Code Duplication - DakuTree/manga-tracker - Measure and Improve Code Quality continuously with Scrutinizer

Code Duplication Length = 65-68 lines in 3 locations

application/models/Site_Model.php 3 locations


	}
}

class SeaOtterScans extends Site_Model {
	public function getFullTitleURL(string $title_url) : string {
		return "http://reader.seaotterscans.com/series/{$title_url}";
	}

	public function isValidTitleURL(string $title_url) : bool {
		$success = (bool) preg_match('/^[a-z0-9_]+/', $title_url);
		if(!$success) log_message('error', "Invalid Title URL (SeaOtterScans): {$title_url}");
		return $success;
	}
	public function isValidChapter(string $chapter) : bool {
		$success = (bool) preg_match('/^en\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+)?)?)?$/', $chapter);
		if(!$success) log_message('error', 'Invalid Chapter (SeaOtterScans): '.$chapter);
		return $success;
	}

	public function getChapterData(string $title_url, string $chapter) : array {
		//LANG/VOLUME/CHAPTER/CHAPTER_EXTRA(/page/)
		$chapter_parts = explode('/', $chapter);
		return [
			'url'    => "https://reader.seaotterscans.com/read/{$title_url}/{$chapter}/",
			'number' => ($chapter_parts[1] !== '0' ? "v{$chapter_parts[1]}/" : '') . "c{$chapter_parts[2]}" . (isset($chapter_parts[3]) ? ".{$chapter_parts[3]}" : '')/*)*/
		];
	}

	public function getTitleData(string $title_url) {
		$titleData = [];

		$fullURL = $this->getFullTitleURL($title_url);

		$content = $this->get_content($fullURL);
		$data = $content['body'];
		if(strpos($data, '404 Page Not Found') === FALSE) {
			//FIXME: For whatever reason, we can't grab the entire div without simplexml shouting at us
			$data = preg_replace('/^[\S\s]*(<article[\S\s]*)<\/article>[\S\s]*$/', '$1', $data);

			$dom = new DOMDocument();
			libxml_use_internal_errors(true);
			$dom->loadHTML($data);
			libxml_use_internal_errors(false);

			$xpath = new DOMXPath($dom);

			$nodes_title = $xpath->query("//div[@class='large comic']/h1[@class='title']");

			//SOO sometimes uses volume groups which are above recent chapters (if they haven't been grouped yet), so make sure we check for both.
			$nodes_row   = $xpath->query("//div[@class='list']/div[@class='group']/div[@class='title' and text() = 'Chapters']/following-sibling::div[@class='element'][1]");
			if($nodes_row->length !== 1) {
				$nodes_row   = $xpath->query("//div[@class='list']/div[@class='group'][1]/div[@class='element'][1]");
			}
			if($nodes_title->length === 1 && $nodes_row->length === 1) {
				$titleData['title'] = trim($nodes_title->item(0)->textContent);

				$firstRow = $nodes_row->item(0);
				$nodes_latest  = $xpath->query("div[@class='meta_r']",  $firstRow);
				$nodes_chapter = $xpath->query("div[@class='title']/a", $firstRow);

				$link = (string) $nodes_chapter->item(0)->getAttribute('href');
				$titleData['latest_chapter'] = preg_replace('/.*\/read\/.*?\/(.*?)\/$/', '$1', $link);
				$titleData['last_updated'] =  date("Y-m-d H:i:s", strtotime((string) str_replace('.', '', explode(',', $nodes_latest[0]->textContent)[1])));
			}
		} else {
			//TODO: Throw ERRORS;
		}

		return (!empty($titleData) ? $titleData : NULL);
	}
}

class HelveticaScans extends Site_Model {
	public function getFullTitleURL(string $title_url) : string {

	}
}

class HelveticaScans extends Site_Model {
	public function getFullTitleURL(string $title_url) : string {
		return "http://helveticascans.com/reader/series/{$title_url}";
	}

	public function isValidTitleURL(string $title_url) : bool {
		$success = (bool) preg_match('/^[a-z0-9_]+/', $title_url);
		if(!$success) log_message('error', "Invalid Title URL (HelveticaScans): {$title_url}");
		return $success;
	}
	public function isValidChapter(string $chapter) : bool {
		$success = (bool) preg_match('/^en\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+)?)?)?$/', $chapter);
		if(!$success) log_message('error', 'Invalid Chapter (HelveticaScans): '.$chapter);
		return $success;
	}

	public function getChapterData(string $title_url, string $chapter) : array {
		//LANG/VOLUME/CHAPTER/CHAPTER_EXTRA(/page/)
		$chapter_parts = explode('/', $chapter);
		return [
			'url'    => "http://helveticascans.com/reader/read/{$title_url}/{$chapter}/",
			'number' => ($chapter_parts[1] !== '0' ? "v{$chapter_parts[1]}/" : '') . "c{$chapter_parts[2]}" . (isset($chapter_parts[3]) ? ".{$chapter_parts[3]}" : '')/*)*/
		];
	}

	public function getTitleData(string $title_url) {
		$titleData = [];

		$fullURL = $this->getFullTitleURL($title_url);

		$content = $this->get_content($fullURL);
		$data = $content['body'];
		if(strpos($data, '404 Page Not Found') === FALSE) {
			//FIXME: For whatever reason, we can't grab the entire div without simplexml shouting at us
			$data = preg_replace('/^[\S\s]*(<article[\S\s]*)<\/article>[\S\s]*$/', '$1', $data);

			$dom = new DOMDocument();
			libxml_use_internal_errors(true);
			$dom->loadHTML($data);
			libxml_use_internal_errors(false);

			$xpath = new DOMXPath($dom);

			$nodes_title = $xpath->query("//div[@class='large comic']/h1[@class='title']");
			$nodes_row   = $xpath->query("//div[@class='list']/div[@class='group']/div[@class='title' and text() = 'Chapters']/following-sibling::div[@class='element'][1]");
			if($nodes_row->length !== 1) {
				$nodes_row   = $xpath->query("//div[@class='list']/div[@class='group'][1]/div[@class='element'][1]");
			}
			if($nodes_title->length === 1 && $nodes_row->length === 1) {
				$titleData['title'] = trim($nodes_title->item(0)->textContent);


				$nodes_latest  = $xpath->query("div[@class='meta_r']", $nodes_row[0]);
				$nodes_chapter = $xpath->query("div[@class='title']/a", $nodes_row[0]);

				$link = (string) $nodes_chapter->item(0)->getAttribute('href');
				$titleData['latest_chapter'] = preg_replace('/.*\/read\/.*?\/(.*?)\/$/', '$1', $link);
				$titleData['last_updated'] =  date("Y-m-d H:i:s", strtotime((string) str_replace('.', '', explode(',', $nodes_latest->item(0)->textContent)[1])));
			}
		} else {
			//TODO: Throw ERRORS;
		}

		return (!empty($titleData) ? $titleData : NULL);
	}
}

class SenseScans extends Site_Model {
	public function getFullTitleURL(string $title_url) : string {

	}
}

class SenseScans extends Site_Model {
	public function getFullTitleURL(string $title_url) : string {
		return "http://reader.sensescans.com/series/{$title_url}";
	}

	public function isValidTitleURL(string $title_url) : bool {
		$success = (bool) preg_match('/^[a-z0-9_]+/', $title_url);
		if(!$success) log_message('error', "Invalid Title URL (SenseScans): {$title_url}");
		return $success;
	}
	public function isValidChapter(string $chapter) : bool {
		$success = (bool) preg_match('/^en\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+)?)?)?$/', $chapter);
		if(!$success) log_message('error', 'Invalid Chapter (SenseScans): '.$chapter);
		return $success;
	}

	public function getChapterData(string $title_url, string $chapter) : array {
		//LANG/VOLUME/CHAPTER/CHAPTER_EXTRA(/page/)
		$chapter_parts = explode('/', $chapter);
		return [
			'url'    => "http://reader.sensescans.com/read/{$title_url}/{$chapter}/",
			'number' => ($chapter_parts[1] !== '0' ? "v{$chapter_parts[1]}/" : '') . "c{$chapter_parts[2]}" . (isset($chapter_parts[3]) ? ".{$chapter_parts[3]}" : '')/*)*/
		];
	}

	public function getTitleData(string $title_url) {
		$titleData = [];

		$fullURL = $this->getFullTitleURL($title_url);

		$content = $this->get_content($fullURL);
		$data = $content['body'];
		if(strpos($data, '404 Page Not Found') === FALSE) {
			//FIXME: For whatever reason, we can't grab the entire div without simplexml shouting at us
			$data = preg_replace('/^[\S\s]*(<article[\S\s]*)<\/article>[\S\s]*$/', '$1', $data);

			$dom = new DOMDocument();
			libxml_use_internal_errors(true);
			$dom->loadHTML($data);
			libxml_use_internal_errors(false);

			$xpath = new DOMXPath($dom);

			$nodes_title = $xpath->query("//div[@class='large comic']/h1[@class='title']");
			$nodes_row   = $xpath->query("//div[@class='list']/div[@class='group']/div[@class='title' and text() = 'Chapters']/following-sibling::div[@class='element'][1]");
			if($nodes_row->length !== 1) {
				$nodes_row   = $xpath->query("//div[@class='list']/div[@class='group'][1]/div[@class='element'][1]");
			}
			if($nodes_title->length === 1 && $nodes_row->length === 1) {
				$titleData['title'] = trim($nodes_title->item(0)->textContent);

				$nodes_latest    = $xpath->query("div[@class='meta_r']", $nodes_row[0]);
				$nodes_chapter   = $xpath->query("div[@class='title']/a", $nodes_row[0]);

				$link = (string) $nodes_chapter->item(0)->getAttribute('href');
				$titleData['latest_chapter'] = preg_replace('/.*\/read\/.*?\/(.*?)\/$/', '$1', $link);
				$titleData['last_updated'] =  date("Y-m-d H:i:s", strtotime((string) str_replace('.', '', explode(',', $nodes_latest->item(0)->textContent)[1])));
			}
		} else {
			//TODO: Throw ERRORS;
		}

		return (!empty($titleData) ? $titleData : NULL);
	}
}


		@@ 926-993 (lines=68) @@
923		}
924		}
925
926		class SeaOtterScans extends Site_Model {
927		public function getFullTitleURL(string $title_url) : string {
928		return "http://reader.seaotterscans.com/series/{$title_url}";
929		}
930
931		public function isValidTitleURL(string $title_url) : bool {
932		$success = (bool) preg_match('/^[a-z0-9_]+/', $title_url);
933		if(!$success) log_message('error', "Invalid Title URL (SeaOtterScans): {$title_url}");
934		return $success;
935		}
936		public function isValidChapter(string $chapter) : bool {
937		$success = (bool) preg_match('/^en\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+)?)?)?$/', $chapter);
938		if(!$success) log_message('error', 'Invalid Chapter (SeaOtterScans): '.$chapter);
939		return $success;
940		}
941
942		public function getChapterData(string $title_url, string $chapter) : array {
943		//LANG/VOLUME/CHAPTER/CHAPTER_EXTRA(/page/)
944		$chapter_parts = explode('/', $chapter);
945		return [
946		'url' => "https://reader.seaotterscans.com/read/{$title_url}/{$chapter}/",
947		'number' => ($chapter_parts[1] !== '0' ? "v{$chapter_parts[1]}/" : '') . "c{$chapter_parts[2]}" . (isset($chapter_parts[3]) ? ".{$chapter_parts[3]}" : '')/)/
948		];
949		}
950
951		public function getTitleData(string $title_url) {
952		$titleData = [];
953
954		$fullURL = $this->getFullTitleURL($title_url);
955
956		$content = $this->get_content($fullURL);
957		$data = $content['body'];
958		if(strpos($data, '404 Page Not Found') === FALSE) {
959		//FIXME: For whatever reason, we can't grab the entire div without simplexml shouting at us
960		$data = preg_replace('/^[\S\s](<article[\S\s])<\/article>[\S\s]*$/', '$1', $data);
961
962		$dom = new DOMDocument();
963		libxml_use_internal_errors(true);
964		$dom->loadHTML($data);
965		libxml_use_internal_errors(false);
966
967		$xpath = new DOMXPath($dom);
968
969		$nodes_title = $xpath->query("//div[@class='large comic']/h1[@class='title']");
970
971		//SOO sometimes uses volume groups which are above recent chapters (if they haven't been grouped yet), so make sure we check for both.
972		$nodes_row = $xpath->query("//div[@class='list']/div[@class='group']/div[@class='title' and text() = 'Chapters']/following-sibling::div[@class='element'][1]");
973		if($nodes_row->length !== 1) {
974		$nodes_row = $xpath->query("//div[@class='list']/div[@class='group'][1]/div[@class='element'][1]");
975		}
976		if($nodes_title->length === 1 && $nodes_row->length === 1) {
977		$titleData['title'] = trim($nodes_title->item(0)->textContent);
978
979		$firstRow = $nodes_row->item(0);
980		$nodes_latest = $xpath->query("div[@class='meta_r']", $firstRow);
981		$nodes_chapter = $xpath->query("div[@class='title']/a", $firstRow);
982
983		$link = (string) $nodes_chapter->item(0)->getAttribute('href');
984		$titleData['latest_chapter'] = preg_replace('/.\/read\/.?\/(.*?)\/$/', '$1', $link);
985		$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) str_replace('.', '', explode(',', $nodes_latest[0]->textContent)[1])));
986		}
987		} else {
988		//TODO: Throw ERRORS;
989		}
990
991		return (!empty($titleData) ? $titleData : NULL);
992		}
993		}
994
995		class HelveticaScans extends Site_Model {
996		public function getFullTitleURL(string $title_url) : string {
		@@ 995-1060 (lines=66) @@
992		}
993		}
994
995		class HelveticaScans extends Site_Model {
996		public function getFullTitleURL(string $title_url) : string {
997		return "http://helveticascans.com/reader/series/{$title_url}";
998		}
999
1000		public function isValidTitleURL(string $title_url) : bool {
1001		$success = (bool) preg_match('/^[a-z0-9_]+/', $title_url);
1002		if(!$success) log_message('error', "Invalid Title URL (HelveticaScans): {$title_url}");
1003		return $success;
1004		}
1005		public function isValidChapter(string $chapter) : bool {
1006		$success = (bool) preg_match('/^en\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+)?)?)?$/', $chapter);
1007		if(!$success) log_message('error', 'Invalid Chapter (HelveticaScans): '.$chapter);
1008		return $success;
1009		}
1010
1011		public function getChapterData(string $title_url, string $chapter) : array {
1012		//LANG/VOLUME/CHAPTER/CHAPTER_EXTRA(/page/)
1013		$chapter_parts = explode('/', $chapter);
1014		return [
1015		'url' => "http://helveticascans.com/reader/read/{$title_url}/{$chapter}/",
1016		'number' => ($chapter_parts[1] !== '0' ? "v{$chapter_parts[1]}/" : '') . "c{$chapter_parts[2]}" . (isset($chapter_parts[3]) ? ".{$chapter_parts[3]}" : '')/)/
1017		];
1018		}
1019
1020		public function getTitleData(string $title_url) {
1021		$titleData = [];
1022
1023		$fullURL = $this->getFullTitleURL($title_url);
1024
1025		$content = $this->get_content($fullURL);
1026		$data = $content['body'];
