Browse Source

update autoloader to consider namespaces for third party libraries: placed and loaded from vendor/namespace/classpath.php
update readability to a newer implementation based on Readability.js (https://github.com/andreskrey/readability.php)
add vendor/Psr/Log interface required for the above

Andrew Dolgov 2 years ago
parent
commit
2aaefbfa54
30 changed files with 3492 additions and 17 deletions
  1. 13 4
      include/autoload.php
  2. 21 13
      plugins/af_readability/init.php
  3. 128 0
      vendor/Psr/Log/AbstractLogger.php
  4. 7 0
      vendor/Psr/Log/InvalidArgumentException.php
  5. 18 0
      vendor/Psr/Log/LogLevel.php
  6. 18 0
      vendor/Psr/Log/LoggerAwareInterface.php
  7. 26 0
      vendor/Psr/Log/LoggerAwareTrait.php
  8. 123 0
      vendor/Psr/Log/LoggerInterface.php
  9. 140 0
      vendor/Psr/Log/LoggerTrait.php
  10. 28 0
      vendor/Psr/Log/NullLogger.php
  11. 140 0
      vendor/Psr/Log/Test/LoggerInterfaceTest.php
  12. 348 0
      vendor/andreskrey/Readability/Configuration.php
  13. 10 0
      vendor/andreskrey/Readability/Nodes/DOM/DOMAttr.php
  14. 10 0
      vendor/andreskrey/Readability/Nodes/DOM/DOMCdataSection.php
  15. 10 0
      vendor/andreskrey/Readability/Nodes/DOM/DOMCharacterData.php
  16. 10 0
      vendor/andreskrey/Readability/Nodes/DOM/DOMComment.php
  17. 30 0
      vendor/andreskrey/Readability/Nodes/DOM/DOMDocument.php
  18. 10 0
      vendor/andreskrey/Readability/Nodes/DOM/DOMDocumentFragment.php
  19. 10 0
      vendor/andreskrey/Readability/Nodes/DOM/DOMDocumentType.php
  20. 10 0
      vendor/andreskrey/Readability/Nodes/DOM/DOMElement.php
  21. 10 0
      vendor/andreskrey/Readability/Nodes/DOM/DOMEntity.php
  22. 10 0
      vendor/andreskrey/Readability/Nodes/DOM/DOMEntityReference.php
  23. 13 0
      vendor/andreskrey/Readability/Nodes/DOM/DOMNode.php
  24. 10 0
      vendor/andreskrey/Readability/Nodes/DOM/DOMNotation.php
  25. 10 0
      vendor/andreskrey/Readability/Nodes/DOM/DOMProcessingInstruction.php
  26. 10 0
      vendor/andreskrey/Readability/Nodes/DOM/DOMText.php
  27. 434 0
      vendor/andreskrey/Readability/Nodes/NodeTrait.php
  28. 159 0
      vendor/andreskrey/Readability/Nodes/NodeUtility.php
  29. 7 0
      vendor/andreskrey/Readability/ParseException.php
  30. 1719 0
      vendor/andreskrey/Readability/Readability.php

+ 13 - 4
include/autoload.php

@@ -2,12 +2,21 @@
 	require_once "functions.php";
 
 	spl_autoload_register(function($class) {
-		$class_file = str_replace("_", "/", strtolower(basename($class)));
+		list ($namespace, $class_name) = explode('\\', $class, 2);
 
-		$file = dirname(__FILE__)."/../classes/$class_file.php";
+		$root_dir = dirname(__DIR__); // we're in tt-rss/include
 
-		if (file_exists($file)) {
-			require $file;
+		// 1. third party libraries with namespaces are loaded from vendor/
+		// 2. internal tt-rss classes are loaded from classes/ and use special naming logic instead of namespaces
+		// 3. plugin classes are loaded by PluginHandler from plugins.local/ and plugins/ (TODO: use generic autoloader?)
+
+		if ($namespace && $class_name) {
+			$class_file = "$root_dir/vendor/$namespace/" . str_replace('\\', '/', $class_name) . ".php";
+		} else {
+			$class_file = "$root_dir/classes/" . str_replace("_", "/", strtolower($class)) . ".php";
 		}
 
+		if (file_exists($class_file))
+			include $class_file;
+
 	});

+ 21 - 13
plugins/af_readability/init.php

@@ -1,4 +1,7 @@
 <?php
+use andreskrey\Readability\Readability;
+use andreskrey\Readability\Configuration;
+
 class Af_Readability extends Plugin {
 
 	/* @var PluginHost $host */
@@ -162,30 +165,35 @@ class Af_Readability extends Plugin {
 				$tmp = $tmpdoc->saveHTML();
 			}
 
-			$r = new Readability($tmp, $fetch_effective_url);
+			$r = new Readability(new Configuration());
 
-			if ($r->init()) {
-				$tmpxpath = new DOMXPath($r->dom);
+			try {
+				if ($r->parse($tmp)) {
 
-				$entries = $tmpxpath->query('(//a[@href]|//img[@src])');
+					$tmpxpath = new DOMXPath($r->getDOMDOcument());
+					$entries = $tmpxpath->query('(//a[@href]|//img[@src])');
 
-				foreach ($entries as $entry) {
-					if ($entry->hasAttribute("href")) {
-						$entry->setAttribute("href",
-								rewrite_relative_url($fetch_effective_url, $entry->getAttribute("href")));
+					foreach ($entries as $entry) {
+						if ($entry->hasAttribute("href")) {
+							$entry->setAttribute("href",
+									rewrite_relative_url($fetch_effective_url, $entry->getAttribute("href")));
 
-					}
+						}
 
-					if ($entry->hasAttribute("src")) {
-						$entry->setAttribute("src",
-								rewrite_relative_url($fetch_effective_url, $entry->getAttribute("src")));
+						if ($entry->hasAttribute("src")) {
+							$entry->setAttribute("src",
+									rewrite_relative_url($fetch_effective_url, $entry->getAttribute("src")));
 
+						}
 					}
 
+					return $r->getContent();
 				}
 
-				return $r->articleContent->innerHTML;
+			} catch (ParseException $e) {
+				return false;
 			}
+
 		}
 
 		return false;

+ 128 - 0
vendor/Psr/Log/AbstractLogger.php

@@ -0,0 +1,128 @@
+<?php
+
+namespace Psr\Log;
+
+/**
+ * This is a simple Logger implementation that other Loggers can inherit from.
+ *
+ * It simply delegates all log-level-specific methods to the `log` method to
+ * reduce boilerplate code that a simple Logger that does the same thing with
+ * messages regardless of the error level has to implement.
+ */
+abstract class AbstractLogger implements LoggerInterface
+{
+    /**
+     * System is unusable.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function emergency($message, array $context = array())
+    {
+        $this->log(LogLevel::EMERGENCY, $message, $context);
+    }
+
+    /**
+     * Action must be taken immediately.
+     *
+     * Example: Entire website down, database unavailable, etc. This should
+     * trigger the SMS alerts and wake you up.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function alert($message, array $context = array())
+    {
+        $this->log(LogLevel::ALERT, $message, $context);
+    }
+
+    /**
+     * Critical conditions.
+     *
+     * Example: Application component unavailable, unexpected exception.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function critical($message, array $context = array())
+    {
+        $this->log(LogLevel::CRITICAL, $message, $context);
+    }
+
+    /**
+     * Runtime errors that do not require immediate action but should typically
+     * be logged and monitored.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function error($message, array $context = array())
+    {
+        $this->log(LogLevel::ERROR, $message, $context);
+    }
+
+    /**
+     * Exceptional occurrences that are not errors.
+     *
+     * Example: Use of deprecated APIs, poor use of an API, undesirable things
+     * that are not necessarily wrong.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function warning($message, array $context = array())
+    {
+        $this->log(LogLevel::WARNING, $message, $context);
+    }
+
+    /**
+     * Normal but significant events.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function notice($message, array $context = array())
+    {
+        $this->log(LogLevel::NOTICE, $message, $context);
+    }
+
+    /**
+     * Interesting events.
+     *
+     * Example: User logs in, SQL logs.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function info($message, array $context = array())
+    {
+        $this->log(LogLevel::INFO, $message, $context);
+    }
+
+    /**
+     * Detailed debug information.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function debug($message, array $context = array())
+    {
+        $this->log(LogLevel::DEBUG, $message, $context);
+    }
+}

+ 7 - 0
vendor/Psr/Log/InvalidArgumentException.php

@@ -0,0 +1,7 @@
+<?php
+
+namespace Psr\Log;
+
+class InvalidArgumentException extends \InvalidArgumentException
+{
+}

+ 18 - 0
vendor/Psr/Log/LogLevel.php

@@ -0,0 +1,18 @@
+<?php
+
+namespace Psr\Log;
+
+/**
+ * Describes log levels.
+ */
+class LogLevel
+{
+    const EMERGENCY = 'emergency';
+    const ALERT     = 'alert';
+    const CRITICAL  = 'critical';
+    const ERROR     = 'error';
+    const WARNING   = 'warning';
+    const NOTICE    = 'notice';
+    const INFO      = 'info';
+    const DEBUG     = 'debug';
+}

+ 18 - 0
vendor/Psr/Log/LoggerAwareInterface.php

@@ -0,0 +1,18 @@
+<?php
+
+namespace Psr\Log;
+
+/**
+ * Describes a logger-aware instance.
+ */
+interface LoggerAwareInterface
+{
+    /**
+     * Sets a logger instance on the object.
+     *
+     * @param LoggerInterface $logger
+     *
+     * @return void
+     */
+    public function setLogger(LoggerInterface $logger);
+}

+ 26 - 0
vendor/Psr/Log/LoggerAwareTrait.php

@@ -0,0 +1,26 @@
+<?php
+
+namespace Psr\Log;
+
+/**
+ * Basic Implementation of LoggerAwareInterface.
+ */
+trait LoggerAwareTrait
+{
+    /**
+     * The logger instance.
+     *
+     * @var LoggerInterface
+     */
+    protected $logger;
+
+    /**
+     * Sets a logger.
+     *
+     * @param LoggerInterface $logger
+     */
+    public function setLogger(LoggerInterface $logger)
+    {
+        $this->logger = $logger;
+    }
+}

+ 123 - 0
vendor/Psr/Log/LoggerInterface.php

@@ -0,0 +1,123 @@
+<?php
+
+namespace Psr\Log;
+
+/**
+ * Describes a logger instance.
+ *
+ * The message MUST be a string or object implementing __toString().
+ *
+ * The message MAY contain placeholders in the form: {foo} where foo
+ * will be replaced by the context data in key "foo".
+ *
+ * The context array can contain arbitrary data. The only assumption that
+ * can be made by implementors is that if an Exception instance is given
+ * to produce a stack trace, it MUST be in a key named "exception".
+ *
+ * See https://github.com/php-fig/fig-standards/blob/master/accepted/PSR-3-logger-interface.md
+ * for the full interface specification.
+ */
+interface LoggerInterface
+{
+    /**
+     * System is unusable.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function emergency($message, array $context = array());
+
+    /**
+     * Action must be taken immediately.
+     *
+     * Example: Entire website down, database unavailable, etc. This should
+     * trigger the SMS alerts and wake you up.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function alert($message, array $context = array());
+
+    /**
+     * Critical conditions.
+     *
+     * Example: Application component unavailable, unexpected exception.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function critical($message, array $context = array());
+
+    /**
+     * Runtime errors that do not require immediate action but should typically
+     * be logged and monitored.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function error($message, array $context = array());
+
+    /**
+     * Exceptional occurrences that are not errors.
+     *
+     * Example: Use of deprecated APIs, poor use of an API, undesirable things
+     * that are not necessarily wrong.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function warning($message, array $context = array());
+
+    /**
+     * Normal but significant events.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function notice($message, array $context = array());
+
+    /**
+     * Interesting events.
+     *
+     * Example: User logs in, SQL logs.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function info($message, array $context = array());
+
+    /**
+     * Detailed debug information.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function debug($message, array $context = array());
+
+    /**
+     * Logs with an arbitrary level.
+     *
+     * @param mixed  $level
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function log($level, $message, array $context = array());
+}

+ 140 - 0
vendor/Psr/Log/LoggerTrait.php

@@ -0,0 +1,140 @@
+<?php
+
+namespace Psr\Log;
+
+/**
+ * This is a simple Logger trait that classes unable to extend AbstractLogger
+ * (because they extend another class, etc) can include.
+ *
+ * It simply delegates all log-level-specific methods to the `log` method to
+ * reduce boilerplate code that a simple Logger that does the same thing with
+ * messages regardless of the error level has to implement.
+ */
+trait LoggerTrait
+{
+    /**
+     * System is unusable.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function emergency($message, array $context = array())
+    {
+        $this->log(LogLevel::EMERGENCY, $message, $context);
+    }
+
+    /**
+     * Action must be taken immediately.
+     *
+     * Example: Entire website down, database unavailable, etc. This should
+     * trigger the SMS alerts and wake you up.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function alert($message, array $context = array())
+    {
+        $this->log(LogLevel::ALERT, $message, $context);
+    }
+
+    /**
+     * Critical conditions.
+     *
+     * Example: Application component unavailable, unexpected exception.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function critical($message, array $context = array())
+    {
+        $this->log(LogLevel::CRITICAL, $message, $context);
+    }
+
+    /**
+     * Runtime errors that do not require immediate action but should typically
+     * be logged and monitored.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function error($message, array $context = array())
+    {
+        $this->log(LogLevel::ERROR, $message, $context);
+    }
+
+    /**
+     * Exceptional occurrences that are not errors.
+     *
+     * Example: Use of deprecated APIs, poor use of an API, undesirable things
+     * that are not necessarily wrong.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function warning($message, array $context = array())
+    {
+        $this->log(LogLevel::WARNING, $message, $context);
+    }
+
+    /**
+     * Normal but significant events.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function notice($message, array $context = array())
+    {
+        $this->log(LogLevel::NOTICE, $message, $context);
+    }
+
+    /**
+     * Interesting events.
+     *
+     * Example: User logs in, SQL logs.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function info($message, array $context = array())
+    {
+        $this->log(LogLevel::INFO, $message, $context);
+    }
+
+    /**
+     * Detailed debug information.
+     *
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function debug($message, array $context = array())
+    {
+        $this->log(LogLevel::DEBUG, $message, $context);
+    }
+
+    /**
+     * Logs with an arbitrary level.
+     *
+     * @param mixed  $level
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    abstract public function log($level, $message, array $context = array());
+}

+ 28 - 0
vendor/Psr/Log/NullLogger.php

@@ -0,0 +1,28 @@
+<?php
+
+namespace Psr\Log;
+
+/**
+ * This Logger can be used to avoid conditional log calls.
+ *
+ * Logging should always be optional, and if no logger is provided to your
+ * library creating a NullLogger instance to have something to throw logs at
+ * is a good way to avoid littering your code with `if ($this->logger) { }`
+ * blocks.
+ */
+class NullLogger extends AbstractLogger
+{
+    /**
+     * Logs with an arbitrary level.
+     *
+     * @param mixed  $level
+     * @param string $message
+     * @param array  $context
+     *
+     * @return void
+     */
+    public function log($level, $message, array $context = array())
+    {
+        // noop
+    }
+}

+ 140 - 0
vendor/Psr/Log/Test/LoggerInterfaceTest.php

@@ -0,0 +1,140 @@
+<?php
+
+namespace Psr\Log\Test;
+
+use Psr\Log\LoggerInterface;
+use Psr\Log\LogLevel;
+
+/**
+ * Provides a base test class for ensuring compliance with the LoggerInterface.
+ *
+ * Implementors can extend the class and implement abstract methods to run this
+ * as part of their test suite.
+ */
+abstract class LoggerInterfaceTest extends \PHPUnit_Framework_TestCase
+{
+    /**
+     * @return LoggerInterface
+     */
+    abstract public function getLogger();
+
+    /**
+     * This must return the log messages in order.
+     *
+     * The simple formatting of the messages is: "<LOG LEVEL> <MESSAGE>".
+     *
+     * Example ->error('Foo') would yield "error Foo".
+     *
+     * @return string[]
+     */
+    abstract public function getLogs();
+
+    public function testImplements()
+    {
+        $this->assertInstanceOf('Psr\Log\LoggerInterface', $this->getLogger());
+    }
+
+    /**
+     * @dataProvider provideLevelsAndMessages
+     */
+    public function testLogsAtAllLevels($level, $message)
+    {
+        $logger = $this->getLogger();
+        $logger->{$level}($message, array('user' => 'Bob'));
+        $logger->log($level, $message, array('user' => 'Bob'));
+
+        $expected = array(
+            $level.' message of level '.$level.' with context: Bob',
+            $level.' message of level '.$level.' with context: Bob',
+        );
+        $this->assertEquals($expected, $this->getLogs());
+    }
+
+    public function provideLevelsAndMessages()
+    {
+        return array(
+            LogLevel::EMERGENCY => array(LogLevel::EMERGENCY, 'message of level emergency with context: {user}'),
+            LogLevel::ALERT => array(LogLevel::ALERT, 'message of level alert with context: {user}'),
+            LogLevel::CRITICAL => array(LogLevel::CRITICAL, 'message of level critical with context: {user}'),
+            LogLevel::ERROR => array(LogLevel::ERROR, 'message of level error with context: {user}'),
+            LogLevel::WARNING => array(LogLevel::WARNING, 'message of level warning with context: {user}'),
+            LogLevel::NOTICE => array(LogLevel::NOTICE, 'message of level notice with context: {user}'),
+            LogLevel::INFO => array(LogLevel::INFO, 'message of level info with context: {user}'),
+            LogLevel::DEBUG => array(LogLevel::DEBUG, 'message of level debug with context: {user}'),
+        );
+    }
+
+    /**
+     * @expectedException \Psr\Log\InvalidArgumentException
+     */
+    public function testThrowsOnInvalidLevel()
+    {
+        $logger = $this->getLogger();
+        $logger->log('invalid level', 'Foo');
+    }
+
+    public function testContextReplacement()
+    {
+        $logger = $this->getLogger();
+        $logger->info('{Message {nothing} {user} {foo.bar} a}', array('user' => 'Bob', 'foo.bar' => 'Bar'));
+
+        $expected = array('info {Message {nothing} Bob Bar a}');
+        $this->assertEquals($expected, $this->getLogs());
+    }
+
+    public function testObjectCastToString()
+    {
+        if (method_exists($this, 'createPartialMock')) {
+            $dummy = $this->createPartialMock('Psr\Log\Test\DummyTest', array('__toString'));
+        } else {
+            $dummy = $this->getMock('Psr\Log\Test\DummyTest', array('__toString'));
+        }
+        $dummy->expects($this->once())
+            ->method('__toString')
+            ->will($this->returnValue('DUMMY'));
+
+        $this->getLogger()->warning($dummy);
+
+        $expected = array('warning DUMMY');
+        $this->assertEquals($expected, $this->getLogs());
+    }
+
+    public function testContextCanContainAnything()
+    {
+        $context = array(
+            'bool' => true,
+            'null' => null,
+            'string' => 'Foo',
+            'int' => 0,
+            'float' => 0.5,
+            'nested' => array('with object' => new DummyTest),
+            'object' => new \DateTime,
+            'resource' => fopen('php://memory', 'r'),
+        );
+
+        $this->getLogger()->warning('Crazy context data', $context);
+
+        $expected = array('warning Crazy context data');
+        $this->assertEquals($expected, $this->getLogs());
+    }
+
+    public function testContextExceptionKeyCanBeExceptionOrOtherValues()
+    {
+        $logger = $this->getLogger();
+        $logger->warning('Random message', array('exception' => 'oops'));
+        $logger->critical('Uncaught Exception!', array('exception' => new \LogicException('Fail')));
+
+        $expected = array(
+            'warning Random message',
+            'critical Uncaught Exception!'
+        );
+        $this->assertEquals($expected, $this->getLogs());
+    }
+}
+
+class DummyTest
+{
+    public function __toString()
+    {
+    }
+}

+ 348 - 0
vendor/andreskrey/Readability/Configuration.php

@@ -0,0 +1,348 @@
+<?php
+
+namespace andreskrey\Readability;
+
+use Psr\Log\LoggerAwareTrait;
+use Psr\Log\LoggerInterface;
+use Psr\Log\NullLogger;
+
+/**
+ * Class Configuration.
+ */
+class Configuration
+{
+    use LoggerAwareTrait;
+
+    /**
+     * @var int
+     */
+    protected $maxTopCandidates = 5;
+
+    /**
+     * @var int
+     */
+    protected $wordThreshold = 500;
+
+    /**
+     * @var bool
+     */
+    protected $articleByLine = false;
+
+    /**
+     * @var bool
+     */
+    protected $stripUnlikelyCandidates = true;
+
+    /**
+     * @var bool
+     */
+    protected $cleanConditionally = true;
+
+    /**
+     * @var bool
+     */
+    protected $weightClasses = true;
+
+    /**
+     * @var bool
+     */
+    protected $fixRelativeURLs = false;
+
+    /**
+     * @var bool
+     */
+    protected $substituteEntities = false;
+
+    /**
+     * @var bool
+     */
+    protected $normalizeEntities = false;
+
+    /**
+     * @var bool
+     */
+    protected $summonCthulhu = false;
+
+    /**
+     * @var string
+     */
+    protected $originalURL = 'http://fakehost';
+
+    /**
+     * Configuration constructor.
+     *
+     * @param array $params
+     */
+    public function __construct(array $params = [])
+    {
+        foreach ($params as $key => $value) {
+            $setter = sprintf('set%s', $key);
+            if (method_exists($this, $setter)) {
+                call_user_func([$this, $setter], $value);
+            }
+        }
+    }
+
+    /**
+     * Returns an array-representation of configuration.
+     *
+     * @return array
+     */
+    public function toArray()
+    {
+        $out = [];
+        foreach ($this as $key => $value) {
+            $getter = sprintf('get%s', $key);
+            if (!is_object($value) && method_exists($this, $getter)) {
+                $out[$key] = call_user_func([$this, $getter]);
+            }
+        }
+
+        return $out;
+    }
+
+    /**
+     * @return LoggerInterface
+     */
+    public function getLogger()
+    {
+        // If no logger has been set, just return a null logger
+        if ($this->logger === null) {
+            return new NullLogger();
+        } else {
+            return $this->logger;
+        }
+    }
+
+    /**
+     * @param LoggerInterface $logger
+     *
+     * @return Configuration
+     */
+    public function setLogger(LoggerInterface $logger)
+    {
+        $this->logger = $logger;
+
+        return $this;
+    }
+
+    /**
+     * @return int
+     */
+    public function getMaxTopCandidates()
+    {
+        return $this->maxTopCandidates;
+    }
+
+    /**
+     * @param int $maxTopCandidates
+     *
+     * @return $this
+     */
+    public function setMaxTopCandidates($maxTopCandidates)
+    {
+        $this->maxTopCandidates = $maxTopCandidates;
+
+        return $this;
+    }
+
+    /**
+     * @return int
+     */
+    public function getWordThreshold()
+    {
+        return $this->wordThreshold;
+    }
+
+    /**
+     * @param int $wordThreshold
+     *
+     * @return $this
+     */
+    public function setWordThreshold($wordThreshold)
+    {
+        $this->wordThreshold = $wordThreshold;
+
+        return $this;
+    }
+
+    /**
+     * @return bool
+     */
+    public function getArticleByLine()
+    {
+        return $this->articleByLine;
+    }
+
+    /**
+     * @param bool $articleByLine
+     *
+     * @return $this
+     */
+    public function setArticleByLine($articleByLine)
+    {
+        $this->articleByLine = $articleByLine;
+
+        return $this;
+    }
+
+    /**
+     * @return bool
+     */
+    public function getStripUnlikelyCandidates()
+    {
+        return $this->stripUnlikelyCandidates;
+    }
+
+    /**
+     * @param bool $stripUnlikelyCandidates
+     *
+     * @return $this
+     */
+    public function setStripUnlikelyCandidates($stripUnlikelyCandidates)
+    {
+        $this->stripUnlikelyCandidates = $stripUnlikelyCandidates;
+
+        return $this;
+    }
+
+    /**
+     * @return bool
+     */
+    public function getCleanConditionally()
+    {
+        return $this->cleanConditionally;
+    }
+
+    /**
+     * @param bool $cleanConditionally
+     *
+     * @return $this
+     */
+    public function setCleanConditionally($cleanConditionally)
+    {
+        $this->cleanConditionally = $cleanConditionally;
+
+        return $this;
+    }
+
+    /**
+     * @return bool
+     */
+    public function getWeightClasses()
+    {
+        return $this->weightClasses;
+    }
+
+    /**
+     * @param bool $weightClasses
+     *
+     * @return $this
+     */
+    public function setWeightClasses($weightClasses)
+    {
+        $this->weightClasses = $weightClasses;
+
+        return $this;
+    }
+
+    /**
+     * @return bool
+     */
+    public function getFixRelativeURLs()
+    {
+        return $this->fixRelativeURLs;
+    }
+
+    /**
+     * @param bool $fixRelativeURLs
+     *
+     * @return $this
+     */
+    public function setFixRelativeURLs($fixRelativeURLs)
+    {
+        $this->fixRelativeURLs = $fixRelativeURLs;
+
+        return $this;
+    }
+
+    /**
+     * @return bool
+     */
+    public function getSubstituteEntities()
+    {
+        return $this->substituteEntities;
+    }
+
+    /**
+     * @param bool $substituteEntities
+     *
+     * @return $this
+     */
+    public function setSubstituteEntities($substituteEntities)
+    {
+        $this->substituteEntities = $substituteEntities;
+
+        return $this;
+    }
+
+    /**
+     * @return bool
+     */
+    public function getNormalizeEntities()
+    {
+        return $this->normalizeEntities;
+    }
+
+    /**
+     * @param bool $normalizeEntities
+     *
+     * @return $this
+     */
+    public function setNormalizeEntities($normalizeEntities)
+    {
+        $this->normalizeEntities = $normalizeEntities;
+
+        return $this;
+    }
+
+    /**
+     * @return string
+     */
+    public function getOriginalURL()
+    {
+        return $this->originalURL;
+    }
+
+    /**
+     * @param string $originalURL
+     *
+     * @return $this
+     */
+    public function setOriginalURL($originalURL)
+    {
+        $this->originalURL = $originalURL;
+
+        return $this;
+    }
+
+    /**
+     * @return bool
+     */
+    public function getSummonCthulhu()
+    {
+        return $this->summonCthulhu;
+    }
+
+    /**
+     * @param bool $summonCthulhu
+     *
+     * @return $this
+     */
+    public function setSummonCthulhu($summonCthulhu)
+    {
+        $this->summonCthulhu = $summonCthulhu;
+
+        return $this;
+    }
+}

+ 10 - 0
vendor/andreskrey/Readability/Nodes/DOM/DOMAttr.php

@@ -0,0 +1,10 @@
+<?php
+
+namespace andreskrey\Readability\Nodes\DOM;
+
+use andreskrey\Readability\Nodes\NodeTrait;
+
+class DOMAttr extends \DOMAttr
+{
+    use NodeTrait;
+}

+ 10 - 0
vendor/andreskrey/Readability/Nodes/DOM/DOMCdataSection.php

@@ -0,0 +1,10 @@
+<?php
+
+namespace andreskrey\Readability\Nodes\DOM;
+
+use andreskrey\Readability\Nodes\NodeTrait;
+
+class DOMCdataSection extends \DOMCdataSection
+{
+    use NodeTrait;
+}

+ 10 - 0
vendor/andreskrey/Readability/Nodes/DOM/DOMCharacterData.php

@@ -0,0 +1,10 @@
+<?php
+
+namespace andreskrey\Readability\Nodes\DOM;
+
+use andreskrey\Readability\Nodes\NodeTrait;
+
+class DOMCharacterData extends \DOMCharacterData
+{
+    use NodeTrait;
+}

+ 10 - 0
vendor/andreskrey/Readability/Nodes/DOM/DOMComment.php

@@ -0,0 +1,10 @@
+<?php
+
+namespace andreskrey\Readability\Nodes\DOM;
+
+use andreskrey\Readability\Nodes\NodeTrait;
+
+class DOMComment extends \DOMComment
+{
+    use NodeTrait;
+}

+ 30 - 0
vendor/andreskrey/Readability/Nodes/DOM/DOMDocument.php

@@ -0,0 +1,30 @@
+<?php
+
+namespace andreskrey\Readability\Nodes\DOM;
+
+use andreskrey\Readability\Nodes\NodeTrait;
+
+class DOMDocument extends \DOMDocument
+{
+    use NodeTrait;
+
+    public function __construct($version, $encoding)
+    {
+        parent::__construct($version, $encoding);
+
+        $this->registerNodeClass('DOMAttr', DOMAttr::class);
+        $this->registerNodeClass('DOMCdataSection', DOMCdataSection::class);
+        $this->registerNodeClass('DOMCharacterData', DOMCharacterData::class);
+        $this->registerNodeClass('DOMComment', DOMComment::class);
+        $this->registerNodeClass('DOMDocument', self::class);
+        $this->registerNodeClass('DOMDocumentFragment', DOMDocumentFragment::class);
+        $this->registerNodeClass('DOMDocumentType', DOMDocumentType::class);
+        $this->registerNodeClass('DOMElement', DOMElement::class);
+        $this->registerNodeClass('DOMEntity', DOMEntity::class);
+        $this->registerNodeClass('DOMEntityReference', DOMEntityReference::class);
+        $this->registerNodeClass('DOMNode', DOMNode::class);
+        $this->registerNodeClass('DOMNotation', DOMNotation::class);
+        $this->registerNodeClass('DOMProcessingInstruction', DOMProcessingInstruction::class);
+        $this->registerNodeClass('DOMText', DOMText::class);
+    }
+}

+ 10 - 0
vendor/andreskrey/Readability/Nodes/DOM/DOMDocumentFragment.php

@@ -0,0 +1,10 @@
+<?php
+
+namespace andreskrey\Readability\Nodes\DOM;
+
+use andreskrey\Readability\Nodes\NodeTrait;
+
+class DOMDocumentFragment extends \DOMDocumentFragment
+{
+    use NodeTrait;
+}

+ 10 - 0
vendor/andreskrey/Readability/Nodes/DOM/DOMDocumentType.php

@@ -0,0 +1,10 @@
+<?php
+
+namespace andreskrey\Readability\Nodes\DOM;
+
+use andreskrey\Readability\Nodes\NodeTrait;
+
+class DOMDocumentType extends \DOMDocumentType
+{
+    use NodeTrait;
+}

+ 10 - 0
vendor/andreskrey/Readability/Nodes/DOM/DOMElement.php

@@ -0,0 +1,10 @@
+<?php
+
+namespace andreskrey\Readability\Nodes\DOM;
+
+use andreskrey\Readability\Nodes\NodeTrait;
+
+class DOMElement extends \DOMElement
+{
+    use NodeTrait;
+}

+ 10 - 0
vendor/andreskrey/Readability/Nodes/DOM/DOMEntity.php

@@ -0,0 +1,10 @@
+<?php
+
+namespace andreskrey\Readability\Nodes\DOM;
+
+use andreskrey\Readability\Nodes\NodeTrait;
+
+class DOMEntity extends \DOMEntity
+{
+    use NodeTrait;
+}

+ 10 - 0
vendor/andreskrey/Readability/Nodes/DOM/DOMEntityReference.php

@@ -0,0 +1,10 @@
+<?php
+
+namespace andreskrey\Readability\Nodes\DOM;
+
+use andreskrey\Readability\Nodes\NodeTrait;
+
+class DOMEntityReference extends \DOMEntityReference
+{
+    use NodeTrait;
+}

+ 13 - 0
vendor/andreskrey/Readability/Nodes/DOM/DOMNode.php

@@ -0,0 +1,13 @@
+<?php
+
+namespace andreskrey\Readability\Nodes\DOM;
+
+use andreskrey\Readability\Nodes\NodeTrait;
+
+/**
+ * @method getAttribute($attribute)
+ */
+class DOMNode extends \DOMNode
+{
+    use NodeTrait;
+}

+ 10 - 0
vendor/andreskrey/Readability/Nodes/DOM/DOMNotation.php

@@ -0,0 +1,10 @@
+<?php
+
+namespace andreskrey\Readability\Nodes\DOM;
+
+use andreskrey\Readability\Nodes\NodeTrait;
+
+class DOMNotation extends \DOMNotation
+{
+    use NodeTrait;
+}

+ 10 - 0
vendor/andreskrey/Readability/Nodes/DOM/DOMProcessingInstruction.php

@@ -0,0 +1,10 @@
+<?php
+
+namespace andreskrey\Readability\Nodes\DOM;
+
+use andreskrey\Readability\Nodes\NodeTrait;
+
+class DOMProcessingInstruction extends \DOMProcessingInstruction
+{
+    use NodeTrait;
+}

+ 10 - 0
vendor/andreskrey/Readability/Nodes/DOM/DOMText.php

@@ -0,0 +1,10 @@
+<?php
+
+namespace andreskrey\Readability\Nodes\DOM;
+
+use andreskrey\Readability\Nodes\NodeTrait;
+
+class DOMText extends \DOMText
+{
+    use NodeTrait;
+}

