HTTPHEADER, $headers); | |
| curl_setopt($ch, CURLOPT_POST, true); | |
| curl_setopt($ch, CURLOPT_POSTFIELDS, $content); | |
| curl_setopt($ch, CURLOPT_USERAGENT, getenv('HTTP_USER_AGENT')); | |
| curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); | |
| $result = curl_exec($ch); | |
| if (!is_int($ch) && | |
| $ch !== false && | |
| $ch !== null && | |
| !is_bool($ch)) { | |
| curl_close($ch); | |
| } | |
| return $result !== false ? $result : $default; | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment