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 $title_url) : string {
		return "https://reader.seaotterscans.com/series/{$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);
	}
}


		@@ 907-974 (lines=68) @@
904		}
905		}
906
907		class SeaOtterScans extends Site_Model {
908		public function getFullTitleURL(string $title_url) : string {
909		return "https://reader.seaotterscans.com/series/{$title_url}";
910		}
911
912		public function isValidTitleURL(string $title_url) : bool {
913		$success = (bool) preg_match('/^[a-z0-9_]+/', $title_url);
914		if(!$success) log_message('error', "Invalid Title URL (SeaOtterScans): {$title_url}");
915		return $success;
916		}
917		public function isValidChapter(string $chapter) : bool {
918		$success = (bool) preg_match('/^en\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+)?)?)?$/', $chapter);
919		if(!$success) log_message('error', 'Invalid Chapter (SeaOtterScans): '.$chapter);
920		return $success;
921		}
922
923		public function getChapterData(string $title_url, string $chapter) : array {
924		//LANG/VOLUME/CHAPTER/CHAPTER_EXTRA(/page/)
925		$chapter_parts = explode('/', $chapter);
926		return [
927		'url' => "https://reader.seaotterscans.com/read/{$title_url}/{$chapter}/",
928		'number' => ($chapter_parts[1] !== '0' ? "v{$chapter_parts[1]}/" : '') . "c{$chapter_parts[2]}" . (isset($chapter_parts[3]) ? ".{$chapter_parts[3]}" : '')/)/
929		];
930		}
931
932		public function getTitleData(string $title_url) {
933		$titleData = [];
934
935		$fullURL = $this->getFullTitleURL($title_url);
936
937		$content = $this->get_content($fullURL);
938		$data = $content['body'];
939		if(strpos($data, '404 Page Not Found') === FALSE) {
940		//FIXME: For whatever reason, we can't grab the entire div without simplexml shouting at us
941		$data = preg_replace('/^[\S\s](<article[\S\s])<\/article>[\S\s]*$/', '$1', $data);
942
943		$dom = new DOMDocument();
944		libxml_use_internal_errors(true);
945		$dom->loadHTML($data);
946		libxml_use_internal_errors(false);
947
948		$xpath = new DOMXPath($dom);
949
950		$nodes_title = $xpath->query("//div[@class='large comic']/h1[@class='title']");
951
952		//SOO sometimes uses volume groups which are above recent chapters (if they haven't been grouped yet), so make sure we check for both.
953		$nodes_row = $xpath->query("//div[@class='list']/div[@class='group']/div[@class='title' and text() = 'Chapters']/following-sibling::div[@class='element'][1]");
954		if($nodes_row->length !== 1) {
955		$nodes_row = $xpath->query("//div[@class='list']/div[@class='group'][1]/div[@class='element'][1]");
956		}
957		if($nodes_title->length === 1 && $nodes_row->length === 1) {
958		$titleData['title'] = trim($nodes_title->item(0)->textContent);
959
960		$firstRow = $nodes_row->item(0);
961		$nodes_latest = $xpath->query("div[@class='meta_r']", $firstRow);
962		$nodes_chapter = $xpath->query("div[@class='title']/a", $firstRow);
963
964		$link = (string) $nodes_chapter->item(0)->getAttribute('href');
965		$titleData['latest_chapter'] = preg_replace('/.\/read\/.?\/(.*?)\/$/', '$1', $link);
966		$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime(((string) str_replace('.', '', explode(',', $nodes_latest[0]->textContent)[1]))));
967		}
968		} else {
969		//TODO: Throw ERRORS;
970		}
971
972		return (!empty($titleData) ? $titleData : NULL);
973		}
974		}
975
976		class HelveticaScans extends Site_Model {
977		public function getFullTitleURL(string $title_url) : string {
		@@ 976-1041 (lines=66) @@
973		}
974		}
975
976		class HelveticaScans extends Site_Model {
977		public function getFullTitleURL(string $title_url) : string {
978		return "http://helveticascans.com/reader/series/{$title_url}";
979		}
980
981		public function isValidTitleURL(string $title_url) : bool {
982		$success = (bool) preg_match('/^[a-z0-9_]+/', $title_url);
983		if(!$success) log_message('error', "Invalid Title URL (HelveticaScans): {$title_url}");
984		return $success;
985		}
986		public function isValidChapter(string $chapter) : bool {
987		$success = (bool) preg_match('/^en\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+)?)?)?$/', $chapter);
988		if(!$success) log_message('error', 'Invalid Chapter (HelveticaScans): '.$chapter);
989		return $success;
990		}
991
992		public function getChapterData(string $title_url, string $chapter) : array {
993		//LANG/VOLUME/CHAPTER/CHAPTER_EXTRA(/page/)
994		$chapter_parts = explode('/', $chapter);
995		return [
996		'url' => "http://helveticascans.com/reader/read/{$title_url}/{$chapter}/",
997		'number' => ($chapter_parts[1] !== '0' ? "v{$chapter_parts[1]}/" : '') . "c{$chapter_parts[2]}" . (isset($chapter_parts[3]) ? ".{$chapter_parts[3]}" : '')/)/
998		];
999		}
1000
1001		public function getTitleData(string $title_url) {
1002		$titleData = [];
1003
1004		$fullURL = $this->getFullTitleURL($title_url);
1005
1006		$content = $this->get_content($fullURL);