+ 434 - 0
vendor/andreskrey/Readability/Nodes/NodeTrait.php

@@ -0,0 +1,434 @@
+<?php
+
+namespace andreskrey\Readability\Nodes;
+
+use andreskrey\Readability\Nodes\DOM\DOMDocument;
+use andreskrey\Readability\Nodes\DOM\DOMElement;
+use andreskrey\Readability\Nodes\DOM\DOMNode;
+use andreskrey\Readability\Nodes\DOM\DOMText;
+
+/**
+ * @method \DOMNode removeAttribute($name)
+ */
+trait NodeTrait
+{
+    /**
+     * Content score of the node. Used to determine the value of the content.
+     *
+     * @var int
+     */
+    public $contentScore = 0;
+
+    /**
+     * Flag for initialized status.
+     *
+     * @var bool
+     */
+    private $initialized = false;
+
+    /**
+     * Flag data tables.
+     *
+     * @var bool
+     */
+    private $readabilityDataTable = false;
+
+    /**
+     * @var array
+     */
+    private $divToPElements = [
+        'a',
+        'blockquote',
+        'dl',
+        'div',
+        'img',
+        'ol',
+        'p',
+        'pre',
+        'table',
+        'ul',
+        'select',
+    ];
+
+    /**
+     * initialized getter.
+     *
+     * @return bool
+     */
+    public function isInitialized()
+    {
+        return $this->initialized;
+    }
+
+    /**
+     * @return bool
+     */
+    public function isReadabilityDataTable()
+    {
+        return $this->readabilityDataTable;
+    }
+
+    /**
+     * @param bool $param
+     */
+    public function setReadabilityDataTable($param)
+    {
+        $this->readabilityDataTable = $param;
+    }
+
+    /**
+     * Initializer. Calculates the current score of the node and returns a full Readability object.
+     *
+     * @ TODO: I don't like the weightClasses param. How can we get the config here?
+     *
+     * @param $weightClasses bool Weight classes?
+     *
+     * @return static
+     */
+    public function initializeNode($weightClasses)
+    {
+        if (!$this->isInitialized()) {
+            $contentScore = 0;
+
+            switch ($this->nodeName) {
+                case 'div':
+                    $contentScore += 5;
+                    break;
+
+                case 'pre':
+                case 'td':
+                case 'blockquote':
+                    $contentScore += 3;
+                    break;
+
+                case 'address':
+                case 'ol':
+                case 'ul':
+                case 'dl':
+                case 'dd':
+                case 'dt':
+                case 'li':
+                case 'form':
+                    $contentScore -= 3;
+                    break;
+
+                case 'h1':
+                case 'h2':
+                case 'h3':
+                case 'h4':
+                case 'h5':
+                case 'h6':
+                case 'th':
+                    $contentScore -= 5;
+                    break;
+            }
+
+            $this->contentScore = $contentScore + ($weightClasses ? $this->getClassWeight() : 0);
+
+            $this->initialized = true;
+        }
+
+        return $this;
+    }
+
+    /**
+     * Override for native getAttribute method. Some nodes have the getAttribute method, some don't, so we need
+     * to check first the existence of the attributes property.
+     *
+     * @param $attributeName string Attribute to retrieve
+     *
+     * @return string
+     */
+    public function getAttribute($attributeName)
+    {
+        if (!is_null($this->attributes)) {
+            return parent::getAttribute($attributeName);
+        }
+
+        return '';
+    }
+
+    /**
+     * Get the ancestors of the current node.
+     *
+     * @param int|bool $maxLevel Max amount of ancestors to get. False for all of them
+     *
+     * @return array
+     */
+    public function getNodeAncestors($maxLevel = 3)
+    {
+        $ancestors = [];
+        $level = 0;
+
+        $node = $this->parentNode;
+
+        while ($node && !($node instanceof DOMDocument)) {
+            $ancestors[] = $node;
+            $level++;
+            if ($level === $maxLevel) {
+                break;
+            }
+            $node = $node->parentNode;
+        }
+
+        return $ancestors;
+    }
+
+    /**
+     * Returns all links from the current element.
+     *
+     * @return array
+     */
+    public function getAllLinks()
+    {
+        return iterator_to_array($this->getElementsByTagName('a'));
+    }
+
+    /**
+     * Get the density of links as a percentage of the content
+     * This is the amount of text that is inside a link divided by the total text in the node.
+     *
+     * @return int
+     */
+    public function getLinkDensity()
+    {
+        $linkLength = 0;
+        $textLength = mb_strlen($this->getTextContent(true));
+
+        if (!$textLength) {
+            return 0;
+        }
+
+        $links = $this->getAllLinks();
+
+        if ($links) {
+            /** @var DOMElement $link */
+            foreach ($links as $link) {
+                $linkLength += mb_strlen($link->getTextContent(true));
+            }
+        }
+
+        return $linkLength / $textLength;
+    }
+
+    /**
+     * Calculates the weight of the class/id of the current element.
+     *
+     * @return int
+     */
+    public function getClassWeight()
+    {
+        $weight = 0;
+
+        // Look for a special classname
+        $class = $this->getAttribute('class');
+        if (trim($class)) {
+            if (preg_match(NodeUtility::$regexps['negative'], $class)) {
+                $weight -= 25;
+            }
+
+            if (preg_match(NodeUtility::$regexps['positive'], $class)) {
+                $weight += 25;
+            }
+        }
+
+        // Look for a special ID
+        $id = $this->getAttribute('id');
+        if (trim($id)) {
+            if (preg_match(NodeUtility::$regexps['negative'], $id)) {
+                $weight -= 25;
+            }
+
+            if (preg_match(NodeUtility::$regexps['positive'], $id)) {
+                $weight += 25;
+            }
+        }
+
+        return $weight;
+    }
+
+    /**
+     * Returns the full text of the node.
+     *
+     * @param bool $normalize Normalize white space?
+     *
+     * @return string
+     */
+    public function getTextContent($normalize = false)
+    {
+        $nodeValue = $this->nodeValue;
+        if ($normalize) {
+            $nodeValue = trim(preg_replace('/\s{2,}/', ' ', $nodeValue));
+        }
+
+        return $nodeValue;
+    }
+
+    /**
+     * Returns the children of the current node.
+     *
+     * @param bool $filterEmptyDOMText Filter empty DOMText nodes?
+     *
+     * @return array
+     */
+    public function getChildren($filterEmptyDOMText = false)
+    {
+        $ret = iterator_to_array($this->childNodes);
+        if ($filterEmptyDOMText) {
+            // Array values is used to discard the key order. Needs to be 0 to whatever without skipping any number
+            $ret = array_values(array_filter($ret, function ($node) {
+                return $node->nodeName !== '#text' || mb_strlen(trim($node->nodeValue));
+            }));
+        }
+
+        return $ret;
+    }
+
+    /**
+     * Return an array indicating how many rows and columns this table has.
+     *
+     * @return array
+     */
+    public function getRowAndColumnCount()
+    {
+        $rows = $columns = 0;
+        $trs = $this->getElementsByTagName('tr');
+        foreach ($trs as $tr) {
+            /** @var \DOMElement $tr */
+            $rowspan = $tr->getAttribute('rowspan');
+            $rows += ($rowspan || 1);
+
+            // Now look for column-related info
+            $columnsInThisRow = 0;
+            $cells = $tr->getElementsByTagName('td');
+            foreach ($cells as $cell) {
+                /** @var \DOMElement $cell */
+                $colspan = $cell->getAttribute('colspan');
+                $columnsInThisRow += ($colspan || 1);
+            }
+            $columns = max($columns, $columnsInThisRow);
+        }
+
+        return ['rows' => $rows, 'columns' => $columns];
+    }
+
+    /**
+     * Creates a new node based on the text content of the original node.
+     *
+     * @param $originalNode DOMNode
+     * @param $tagName string
+     *
+     * @return DOMElement
+     */
+    public function createNode($originalNode, $tagName)
+    {
+        $text = $originalNode->getTextContent();
+        $newNode = $originalNode->ownerDocument->createElement($tagName, $text);
+
+        return $newNode;
+    }
+
+    /**
+     * Check if a given node has one of its ancestor tag name matching the
+     * provided one.
+     *
+     * @param DOMElement $node
+     * @param string $tagName
+     * @param int $maxDepth
+     *
+     * @return bool
+     */
+    public function hasAncestorTag($node, $tagName, $maxDepth = 3)
+    {
+        $depth = 0;
+        while ($node->parentNode) {
+            if ($maxDepth > 0 && $depth > $maxDepth) {
+                return false;
+            }
+            if ($node->parentNode->nodeName === $tagName) {
+                return true;
+            }
+            $node = $node->parentNode;
+            $depth++;
+        }
+
+        return false;
+    }
+
+    /**
+     * Checks if the current node has a single child and if that child is a P node.
+     * Useful to convert <div><p> nodes to a single <p> node and avoid confusing the scoring system since div with p
+     * tags are, in practice, paragraphs.
+     *
+     * @param DOMNode $node
+     *
+     * @return bool
+     */
+    public function hasSinglePNode()
+    {
+        // There should be exactly 1 element child which is a P:
+        if (count($children = $this->getChildren(true)) !== 1 || $children[0]->nodeName !== 'p') {
+            return false;
+        }
+
+        // And there should be no text nodes with real content (param true on ->getChildren)
+        foreach ($children as $child) {
+            /** @var $child DOMNode */
+            if ($child->nodeType === XML_TEXT_NODE && !preg_match('/\S$/', $child->getTextContent())) {
+                return false;
+            }
+        }
+
+        return true;
+    }
+
+    /**
+     * Check if the current element has a single child block element.
+     * Block elements are the ones defined in the divToPElements array.
+     *
+     * @return bool
+     */
+    public function hasSingleChildBlockElement()
+    {
+        $result = false;
+        if ($this->hasChildNodes()) {
+            foreach ($this->getChildren() as $child) {
+                if (in_array($child->nodeName, $this->divToPElements)) {
+                    $result = true;
+                } else {
+                    // If any of the hasSingleChildBlockElement calls return true, return true then.
+                    /** @var $child DOMElement */
+                    $result = ($result || $child->hasSingleChildBlockElement());
+                }
+            }
+        }
+
+        return $result;
+    }
+
+    /**
+     * Determines if a node has no content or it is just a bunch of dividing lines and/or whitespace.
+     *
+     * @return bool
+     */
+    public function isElementWithoutContent()
+    {
+        return $this instanceof DOMElement &&
+            mb_strlen(preg_replace(NodeUtility::$regexps['onlyWhitespace'], '', $this->textContent)) === 0 &&
+            ($this->childNodes->length === 0 ||
+                $this->childNodes->length === $this->getElementsByTagName('br')->length + $this->getElementsByTagName('hr')->length
+                /*
+                 * Special PHP DOMDocument case: We also need to count how many DOMText we have inside the node.
+                 * If there's an empty tag with an space inside and a BR (for example "<p> <br/></p>) counting only BRs and
+                 * HRs will will say that the example has 2 nodes, instead of one. This happens because in DOMDocument,
+                 * DOMTexts are also nodes (which doesn't happen in JS). So we need to also count how many DOMText we
+                 * are dealing with (And at this point we know they are empty or are just whitespace, because of the
+                 * mb_strlen in this chain of checks).
+                 */
+                + count(array_filter(iterator_to_array($this->childNodes), function ($child) {
+                    return $child instanceof DOMText;
+                }))
+
+            );
+    }
+}

