+global\Base_Site_Model::parseTitleDataDOM()

Complexity

Conditions	20
Paths	16

Size

Total Lines	81
Code Lines	57

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	0
CRAP Score	420

Importance

Changes

0

<?php declare(strict_types=1); defined('BASEPATH') OR exit('No direct script access allowed');
	final protected function parseTitleDataDOM(
		$content, string $title_url,
		string $node_title_string, string $node_row_string,
		string $node_latest_string, string $node_chapter_string,
		string $failure_string = "", closure $noChaptersCall = NULL, closure $extraCall = NULL) {

		if(!is_array($content)) {
			log_message('error', "{$this->site} : {$title_url} | Failed to grab URL (See above curl error)");
		} else {
			list('headers' => $headers, 'status_code' => $status_code, 'body' => $data) = $content;

The assignment to $headers is unused. Consider omitting it like so list($first,,$third).

			if(!($status_code >= 200 && $status_code < 300)) {
				if($status_code === 502) {

This if statement is empty and can be removed.

					// Site is overloaded, no need to log this.
				} else {
					log_message('error', "{$this->site} : {$title_url} | Bad Status Code ({$status_code})");
				}
			} else if(empty($data)) {
				log_message('error', "{$this->site} : {$title_url} | Data is empty? (Status code: {$status_code})");
			} else if($failure_string !== "" && strpos($data, $failure_string) !== FALSE) {
				log_message('error', "{$this->site} : {$title_url} | Failure string matched");
			} else {
				$data = $this->cleanTitleDataDOM($data); //This allows us to clean the DOM prior to parsing. It's faster to grab the only part we need THEN parse it.

				$dom = new DOMDocument();
				libxml_use_internal_errors(TRUE);
				$dom->loadHTML('<?xml encoding="utf-8" ?>' . $data);
				libxml_use_internal_errors(FALSE);

				$xpath = new DOMXPath($dom);
				$nodes_title = $xpath->query($node_title_string);
				$nodes_row   = $xpath->query($node_row_string);
				if($nodes_title->length === 1) {
					if($nodes_row->length === 1) {
						$firstRow      = $nodes_row->item(0);
						$nodes_latest  = $xpath->query($node_latest_string,  $firstRow);

						if($node_chapter_string !== '') {
							$nodes_chapter = $xpath->query($node_chapter_string, $firstRow);
						} else {
							$nodes_chapter = $nodes_row;
						}

						if($nodes_latest->length === 1 && $nodes_chapter->length === 1) {
							$returnData = [
								'nodes_title'   => $nodes_title->item(0),
								'nodes_latest'  => $nodes_latest->item(0),
								'nodes_chapter' => $nodes_chapter->item(0)
							];

							if(is_callable($extraCall)) $extraCall($xpath, $returnData);

							return $returnData;
						} else {
							log_message('error', "{$this->site} : {$title_url} | Invalid amount of nodes (LATEST: {$nodes_latest->length} | CHAPTER: {$nodes_chapter->length})");
						}
					} elseif($this->canHaveNoChapters && !is_null($noChaptersCall) && is_callable($noChaptersCall)) {
						$returnData = [
							'nodes_title'   => $nodes_title->item(0)
						];

						$noChaptersCall($data, $xpath, $returnData);

						if(is_array($returnData)) {
							if(is_callable($extraCall) && is_array($returnData)) $extraCall($xpath, $returnData);
						} else {
							log_message('error', "{$this->site} : {$title_url} | canHaveNoChapters set, but doesn't match possible checks! XPath is probably broken.");
						}

						return $returnData;
					} else {
						log_message('error', "{$this->site} : {$title_url} | Invalid amount of nodes (ROW: {$nodes_row->length})");
					}
				} else {
					log_message('error', "{$this->site} : {$title_url} | Invalid amount of nodes (TITLE: {$nodes_title->length})");
				}
			}
		}

		return FALSE;
	}