1007		$data = $content['body'];
1008		if(strpos($data, '404 Page Not Found') === FALSE) {
1009		//FIXME: For whatever reason, we can't grab the entire div without simplexml shouting at us
1010		$data = preg_replace('/^[\S\s](<article[\S\s])<\/article>[\S\s]*$/', '$1', $data);
1011
1012		$dom = new DOMDocument();
1013		libxml_use_internal_errors(true);
1014		$dom->loadHTML($data);
1015		libxml_use_internal_errors(false);
1016
1017		$xpath = new DOMXPath($dom);
1018
1019		$nodes_title = $xpath->query("//div[@class='large comic']/h1[@class='title']");
1020		$nodes_row = $xpath->query("//div[@class='list']/div[@class='group']/div[@class='title' and text() = 'Chapters']/following-sibling::div[@class='element'][1]");
1021		if($nodes_row->length !== 1) {
1022		$nodes_row = $xpath->query("//div[@class='list']/div[@class='group'][1]/div[@class='element'][1]");
1023		}
1024		if($nodes_title->length === 1 && $nodes_row->length === 1) {
1025		$titleData['title'] = trim($nodes_title->item(0)->textContent);
1026
1027
1028		$nodes_latest = $xpath->query("div[@class='meta_r']", $nodes_row[0]);
1029		$nodes_chapter = $xpath->query("div[@class='title']/a", $nodes_row[0]);
1030
1031		$link = (string) $nodes_chapter->item(0)->getAttribute('href');
1032		$titleData['latest_chapter'] = preg_replace('/.\/read\/.?\/(.*?)\/$/', '$1', $link);
1033		$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) str_replace('.', '', explode(',', $nodes_latest->item(0)->textContent)[1])));
1034		}
1035		} else {
1036		//TODO: Throw ERRORS;
1037		}
1038
1039		return (!empty($titleData) ? $titleData : NULL);
1040		}
1041		}
1042
1043		class SenseScans extends Site_Model {
1044		public function getFullTitleURL(string $title_url) : string {
		@@ 1043-1107 (lines=65) @@
1040		}
1041		}
1042
1043		class SenseScans extends Site_Model {
1044		public function getFullTitleURL(string $title_url) : string {
1045		return "http://reader.sensescans.com/series/{$title_url}";
1046		}
1047
1048		public function isValidTitleURL(string $title_url) : bool {
1049		$success = (bool) preg_match('/^[a-z0-9_]+/', $title_url);
1050		if(!$success) log_message('error', "Invalid Title URL (SenseScans): {$title_url}");
1051		return $success;
1052		}
1053		public function isValidChapter(string $chapter) : bool {
1054		$success = (bool) preg_match('/^en\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+(?:\/[0-9]+)?)?)?$/', $chapter);
1055		if(!$success) log_message('error', 'Invalid Chapter (SenseScans): '.$chapter);
1056		return $success;
1057		}
1058
1059		public function getChapterData(string $title_url, string $chapter) : array {
1060		//LANG/VOLUME/CHAPTER/CHAPTER_EXTRA(/page/)
1061		$chapter_parts = explode('/', $chapter);
1062		return [
1063		'url' => "http://reader.sensescans.com/read/{$title_url}/{$chapter}/",
1064		'number' => ($chapter_parts[1] !== '0' ? "v{$chapter_parts[1]}/" : '') . "c{$chapter_parts[2]}" . (isset($chapter_parts[3]) ? ".{$chapter_parts[3]}" : '')/)/
1065		];
1066		}
1067
1068		public function getTitleData(string $title_url) {
1069		$titleData = [];
1070
1071		$fullURL = $this->getFullTitleURL($title_url);
1072
1073		$content = $this->get_content($fullURL);
1074		$data = $content['body'];
1075		if(strpos($data, '404 Page Not Found') === FALSE) {
1076		//FIXME: For whatever reason, we can't grab the entire div without simplexml shouting at us
1077		$data = preg_replace('/^[\S\s](<article[\S\s])<\/article>[\S\s]*$/', '$1', $data);
1078
1079		$dom = new DOMDocument();
1080		libxml_use_internal_errors(true);
1081		$dom->loadHTML($data);
1082		libxml_use_internal_errors(false);
1083
1084		$xpath = new DOMXPath($dom);
1085
1086		$nodes_title = $xpath->query("//div[@class='large comic']/h1[@class='title']");
1087		$nodes_row = $xpath->query("//div[@class='list']/div[@class='group']/div[@class='title' and text() = 'Chapters']/following-sibling::div[@class='element'][1]");
1088		if($nodes_row->length !== 1) {
1089		$nodes_row = $xpath->query("//div[@class='list']/div[@class='group'][1]/div[@class='element'][1]");
1090		}
1091		if($nodes_title->length === 1 && $nodes_row->length === 1) {
1092		$titleData['title'] = trim($nodes_title->item(0)->textContent);
1093
1094		$nodes_latest = $xpath->query("div[@class='meta_r']", $nodes_row[0]);
1095		$nodes_chapter = $xpath->query("div[@class='title']/a", $nodes_row[0]);
1096
1097		$link = (string) $nodes_chapter->item(0)->getAttribute('href');
1098		$titleData['latest_chapter'] = preg_replace('/.\/read\/.?\/(.*?)\/$/', '$1', $link);
1099		$titleData['last_updated'] = date("Y-m-d H:i:s", strtotime((string) str_replace('.', '', explode(',', $nodes_latest->item(0)->textContent)[1])));
1100		}
1101		} else {
1102		//TODO: Throw ERRORS;
1103		}
1104
1105		return (!empty($titleData) ? $titleData : NULL);
1106		}
1107		}
1108

DakuTree / manga-tracker

Code Duplication Length = 65-68 lines in 3 locations

application/models/Site_Model.php 3 locations