+ 159 - 0
vendor/andreskrey/Readability/Nodes/NodeUtility.php

@@ -0,0 +1,159 @@
+<?php
+
+namespace andreskrey\Readability\Nodes;
+
+use andreskrey\Readability\Nodes\DOM\DOMDocument;
+use andreskrey\Readability\Nodes\DOM\DOMElement;
+use andreskrey\Readability\Nodes\DOM\DOMNode;
+
+/**
+ * Class NodeUtility.
+ */
+class NodeUtility
+{
+    /**
+     * Collection of regexps to check the node usability.
+     *
+     * @var array
+     */
+    public static $regexps = [
+        'unlikelyCandidates' => '/banner|breadcrumbs|combx|comment|community|cover-wrap|disqus|extra|foot|header|legends|menu|related|remark|replies|rss|shoutbox|sidebar|skyscraper|social|sponsor|supplemental|ad-break|agegate|pagination|pager|popup|yom-remote/i',
+        'okMaybeItsACandidate' => '/and|article|body|column|main|shadow/i',
+        'extraneous' => '/print|archive|comment|discuss|e[\-]?mail|share|reply|all|login|sign|single|utility/i',
+        'byline' => '/byline|author|dateline|writtenby|p-author/i',
+        'replaceFonts' => '/<(\/?)font[^>]*>/gi',
+        'normalize' => '/\s{2,}/',
+        'videos' => '/\/\/(www\.)?(dailymotion|youtube|youtube-nocookie|player\.vimeo)\.com/i',
+        'nextLink' => '/(next|weiter|continue|>([^\|]|$)|»([^\|]|$))/i',
+        'prevLink' => '/(prev|earl|old|new|<|«)/i',
+        'whitespace' => '/^\s*$/',
+        'hasContent' => '/\S$/',
+        'positive' => '/article|body|content|entry|hentry|h-entry|main|page|pagination|post|text|blog|story/i',
+        'negative' => '/hidden|^hid$| hid$| hid |^hid |banner|combx|comment|com-|contact|foot|footer|footnote|masthead|media|meta|outbrain|promo|related|scroll|share|shoutbox|sidebar|skyscraper|sponsor|shopping|tags|tool|widget/i',
+        // \x{00A0} is the unicode version of &nbsp;
+        'onlyWhitespace' => '/\x{00A0}|\s+/u'
+    ];
+
+    /**
+     * Imported from the Element class on league\html-to-markdown.
+     *
+     * @param $node
+     *
+     * @return DOMElement
+     */
+    public static function nextElement($node)
+    {
+        $next = $node;
+        while ($next
+            && $next->nodeName !== '#text'
+            && trim($next->textContent)) {
+            $next = $next->nextSibling;
+        }
+
+        return $next;
+    }
+
+    /**
+     * Changes the node tag name. Since tagName on DOMElement is a read only value, this must be done creating a new
+     * element with the new tag name and importing it to the main DOMDocument.
+     *
+     * @param string $value
+     * @param bool $importAttributes
+     *
+     * @return DOMNode
+     */
+    public static function setNodeTag($node, $value, $importAttributes = false)
+    {
+        $new = new DOMDocument('1.0', 'utf-8');
+        $new->appendChild($new->createElement($value));
+
+        $children = $node->childNodes;
+        /** @var $children \DOMNodeList $i */
+        for ($i = 0; $i < $children->length; $i++) {
+            $import = $new->importNode($children->item($i), true);
+            $new->firstChild->appendChild($import);
+        }
+
+        if ($importAttributes) {
+            // Import attributes from the original node.
+            foreach ($node->attributes as $attribute) {
+                $new->firstChild->setAttribute($attribute->nodeName, $attribute->nodeValue);
+            }
+        }
+
+        // The import must be done on the firstChild of $new, since $new is a DOMDocument and not a DOMElement.
+        $import = $node->ownerDocument->importNode($new->firstChild, true);
+        $node->parentNode->replaceChild($import, $node);
+
+        return $import;
+    }
+
+    /**
+     * Removes the current node and returns the next node to be parsed (child, sibling or parent).
+     *
+     * @param DOMNode $node
+     *
+     * @return DOMNode
+     */
+    public static function removeAndGetNext($node)
+    {
+        $nextNode = self::getNextNode($node, true);
+        $node->parentNode->removeChild($node);
+
+        return $nextNode;
+    }
+
+    /**
+     * Remove the selected node.
+     *
+     * @param $node DOMElement
+     *
+     * @return void
+     **/
+    public static function removeNode($node)
+    {
+        $parent = $node->parentNode;
+        if ($parent) {
+            $parent->removeChild($node);
+        }
+    }
+
+    /**
+     * Returns the next node. First checks for children (if the flag allows it), then for siblings, and finally
+     * for parents.
+     *
+     * @param DOMNode $originalNode
+     * @param bool $ignoreSelfAndKids
+     *
+     * @return DOMNode
+     */
+    public static function getNextNode($originalNode, $ignoreSelfAndKids = false)
+    {
+        /*
+         * Traverse the DOM from node to node, starting at the node passed in.
+         * Pass true for the second parameter to indicate this node itself
+         * (and its kids) are going away, and we want the next node over.
+         *
+         * Calling this in a loop will traverse the DOM depth-first.
+         */
+
+        // First check for kids if those aren't being ignored
+        if (!$ignoreSelfAndKids && $originalNode->firstChild) {
+            return $originalNode->firstChild;
+        }
+
+        // Then for siblings...
+        if ($originalNode->nextSibling) {
+            return $originalNode->nextSibling;
+        }
+
+        // And finally, move up the parent chain *and* find a sibling
+        // (because this is depth-first traversal, we will have already
+        // seen the parent nodes themselves).
+        do {
+            $originalNode = $originalNode->parentNode;
+        } while ($originalNode && !$originalNode->nextSibling);
+
+        return ($originalNode) ? $originalNode->nextSibling : $originalNode;
+    }
+}

+ 7 - 0
vendor/andreskrey/Readability/ParseException.php

@@ -0,0 +1,7 @@
+<?php
+
+namespace andreskrey\Readability;
+
+class ParseException extends \Exception
+{
+}