1027		if(strpos($data, '404 Page Not Found') === FALSE) {
1028		//FIXME: For whatever reason, we can't grab the entire div without simplexml shouting at us
1029		$data = preg_replace('/^[\S\s](<article[\S\s])<\/article>[\S\s]*$/', '$1', $data);
1030
1031		$dom = new DOMDocument();
1032		libxml_use_internal_errors(true);
1033		$dom->loadHTML($data);
1034		libxml_use_internal_errors(false);
1035
1036		$xpath = new DOMXPath($dom);
1037
1038		$nodes_title = $xpath->query("//div[@class='large comic']/h1[@class='title']");
1039		$nodes_row = $xpath->query("//div[@class='list']/div[@class='group']/div[@class='title' and text() = 'Chapters']/following-sibling::div[@class='element'][1]");
1040		if($nodes_row->length !== 1) {
1041		$nodes_row = $xpath->query("//div[@class='list']/div[@class='group'][1]/div[@class='element'][1]");
1042		}
1043		if($nodes_title->length === 1 && $nodes_row->length === 1) {
1044		$titleData['title'] = trim($nodes_title->item(0)->textContent);
1045
1046
1047		$nodes_latest = $xpath->query("div[@class='meta_r']", $nodes_row[0]);
1048		$nodes_chapter = $xpath->query("div[@class='title']/a", $nodes_row[0]);
1049
1050		$link = (string) $nodes_chapter->item(0)->getAttribute('href');
1051		$titleData['latest_chapter'] = preg_replace('/.\/read\/.?\/(.*?)\/$/', '$1', $link);
1052		$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) str_replace('.', '', explode(',', $nodes_latest->item(0)->textContent)[1])));
1053		}
1054		} else {
1055		//TODO: Throw ERRORS;
1056		}
1057
1058		return (!empty($titleData) ? $titleData : NULL);
1059		}
1060		}
1061
1062		class SenseScans extends Site_Model {
1063		public function getFullTitleURL(string $title_url) : string {
		@@ 1062-1126 (lines=65) @@
1059		}
1060		}
1061
1062		class SenseScans extends Site_Model {
1063		public function getFullTitleURL(string $title_url) : string {
1064		return "http://reader.sensescans.com/series/{$title_url}";
1065		}
1066
1067		public function isValidTitleURL(string $title_url) : bool {
1068		$success = (bool) preg_match('/^[a-z0-9_]+/', $title_url);
1069		if(!$success) log_message('error', "Invalid Title URL (SenseScans): {$title_url}");
1070		return $success;
1071		}
1072		public function isValidChapter(string $chapter) : bool {
1073		$success = (bool) preg_match('/^en\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+)?)?)?$/', $chapter);
1074		if(!$success) log_message('error', 'Invalid Chapter (SenseScans): '.$chapter);
1075		return $success;
1076		}
1077
1078		public function getChapterData(string $title_url, string $chapter) : array {
1079		//LANG/VOLUME/CHAPTER/CHAPTER_EXTRA(/page/)
1080		$chapter_parts = explode('/', $chapter);
1081		return [
1082		'url' => "http://reader.sensescans.com/read/{$title_url}/{$chapter}/",
1083		'number' => ($chapter_parts[1] !== '0' ? "v{$chapter_parts[1]}/" : '') . "c{$chapter_parts[2]}" . (isset($chapter_parts[3]) ? ".{$chapter_parts[3]}" : '')/)/
1084		];
1085		}
1086
1087		public function getTitleData(string $title_url) {
1088		$titleData = [];
1089
1090		$fullURL = $this->getFullTitleURL($title_url);
1091
1092		$content = $this->get_content($fullURL);
1093		$data = $content['body'];
1094		if(strpos($data, '404 Page Not Found') === FALSE) {
1095		//FIXME: For whatever reason, we can't grab the entire div without simplexml shouting at us
1096		$data = preg_replace('/^[\S\s](<article[\S\s])<\/article>[\S\s]*$/', '$1', $data);
1097
1098		$dom = new DOMDocument();
1099		libxml_use_internal_errors(true);
1100		$dom->loadHTML($data);
1101		libxml_use_internal_errors(false);
1102
1103		$xpath = new DOMXPath($dom);
1104
1105		$nodes_title = $xpath->query("//div[@class='large comic']/h1[@class='title']");
1106		$nodes_row = $xpath->query("//div[@class='list']/div[@class='group']/div[@class='title' and text() = 'Chapters']/following-sibling::div[@class='element'][1]");
1107		if($nodes_row->length !== 1) {
1108		$nodes_row = $xpath->query("//div[@class='list']/div[@class='group'][1]/div[@class='element'][1]");
1109		}
1110		if($nodes_title->length === 1 && $nodes_row->length === 1) {
1111		$titleData['title'] = trim($nodes_title->item(0)->textContent);
1112
1113		$nodes_latest = $xpath->query("div[@class='meta_r']", $nodes_row[0]);
1114		$nodes_chapter = $xpath->query("div[@class='title']/a", $nodes_row[0]);
1115
1116		$link = (string) $nodes_chapter->item(0)->getAttribute('href');
1117		$titleData['latest_chapter'] = preg_replace('/.\/read\/.?\/(.*?)\/$/', '$1', $link);
1118		$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) str_replace('.', '', explode(',', $nodes_latest->item(0)->textContent)[1])));
1119		}
1120		} else {
1121		//TODO: Throw ERRORS;
1122		}
1123
1124		return (!empty($titleData) ? $titleData : NULL);
1125		}
1126		}
1127

DakuTree / manga-tracker

Code Duplication Length = 65-68 lines in 3 locations

application/models/Site_Model.php 3 locations