+ 1719 - 0
vendor/andreskrey/Readability/Readability.php

@@ -0,0 +1,1719 @@
+<?php
+
+namespace andreskrey\Readability;
+
+use andreskrey\Readability\Nodes\DOM\DOMDocument;
+use andreskrey\Readability\Nodes\DOM\DOMElement;
+use andreskrey\Readability\Nodes\DOM\DOMNode;
+use andreskrey\Readability\Nodes\DOM\DOMText;
+use andreskrey\Readability\Nodes\NodeUtility;
+use Psr\Log\LoggerInterface;
+
+/**
+ * Class Readability.
+ */
+class Readability
+{
+    /**
+     * Main DOMDocument where all the magic happens.
+     *
+     * @var DOMDocument
+     */
+    protected $dom;
+
+    /**
+     * Title of the article.
+     *
+     * @var string|null
+     */
+    protected $title = null;
+
+    /**
+     * Final DOMDocument with the fully parsed HTML.
+     *
+     * @var DOMDocument|null
+     */
+    protected $content = null;
+
+    /**
+     * Excerpt of the article.
+     *
+     * @var string|null
+     */
+    protected $excerpt = null;
+
+    /**
+     * Main image of the article.
+     *
+     * @var string|null
+     */
+    protected $image = null;
+
+    /**
+     * Author of the article. Extracted from the byline tags and other social media properties.
+     *
+     * @var string|null
+     */
+    protected $author = null;
+
+    /**
+     * Direction of the text.
+     *
+     * @var string|null
+     */
+    protected $direction = null;
+
+    /**
+     * Configuration object.
+     *
+     * @var Configuration
+     */
+    private $configuration;
+
+    /**
+     * Logger object.
+     *
+     * @var LoggerInterface
+     */
+    private $logger;
+
+    /**
+     * Collection of attempted text extractions.
+     *
+     * @var array
+     */
+    private $attempts = [];
+
+    /**
+     * @var array
+     */
+    private $defaultTagsToScore = [
+        'section',
+        'h2',
+        'h3',
+        'h4',
+        'h5',
+        'h6',
+        'p',
+        'td',
+        'pre',
+    ];
+
+    /**
+     * @var array
+     */
+    private $alterToDIVExceptions = [
+        'div',
+        'article',
+        'section',
+        'p',
+    ];
+
+    /**
+     * Readability constructor.
+     *
+     * @param Configuration $configuration
+     */
+    public function __construct(Configuration $configuration)
+    {
+        $this->configuration = $configuration;
+        $this->logger = $this->configuration->getLogger();
+    }
+
+    /**
+     * Main parse function.
+     *
+     * @param $html
+     *
+     * @throws ParseException
+     *
+     * @return array|bool
+     */
+    public function parse($html)
+    {
+        $this->logger->info('*** Starting parse process...');
+
+        $this->dom = $this->loadHTML($html);
+
+        // Checking for minimum HTML to work with.
+        if (!($root = $this->dom->getElementsByTagName('body')->item(0)) || !$root->firstChild) {
+            $this->logger->emergency('No body tag present or body tag empty');
+
+            throw new ParseException('Invalid or incomplete HTML.');
+        }
+
+        $this->getMetadata();
+
+        $this->getMainImage();
+
+        while (true) {
+            $root = $root->firstChild;
+
+            $elementsToScore = $this->getNodes($root);
+            $this->logger->debug(sprintf('Elements to score: \'%s\'', count($elementsToScore)));
+
+            $result = $this->rateNodes($elementsToScore);
+
+            /*
+             * Now that we've gone through the full algorithm, check to see if
+             * we got any meaningful content. If we didn't, we may need to re-run
+             * grabArticle with different flags set. This gives us a higher likelihood of
+             * finding the content, and the sieve approach gives us a higher likelihood of
+             * finding the -right- content.
+             */
+
+            $length = mb_strlen(preg_replace(NodeUtility::$regexps['onlyWhitespace'], '', $result->textContent));
+
+            $this->logger->info(sprintf('[Parsing] Article parsed. Amount of words: %s. Current threshold is: %s', $length, $this->configuration->getWordThreshold()));
+
+            $parseSuccessful = true;
+
+            if ($result && $length < $this->configuration->getWordThreshold()) {
+                $this->dom = $this->loadHTML($html);
+                $root = $this->dom->getElementsByTagName('body')->item(0);
+                $parseSuccessful = false;
+
+                if ($this->configuration->getStripUnlikelyCandidates()) {
+                    $this->logger->debug('[Parsing] Threshold not met, trying again setting StripUnlikelyCandidates as false');
+                    $this->configuration->setStripUnlikelyCandidates(false);
+                    $this->attempts[] = ['articleContent' => $result, 'textLength' => $length];
+                } elseif ($this->configuration->getWeightClasses()) {
+                    $this->logger->debug('[Parsing] Threshold not met, trying again setting WeightClasses as false');
+                    $this->configuration->setWeightClasses(false);
+                    $this->attempts[] = ['articleContent' => $result, 'textLength' => $length];
+                } elseif ($this->configuration->getCleanConditionally()) {
+                    $this->logger->debug('[Parsing] Threshold not met, trying again setting CleanConditionally as false');
+                    $this->configuration->setCleanConditionally(false);
+                    $this->attempts[] = ['articleContent' => $result, 'textLength' => $length];
+                } else {
+                    $this->logger->debug('[Parsing] Threshold not met, searching across attempts for some content.');
+                    $this->attempts[] = ['articleContent' => $result, 'textLength' => $length];
+
+                    // No luck after removing flags, just return the longest text we found during the different loops
+                    usort($this->attempts, function ($a, $b) {
+                        return $a['textLength'] < $b['textLength'];
+                    });
+
+                    // But first check if we actually have something
+                    if (!$this->attempts[0]['textLength']) {
+                        $this->logger->emergency('[Parsing] Could not parse text, giving up :(');
+
+                        throw new ParseException('Could not parse text.');
+                    }
+
+                    $this->logger->debug('[Parsing] Threshold not met, but found some content in previous attempts.');
+
+                    $result = $this->attempts[0]['articleContent'];
+                    $parseSuccessful = true;
+                    break;
+                }
+            } else {
+                break;
+            }
+        }
+
+        if ($parseSuccessful) {
+            $result = $this->postProcessContent($result);
+
+            // If we haven't found an excerpt in the article's metadata, use the article's
+            // first paragraph as the excerpt. This can be used for displaying a preview of
+            // the article's content.
+            if (!$this->getExcerpt()) {
+                $this->logger->debug('[Parsing] No excerpt text found on metadata, extracting first p node and using it as excerpt.');
+                $paragraphs = $result->getElementsByTagName('p');
+                if ($paragraphs->length > 0) {
+                    $this->setExcerpt(trim($paragraphs->item(0)->textContent));
+                }
+            }
+
+            $this->setContent($result);
+
+            $this->logger->info('*** Parse successful :)');
+
+            return true;
+        }
+    }
+
+    /**
+     * Creates a DOM Document object and loads the provided HTML on it.
+     *
+     * Used for the first load of Readability and subsequent reloads (when disabling flags and rescanning the text)
+     * Previous versions of Readability used this method one time and cloned the DOM to keep a backup. This caused bugs
+     * because cloning the DOM object keeps a relation between the clone and the original one, doing changes in both
+     * objects and ruining the backup.
+     *
+     * @param string $html
+     *
+     * @return DOMDocument
+     */
+    private function loadHTML($html)
+    {
+        $this->logger->debug('[Loading] Loading HTML...');
+
+        // To avoid throwing a gazillion of errors on malformed HTMLs
+        libxml_use_internal_errors(true);
+
+        $dom = new DOMDocument('1.0', 'utf-8');
+
+        if (!$this->configuration->getSubstituteEntities()) {
+            // Keep the original HTML entities
+            $dom->substituteEntities = false;
+        }
+
+        if ($this->configuration->getNormalizeEntities()) {
+            $this->logger->debug('[Loading] Normalized entities via mb_convert_encoding.');
+            // Replace UTF-8 characters with the HTML Entity equivalent. Useful to fix html with mixed content
+            $html = mb_convert_encoding($html, 'HTML-ENTITIES', 'UTF-8');
+        }
+
+        if ($this->configuration->getSummonCthulhu()) {
+            $this->logger->debug('[Loading] Removed script tags via regex H̶͈̩̟̬̱͠E̡̨̬͔̳̜͢͠ ̡̧̯͉̩͙̩̹̞̠͎͈̹̥̠͞ͅͅC̶͉̞̘̖̝̗͓̬̯͍͉̤̬͢͢͞Ò̟̘͉͖͎͉̱̭̣̕M̴̯͈̻̱̱̣̗͈̠̙̲̥͘͞E̷̛͙̼̲͍͕̹͍͇̗̻̬̮̭̱̥͢Ş̛̟͔̙̜̤͇̮͍̙̝̀͘');
+            $html = preg_replace('/<script\b[^>]*>([\s\S]*?)<\/script>/', '', $html);
+        }
+
+        // Prepend the XML tag to avoid having issues with special characters. Should be harmless.
+        $dom->loadHTML('<?xml encoding="UTF-8">' . $html);
+        $dom->encoding = 'UTF-8';
+
+        $this->removeScripts($dom);
+
+        $this->prepDocument($dom);
+
+        $this->logger->debug('[Loading] Loaded HTML successfully.');
+
+        return $dom;
+    }
+
+    /**
+     * Tries to guess relevant info from metadata of the html. Sets the results in the Readability properties.
+     */
+    private function getMetadata()
+    {
+        $this->logger->debug('[Metadata] Retrieving metadata...');
+
+        $values = [];
+        // Match "description", or Twitter's "twitter:description" (Cards)
+        // in name attribute.
+        $namePattern = '/^\s*((twitter)\s*:\s*)?(description|title|image)\s*$/i';
+
+        // Match Facebook's Open Graph title & description properties.
+        $propertyPattern = '/^\s*og\s*:\s*(description|title|image)\s*$/i';
+
+        foreach ($this->dom->getElementsByTagName('meta') as $meta) {
+            /* @var DOMNode $meta */
+            $elementName = $meta->getAttribute('name');
+            $elementProperty = $meta->getAttribute('property');
+
+            if (in_array('author', [$elementName, $elementProperty])) {
+                $this->logger->info(sprintf('[Metadata] Found author: \'%s\'', $meta->getAttribute('content')));
+                $this->setAuthor($meta->getAttribute('content'));
+                continue;
+            }
+
+            $name = null;
+            if (preg_match($namePattern, $elementName)) {
+                $name = $elementName;
+            } elseif (preg_match($propertyPattern, $elementProperty)) {
+                $name = $elementProperty;
+            }
+
+            if ($name) {
+                $content = $meta->getAttribute('content');
+                if ($content) {
+                    // Convert to lowercase and remove any whitespace
+                    // so we can match below.
+                    $name = preg_replace('/\s/', '', strtolower($name));
+                    $values[$name] = trim($content);
+                }
+            }
+        }
+        if (array_key_exists('description', $values)) {
+            $this->logger->info(sprintf('[Metadata] Found excerpt in \'description\' tag: \'%s\'', $values['description']));
+            $this->setExcerpt($values['description']);
+        } elseif (array_key_exists('og:description', $values)) {
+            // Use facebook open graph description.
+            $this->logger->info(sprintf('[Metadata] Found excerpt in \'og:description\' tag: \'%s\'', $values['og:description']));
+            $this->setExcerpt($values['og:description']);
+        } elseif (array_key_exists('twitter:description', $values)) {
+            // Use twitter cards description.
+            $this->logger->info(sprintf('[Metadata] Found excerpt in \'twitter:description\' tag: \'%s\'', $values['twitter:description']));
+            $this->setExcerpt($values['twitter:description']);
+        }
+
+        $this->setTitle($this->getArticleTitle());
+
+        if (!$this->getTitle()) {
+            if (array_key_exists('og:title', $values)) {
+                // Use facebook open graph title.
+                $this->logger->info(sprintf('[Metadata] Found title in \'og:title\' tag: \'%s\'', $values['og:title']));
+                $this->setTitle($values['og:title']);
+            } elseif (array_key_exists('twitter:title', $values)) {
+                // Use twitter cards title.
+                $this->logger->info(sprintf('[Metadata] Found title in \'twitter:title\' tag: \'%s\'', $values['twitter:title']));
+                $this->setTitle($values['twitter:title']);
+            }
+        }
+
+        if (array_key_exists('og:image', $values) || array_key_exists('twitter:image', $values)) {
+            if (array_key_exists('og:image', $values)) {
+                $this->logger->info(sprintf('[Metadata] Found main image in \'og:image\' tag: \'%s\'', $values['og:image']));
+                $this->setImage($values['og:image']);
+            } else {
+                $this->logger->info(sprintf('[Metadata] Found main image in \'twitter:image\' tag: \'%s\'', $values['twitter:image']));
+                $this->setImage($values['twitter:image']);
+            }
+        }
+    }
+
+    /**
+     * Returns all the images of the parsed article.
+     *
+     * @return array
+     */
+    public function getImages()
+    {
+        $result = [];
+        if ($this->getImage()) {
+            $result[] = $this->getImage();
+        }
+
+        if (null == $this->getDOMDocument()) {
+            return $result;
+        }
+
+        foreach ($this->getDOMDocument()->getElementsByTagName('img') as $img) {
+            if ($src = $img->getAttribute('src')) {
+                $result[] = $src;
+            }
+        }
+
+        if ($this->configuration->getFixRelativeURLs()) {
+            foreach ($result as &$imgSrc) {
+                $imgSrc = $this->toAbsoluteURI($imgSrc);
+            }
+        }
+
+        $result = array_unique(array_filter($result));
+
+        return $result;
+    }
+
+    /**
+     * Tries to get the main article image. Will only update the metadata if the getMetadata function couldn't
+     * find a correct image.
+     */
+    public function getMainImage()
+    {
+        $imgUrl = false;
+
+        if ($this->getImage() !== null) {
+            $imgUrl = $this->getImage();
+        }
+
+        if (!$imgUrl) {
+            foreach ($this->dom->getElementsByTagName('link') as $link) {
+                /** @var \DOMElement $link */
+                /*
+                 * Check for the rel attribute, then check if the rel attribute is either img_src or image_src, and
+                 * finally check for the existence of the href attribute, which should hold the image url.
+                 */
+                if ($link->hasAttribute('rel') && ($link->getAttribute('rel') === 'img_src' || $link->getAttribute('rel') === 'image_src') && $link->hasAttribute('href')) {
+                    $imgUrl = $link->getAttribute('href');
+                    break;
+                }
+            }
+        }
+
+        if (!empty($imgUrl) && $this->configuration->getFixRelativeURLs()) {
+            $this->setImage($this->toAbsoluteURI($imgUrl));
+        }
+    }
+
+    /**
+     * Returns the title of the html. Prioritizes the title from the metadata against the title tag.
+     *
+     * @return string|null
+     */
+    private function getArticleTitle()
+    {
+        $originalTitle = null;
+
+        if ($this->getTitle()) {
+            $originalTitle = $this->getTitle();
+        } else {
+            $this->logger->debug('[Metadata] Could not find title in metadata, searching for the title tag...');
+            $titleTag = $this->dom->getElementsByTagName('title');
+            if ($titleTag->length > 0) {
+                $this->logger->info(sprintf('[Metadata] Using title tag as article title: \'%s\'', $titleTag->item(0)->nodeValue));
+                $originalTitle = $titleTag->item(0)->nodeValue;
+            }
+        }
+
+        if ($originalTitle === null) {
+            return null;
+        }
+
+        $curTitle = $originalTitle;
+        $titleHadHierarchicalSeparators = false;
+
+        /*
+         * If there's a separator in the title, first remove the final part
+         *
+         * Sanity warning: if you eval this match in PHPStorm's "Evaluate expression" box, it will return false
+         * I can assure you it works properly if you let the code run.
+         */
+        if (preg_match('/ [\|\-\\\\\/>»] /i', $curTitle)) {
+            $titleHadHierarchicalSeparators = (bool)preg_match('/ [\\\\\/>»] /', $curTitle);
+            $curTitle = preg_replace('/(.*)[\|\-\\\\\/>»] .*/i', '$1', $originalTitle);
+
+            $this->logger->info(sprintf('[Metadata] Found hierarchical separators in title, new title is: \'%s\'', $curTitle));
+
+            // If the resulting title is too short (3 words or fewer), remove
+            // the first part instead:
+            if (count(preg_split('/\s+/', $curTitle)) < 3) {
+                $curTitle = preg_replace('/[^\|\-\\\\\/>»]*[\|\-\\\\\/>»](.*)/i', '$1', $originalTitle);
+                $this->logger->info(sprintf('[Metadata] Title too short, using the first part of the title instead: \'%s\'', $curTitle));
+            }
+        } elseif (strpos($curTitle, ': ') !== false) {
+            // Check if we have an heading containing this exact string, so we
+            // could assume it's the full title.
+            $match = false;
+            for ($i = 1; $i <= 2; $i++) {
+                foreach ($this->dom->getElementsByTagName('h' . $i) as $hTag) {
+                    // Trim texts to avoid having false negatives when the title is surrounded by spaces or tabs
+                    if (trim($hTag->nodeValue) === trim($curTitle)) {
+                        $match = true;
+                    }
+                }
+            }
+
+            // If we don't, let's extract the title out of the original title string.
+            if (!$match) {
+                $curTitle = substr($originalTitle, strrpos($originalTitle, ':') + 1);
+
+                $this->logger->info(sprintf('[Metadata] Title has a colon in the middle, new title is: \'%s\'', $curTitle));
+
+                // If the title is now too short, try the first colon instead:
+                if (count(preg_split('/\s+/', $curTitle)) < 3) {
+                    $curTitle = substr($originalTitle, strpos($originalTitle, ':') + 1);
+                    $this->logger->info(sprintf('[Metadata] Title too short, using the first part of the title instead: \'%s\'', $curTitle));
+                } elseif (count(preg_split('/\s+/', substr($curTitle, 0, strpos($curTitle, ':')))) > 5) {
+                    // But if we have too many words before the colon there's something weird
+                    // with the titles and the H tags so let's just use the original title instead
+                    $curTitle = $originalTitle;
+                }
+            }
+        } elseif (mb_strlen($curTitle) > 150 || mb_strlen($curTitle) < 15) {
+            $hOnes = $this->dom->getElementsByTagName('h1');
+
+            if ($hOnes->length === 1) {
+                $curTitle = $hOnes->item(0)->nodeValue;
+                $this->logger->info(sprintf('[Metadata] Using title from an H1 node: \'%s\'', $curTitle));
+            }
+        }
+
+        $curTitle = trim($curTitle);
+
+        /*
+         * If we now have 4 words or fewer as our title, and either no
+         * 'hierarchical' separators (\, /, > or ») were found in the original
+         * title or we decreased the number of words by more than 1 word, use
+         * the original title.
+         */
+        $curTitleWordCount = count(preg_split('/\s+/', $curTitle));
+        $originalTitleWordCount = count(preg_split('/\s+/', preg_replace('/[\|\-\\\\\/>»]+/', '', $originalTitle))) - 1;
+
+        if ($curTitleWordCount <= 4 &&
+            (!$titleHadHierarchicalSeparators || $curTitleWordCount !== $originalTitleWordCount)) {
+            $curTitle = $originalTitle;
+
+            $this->logger->info(sprintf('Using title from an H1 node: \'%s\'', $curTitle));
+        }
+
+        return $curTitle;
+    }
+
+    /**
+     * Convert URI to an absolute URI.
+     *
+     * @param $uri string URI to convert
+     *
+     * @return string
+     */
+    private function toAbsoluteURI($uri)
+    {
+        list($pathBase, $scheme, $prePath) = $this->getPathInfo($this->configuration->getOriginalURL());
+
+        // If this is already an absolute URI, return it.
+        if (preg_match('/^[a-zA-Z][a-zA-Z0-9\+\-\.]*:/', $uri)) {
+            return $uri;
+        }
+
+        // Scheme-rooted relative URI.
+        if (substr($uri, 0, 2) === '//') {
+            return $scheme . '://' . substr($uri, 2);
+        }
+
+        // Prepath-rooted relative URI.
+        if (substr($uri, 0, 1) === '/') {
+            return $prePath . $uri;
+        }
+
+        // Dotslash relative URI.
+        if (strpos($uri, './') === 0) {
+            return $pathBase . substr($uri, 2);
+        }
+        // Ignore hash URIs:
+        if (substr($uri, 0, 1) === '#') {
+            return $uri;
+        }
+
+        // Standard relative URI; add entire path. pathBase already includes a
+        // trailing "/".
+        return $pathBase . $uri;
+    }
+
+    /**
+     * Returns full path info of an URL.
+     *
+     * @param  string $url
+     *
+     * @return array [$pathBase, $scheme, $prePath]
+     */
+    public function getPathInfo($url)
+    {
+        // Check for base URLs
+        if ($this->dom->baseURI !== null) {
+            if (substr($this->dom->baseURI, 0, 1) === '/') {
+                // URLs starting with '/' override completely the URL defined in the link
+                $pathBase = parse_url($url, PHP_URL_SCHEME) . '://' . parse_url($url, PHP_URL_HOST) . $this->dom->baseURI;
+            } else {
+                // Otherwise just prepend the base to the actual path
+                $pathBase = parse_url($url, PHP_URL_SCHEME) . '://' . parse_url($url, PHP_URL_HOST) . dirname(parse_url($url, PHP_URL_PATH)) . '/' . rtrim($this->dom->baseURI, '/') . '/';
+            }
+        } else {
+            $pathBase = parse_url($url, PHP_URL_SCHEME) . '://' . parse_url($url, PHP_URL_HOST) . dirname(parse_url($url, PHP_URL_PATH)) . '/';
+        }
+
+        $scheme = parse_url($pathBase, PHP_URL_SCHEME);
+        $prePath = $scheme . '://' . parse_url($pathBase, PHP_URL_HOST);
+
+        return [$pathBase, $scheme, $prePath];
+    }
+
+    /**
+     * Gets nodes from the root element.
+     *
+     * @param $node DOMNode|DOMText
+     *
+     * @return array
+     */
+    private function getNodes($node)
+    {
+        $this->logger->info('[Get Nodes] Retrieving nodes...');
+
+        $stripUnlikelyCandidates = $this->configuration->getStripUnlikelyCandidates();
+
+        $elementsToScore = [];
+
+        /*
+         * First, node prepping. Trash nodes that look cruddy (like ones with the
+         * class name "comment", etc), and turn divs into P tags where they have been
+         * used inappropriately (as in, where they contain no other block level elements.)
+         */
+
+        while ($node) {
+            $matchString = $node->getAttribute('class') . ' ' . $node->getAttribute('id');
+
+            // Remove DOMComments nodes as we don't need them and mess up children counting
+            if ($node->nodeType === XML_COMMENT_NODE) {
+                $this->logger->debug(sprintf('[Get Nodes] Found comment node, removing... Node content was: \'%s\'', substr($node->nodeValue, 0, 128)));
+                $node = NodeUtility::removeAndGetNext($node);
+                continue;
+            }
+
+            // Check to see if this node is a byline, and remove it if it is.
+            if ($this->checkByline($node, $matchString)) {
+                $this->logger->debug(sprintf('[Get Nodes] Found byline, removing... Node content was: \'%s\'', substr($node->nodeValue, 0, 128)));
+                $node = NodeUtility::removeAndGetNext($node);
+                continue;
+            }
+
+            // Remove unlikely candidates
+            if ($stripUnlikelyCandidates) {
+                if (
+                    preg_match(NodeUtility::$regexps['unlikelyCandidates'], $matchString) &&
+                    !preg_match(NodeUtility::$regexps['okMaybeItsACandidate'], $matchString) &&
+                    $node->nodeName !== 'body' &&
+                    $node->nodeName !== 'a'
+                ) {
+                    $this->logger->debug(sprintf('[Get Nodes] Removing unlikely candidate. Node content was: \'%s\'', substr($node->nodeValue, 0, 128)));
+                    $node = NodeUtility::removeAndGetNext($node);
+                    continue;
+                }
+            }
+
+            // Remove DIV, SECTION, and HEADER nodes without any content(e.g. text, image, video, or iframe).
+            if (($node->nodeName === 'div' || $node->nodeName === 'section' || $node->nodeName === 'header' ||
+                    $node->nodeName === 'h1' || $node->nodeName === 'h2' || $node->nodeName === 'h3' ||
+                    $node->nodeName === 'h4' || $node->nodeName === 'h5' || $node->nodeName === 'h6' ||
+                    $node->nodeName === 'p') &&
+                $node->isElementWithoutContent()) {
+                $this->logger->debug(sprintf('[Get Nodes] Removing empty \'%s\' node.', $node->nodeName));
+                $node = NodeUtility::removeAndGetNext($node);
+                continue;
+            }
+
+            if (in_array(strtolower($node->nodeName), $this->defaultTagsToScore)) {
+                $this->logger->debug(sprintf('[Get Nodes] Adding node to score list, node content is: \'%s\'', substr($node->nodeValue, 0, 128)));
+                $elementsToScore[] = $node;
+            }
+
+            // Turn all divs that don't have children block level elements into p's
+            if ($node->nodeName === 'div') {
+                /*
+                 * Sites like http://mobile.slate.com encloses each paragraph with a DIV
+                 * element. DIVs with only a P element inside and no text content can be
+                 * safely converted into plain P elements to avoid confusing the scoring
+                 * algorithm with DIVs with are, in practice, paragraphs.
+                 */
+                if ($node->hasSinglePNode()) {
+                    $this->logger->debug(sprintf('[Get Nodes] Found DIV with a single P node, removing DIV. Node content is: \'%s\'', substr($node->nodeValue, 0, 128)));
+                    $pNode = $node->getChildren(true)[0];
+                    $node->parentNode->replaceChild($pNode, $node);
+                    $node = $pNode;
+                    $elementsToScore[] = $node;
+                } elseif (!$node->hasSingleChildBlockElement()) {
+                    $this->logger->debug(sprintf('[Get Nodes] Found DIV with a single child block element, converting to a P node. Node content is: \'%s\'', substr($node->nodeValue, 0, 128)));
+                    $node = NodeUtility::setNodeTag($node, 'p');
+                    $elementsToScore[] = $node;
+                } else {
+                    // EXPERIMENTAL
+                    foreach ($node->getChildren() as $child) {
+                        /** @var $child DOMNode */
+                        if ($child->nodeType === XML_TEXT_NODE && mb_strlen(trim($child->getTextContent())) > 0) {
+                            $this->logger->debug(sprintf('[Get Nodes] Found DIV a text node inside, converting to a P node. Node content is: \'%s\'', substr($node->nodeValue, 0, 128)));
+                            $newNode = $node->createNode($child, 'p');
+                            $child->parentNode->replaceChild($newNode, $child);
+                        }
+                    }
+                }
+            }
+
+            $node = NodeUtility::getNextNode($node);
+        }
+
+        return $elementsToScore;
+    }
+
+    /**
+     * Checks if the node is a byline.
+     *
+     * @param DOMNode $node
+     * @param string $matchString
+     *
+     * @return bool
+     */
+    private function checkByline($node, $matchString)
+    {
+        if (!$this->configuration->getArticleByLine()) {
+            return false;
+        }
+
+        /*
+         * Check if the byline is already set
+         */
+        if ($this->getAuthor()) {
+            return false;
+        }
+
+        $rel = $node->getAttribute('rel');
+
+        if ($rel === 'author' || preg_match(NodeUtility::$regexps['byline'], $matchString) && $this->isValidByline($node->getTextContent())) {
+            $this->logger->info(sprintf('[Metadata] Found article author: \'%s\'', $node->getTextContent()));
+            $this->setAuthor(trim($node->getTextContent()));
+
+            return true;
+        }
+
+        return false;
+    }
+
+    /**
+     * Checks the validity of a byLine. Based on string length.
+     *
+     * @param string $text
+     *
+     * @return bool
+     */
+    private function isValidByline($text)
+    {
+        if (gettype($text) == 'string') {
+            $byline = trim($text);
+
+            return (mb_strlen($byline) > 0) && (mb_strlen($text) < 100);
+        }
+
+        return false;
+    }
+
+    /**
+     * Removes all the scripts of the html.
+     *
+     * @param DOMDocument $dom
+     */
+    private function removeScripts(DOMDocument $dom)
+    {
+        $toRemove = ['script', 'noscript'];
+
+        foreach ($toRemove as $tag) {
+            while ($script = $dom->getElementsByTagName($tag)) {
+                if ($script->item(0)) {
+                    $script->item(0)->parentNode->removeChild($script->item(0));
+                } else {
+                    break;
+                }
+            }
+        }
+    }
+
+    /**
+     * Prepares the document for parsing.
+     *
+     * @param DOMDocument $dom
+     */
+    private function prepDocument(DOMDocument $dom)
+    {
+        $this->logger->info('[PrepDocument] Preparing document for parsing...');
+
+        /*
+         * DOMNodeList must be converted to an array before looping over it.
+         * This is done to avoid node shifting when removing nodes.
+         *
+         * Reverse traversing cannot be done here because we need to find brs that are right next to other brs.
+         * (If we go the other way around we need to search for previous nodes forcing the creation of new functions
+         * that will be used only here)
+         */
+        foreach (iterator_to_array($dom->getElementsByTagName('br')) as $br) {
+            $next = $br->nextSibling;
+
+            /*
+             * Whether 2 or more <br> elements have been found and replaced with a
+             * <p> block.
+             */
+            $replaced = false;
+
+            /*
+             * If we find a <br> chain, remove the <br>s until we hit another element
+             * or non-whitespace. This leaves behind the first <br> in the chain
+             * (which will be replaced with a <p> later).
+             */
+            while (($next = NodeUtility::nextElement($next)) && ($next->nodeName === 'br')) {
+                $this->logger->debug('[PrepDocument] Removing chain of BR nodes...');
+
+                $replaced = true;
+                $brSibling = $next->nextSibling;
+                $next->parentNode->removeChild($next);
+                $next = $brSibling;
+            }
+
+            /*
+             * If we removed a <br> chain, replace the remaining <br> with a <p>. Add
+             * all sibling nodes as children of the <p> until we hit another <br>
+             * chain.
+             */
+
+            if ($replaced) {
+                $p = $dom->createElement('p');
+                $br->parentNode->replaceChild($p, $br);
+
+                $next = $p->nextSibling;
+                while ($next) {
+                    // If we've hit another <br><br>, we're done adding children to this <p>.
+                    if ($next->nodeName === 'br') {
+                        $nextElem = NodeUtility::nextElement($next);
+                        if ($nextElem && $nextElem->nodeName === 'br') {
+                            break;
+                        }
+                    }
+
+                    $this->logger->debug('[PrepDocument] Replacing BR with a P node...');
+
+                    // Otherwise, make this node a child of the new <p>.
+                    $sibling = $next->nextSibling;
+                    $p->appendChild($next);
+                    $next = $sibling;
+                }
+            }
+        }
+
+        // Replace font tags with span
+        $fonts = $dom->getElementsByTagName('font');
+        $length = $fonts->length;
+        for ($i = 0; $i < $length; $i++) {
+            $this->logger->debug('[PrepDocument] Converting font tag into a span tag.');
+            $font = $fonts->item($length - 1 - $i);
+            NodeUtility::setNodeTag($font, 'span', true);
+        }
+    }
+
+    /**
+     * Assign scores to each node. Returns full article parsed or false on error.
+     *
+     * @param array $nodes
+     *
+     * @return DOMDocument|bool
+     */
+    private function rateNodes($nodes)
+    {
+        $this->logger->info('[Rating] Rating nodes...');
+
+        $candidates = [];
+
+        /** @var DOMElement $node */
+        foreach ($nodes as $node) {
+            if (is_null($node->parentNode)) {
+                continue;
+            }
+
+            // Discard nodes with less than 25 characters, without blank space
+            if (mb_strlen($node->getTextContent(true)) < 25) {
+                continue;
+            }
+
+            $ancestors = $node->getNodeAncestors();
+
+            // Exclude nodes with no ancestor
+            if (count($ancestors) === 0) {
+                continue;
+            }
+
+            // Start with a point for the paragraph itself as a base.
+            $contentScore = 1;
+
+            // Add points for any commas within this paragraph.
+            $contentScore += count(explode(',', $node->getTextContent(true)));
+
+            // For every 100 characters in this paragraph, add another point. Up to 3 points.
+            $contentScore += min(floor(mb_strlen($node->getTextContent(true)) / 100), 3);
+
+            $this->logger->debug(sprintf('[Rating] Node score %s, content: \'%s\'', $contentScore, substr($node->nodeValue, 0, 128)));
+
+            /** @var $ancestor DOMElement */
+            foreach ($ancestors as $level => $ancestor) {
+                $this->logger->debug('[Rating] Found ancestor, initializing and adding it as a candidate...');
+                if (!$ancestor->isInitialized()) {
+                    $ancestor->initializeNode($this->configuration->getWeightClasses());
+                    $candidates[] = $ancestor;
+                }
+
+                /*
+                 * Node score divider:
+                 *  - parent:             1 (no division)
+                 *  - grandparent:        2
+                 *  - great grandparent+: ancestor level * 3
+                 */
+
+                if ($level === 0) {
+                    $scoreDivider = 1;
+                } elseif ($level === 1) {
+                    $scoreDivider = 2;
+                } else {
+                    $scoreDivider = $level * 3;
+                }
+
+                $currentScore = $ancestor->contentScore;
+                $ancestor->contentScore = $currentScore + ($contentScore / $scoreDivider);
+
+                $this->logger->debug(sprintf('[Rating] Ancestor score %s, value: \'%s\'', $ancestor->contentScore, substr($ancestor->nodeValue, 0, 128)));
+            }
+        }
+
+        /*
+         * After we've calculated scores, loop through all of the possible
+         * candidate nodes we found and find the one with the highest score.
+         */
+
+        $topCandidates = [];
+        foreach ($candidates as $candidate) {
+
+            /*
+             * Scale the final candidates score based on link density. Good content
+             * should have a relatively small link density (5% or less) and be mostly
+             * unaffected by this operation.
+             */
+
+            $candidate->contentScore = $candidate->contentScore * (1 - $candidate->getLinkDensity());
+
+            for ($i = 0; $i < $this->configuration->getMaxTopCandidates(); $i++) {
+                $aTopCandidate = isset($topCandidates[$i]) ? $topCandidates[$i] : null;
+
+                if (!$aTopCandidate || $candidate->contentScore > $aTopCandidate->contentScore) {
+                    array_splice($topCandidates, $i, 0, [$candidate]);
+                    if (count($topCandidates) > $this->configuration->getMaxTopCandidates()) {
+                        array_pop($topCandidates);
+                    }
+                    break;
+                }
+            }
+        }
+
+        $topCandidate = isset($topCandidates[0]) ? $topCandidates[0] : null;
+        $parentOfTopCandidate = null;
+
+        /*
+         * If we still have no top candidate, just use the body as a last resort.
+         * We also have to copy the body node so it is something we can modify.
+         */
+
+        if ($topCandidate === null || $topCandidate->nodeName === 'body') {
+            $this->logger->info('[Rating] No top candidate found or top candidate is the body tag. Moving all child nodes to a new DIV node.');
+
+            // Move all of the page's children into topCandidate
+            $topCandidate = new DOMDocument('1.0', 'utf-8');
+            $topCandidate->encoding = 'UTF-8';
+            $topCandidate->appendChild($topCandidate->createElement('div', ''));
+            $kids = $this->dom->getElementsByTagName('body')->item(0)->childNodes;
+
+            // Cannot be foreached, don't ask me why.
+            for ($i = 0; $i < $kids->length; $i++) {
+                $import = $topCandidate->importNode($kids->item($i), true);
+                $topCandidate->firstChild->appendChild($import);
+            }
+
+            // Candidate must be created using firstChild to grab the DOMElement instead of the DOMDocument.
+            $topCandidate = $topCandidate->firstChild;
+        } elseif ($topCandidate) {
+            $this->logger->info(sprintf('[Rating] Found top candidate, score: %s', $topCandidate->contentScore));
+            // Find a better top candidate node if it contains (at least three) nodes which belong to `topCandidates` array
+            // and whose scores are quite closed with current `topCandidate` node.
+            $alternativeCandidateAncestors = [];
+            for ($i = 1; $i < count($topCandidates); $i++) {
+                if ($topCandidates[$i]->contentScore / $topCandidate->contentScore >= 0.75) {
+                    array_push($alternativeCandidateAncestors, $topCandidates[$i]->getNodeAncestors(false));
+                }
+            }
+
+            $MINIMUM_TOPCANDIDATES = 3;
+            if (count($alternativeCandidateAncestors) >= $MINIMUM_TOPCANDIDATES) {
+                $parentOfTopCandidate = $topCandidate->parentNode;
+                while ($parentOfTopCandidate->nodeName !== 'body') {
+                    $listsContainingThisAncestor = 0;
+                    for ($ancestorIndex = 0; $ancestorIndex < count($alternativeCandidateAncestors) && $listsContainingThisAncestor < $MINIMUM_TOPCANDIDATES; $ancestorIndex++) {
+                        $listsContainingThisAncestor += (int)in_array($parentOfTopCandidate, $alternativeCandidateAncestors[$ancestorIndex]);
+                    }
+                    if ($listsContainingThisAncestor >= $MINIMUM_TOPCANDIDATES) {
+                        $topCandidate = $parentOfTopCandidate;
+                        break;
+                    }
+                    $parentOfTopCandidate = $parentOfTopCandidate->parentNode;
+                }
+            }
+
+            /*
+             * Because of our bonus system, parents of candidates might have scores
+             * themselves. They get half of the node. There won't be nodes with higher
+             * scores than our topCandidate, but if we see the score going *up* in the first
+             * few steps up the tree, that's a decent sign that there might be more content
+             * lurking in other places that we want to unify in. The sibling stuff
+             * below does some of that - but only if we've looked high enough up the DOM
+             * tree.
+             */
+
+            $parentOfTopCandidate = $topCandidate->parentNode;
+            $lastScore = $topCandidate->contentScore;
+
+            // The scores shouldn't get too low.