Merge pull request #24 from j0k3r/links

Don't be to hard on 'links' attribute

.gitattributes

@@ -0,0 +1,9 @@
+/.editorconfig export-ignore
+/.gitattributes export-ignore
+/.gitignore export-ignore
+/.scrutinizer.yml export-ignore
+/.travis.yml export-ignore
+/.php_cs export-ignore
+/README.md export-ignore
+/phpunit.xml.dist export-ignore
+/tests export-ignore

.gitignore

@@ -1,3 +1,4 @@
 vendor/
 coverage/
 composer.lock
+.php_cs.cache

.php_cs

@@ -0,0 +1,20 @@
+<?php
+
+return Symfony\CS\Config\Config::create()
+    ->setUsingCache(true)
+    ->level(Symfony\CS\FixerInterface::SYMFONY_LEVEL)
+    // use default SYMFONY_LEVEL and extra fixers:
+    ->fixers(array(
+        'concat_with_spaces',
+        'ordered_use',
+        'phpdoc_order',
+        'strict',
+        'strict_param',
+        'long_array_syntax',
+    ))
+    ->finder(
+        Symfony\CS\Finder\DefaultFinder::create()
+            ->in(__DIR__)
+            ->exclude(array('vendor'))
+    )
+;

.scrutinizer.yml

@@ -1,3 +1,2 @@
 tools:
-    external_code_coverage:
-        timeout: 600
+    external_code_coverage: false

.travis.yml

@@ -6,19 +6,38 @@ php:
     - 5.4
     - 5.5
     - 5.6
+    - 7.0
+    - 7.1
     - nightly
     - hhvm
 
-# run build against nightly but allow them to fail
 matrix:
+    include:
+        - php: 7.0
+          env: CS_FIXER=run
     fast_finish: true
     allow_failures:
-        - php: nightly
         - php: hhvm
+        - php: nightly
 
 # faster builds on new travis setup not using sudo
 sudo: false
 
+# cache vendor dirs
+cache:
+    directories:
+        - vendor
+        - $HOME/.composer/cache
+
+before_install:
+    - if [ -n "$GH_TOKEN" ]; then composer config github-oauth.github.com ${GH_TOKEN}; fi;
+    # disable TLS for composer because openssl is disabled for PHP 5.3.3 on travis
+    # see: https://blog.travis-ci.com/upcoming_ubuntu_11_10_migration/
+    - if [[ $TRAVIS_PHP_VERSION = 5.3.3 ]]; then composer config -g -- disable-tls true; fi;
+    - if [[ $TRAVIS_PHP_VERSION = 5.3.3 ]]; then composer config -g -- secure-http false; fi;
+    # no version compatible with PHP > 7.1
+    - if [[ $TRAVIS_PHP_VERSION = 7.2.* ]]; then composer remove friendsofphp/php-cs-fixer; fi;
+
 install:
     - composer self-update
 
@@ -26,9 +45,9 @@ before_script:
     - composer install --prefer-dist --no-interaction
 
 script:
-    - phpunit --coverage-clover=coverage.clover
+    - mkdir -p build/logs
+    - phpunit -v --coverage-clover build/logs/clover.xml
+    - if [ "$CS_FIXER" = "run" ]; then php vendor/bin/php-cs-fixer fix --verbose --dry-run ; fi;
 
 after_script:
-    - |
-        wget https://scrutinizer-ci.com/ocular.phar
-        php ocular.phar code-coverage:upload --format=php-clover coverage.clover
+    - php vendor/bin/coveralls -v

README.md

@@ -1,13 +1,13 @@
 # Readability
 
 [![Build Status](https://travis-ci.org/j0k3r/php-readability.svg?branch=master)](https://travis-ci.org/j0k3r/php-readability)
-[![Code Coverage](https://scrutinizer-ci.com/g/j0k3r/php-readability/badges/coverage.png?b=master)](https://scrutinizer-ci.com/g/j0k3r/php-readability/?branch=master)
+[![Coverage Status](https://coveralls.io/repos/j0k3r/php-readability/badge.svg?branch=master&service=github)](https://coveralls.io/github/j0k3r/php-readability/?branch=master)
 
-This is an extract of the Readability class from the [full-text-rss](https://github.com/Dither/full-text-rss) fork. It kind be defined as a better version of the original [php-readability](https://bitbucket.org/fivefilters/php-readability/overview).
+This is an extract of the Readability class from this [full-text-rss](https://github.com/Dither/full-text-rss) fork. It can be defined as a better version of the original [php-readability](https://bitbucket.org/fivefilters/php-readability/overview).
 
 ## Differences
 
-The default php-readability lib is really old and needs to be improved. I found a great fork of [full-text-rss](http://fivefilters.org/content-only/) from @Dither which improve the Readability class.
+The default php-readability lib is really old and needs to be improved. I found a great fork of full-text-rss from [@Dither](https://github.com/Dither/full-text-rss) which improve the Readability class.
 
  - I've extracted the class from its fork to be able to use it out of the box
  - I've added some simple tests
@@ -15,6 +15,12 @@ The default php-readability lib is really old and needs to be improved. I found
 
 **But** the code is still really hard to understand / read ...
 
+## Requirements
+
+By default, this lib will use the [Tidy extension](https://github.com/htacg/tidy-html5) if it's available. Tidy is only used to cleanup the given HTML and avoid problems with bad HTML structure, etc ..
+
+Since Composer doesn't support suggestion on PHP extension, I write this suggestion here.
+
 ## Usage
 
 ```php
@@ -26,6 +32,8 @@ $url = 'http://www.medialens.org/index.php/alerts/alert-archive/alerts-2013/729-
 $html = file_get_contents($url);
 
 $readability = new Readability($html, $url);
+// or without Tidy
+// $readability = new Readability($html, $url, 'libxml', false);
 $result = $readability->init();
 
 if ($result) {
@@ -37,3 +45,20 @@ if ($result) {
     echo 'Looks like we couldn\'t find the content. :(';
 }
 ```
+
+If you want to debug it, or check what's going on, you can inject a logger (which must follow `Psr\Log\LoggerInterface`, Monolog for example):
+
+```php
+use Readability\Readability;
+use Monolog\Logger;
+use Monolog\Handler\StreamHandler;
+
+$url = 'http://www.medialens.org/index.php/alerts/alert-archive/alerts-2013/729-thatcher.html';
+$html = file_get_contents($url);
+
+$logger = new Logger('readability');
+$logger->pushHandler(new StreamHandler('path/to/your.log', Logger::DEBUG));
+
+$readability = new Readability($html, $url);
+$readability->setLogger($logger);
+```

composer.json

@@ -25,7 +25,12 @@
     }],
     "require": {
         "php": ">=5.3.3",
-        "ext-tidy": ">=1.2"
+        "psr/log": "^1.0"
+    },
+    "require-dev": {
+        "satooshi/php-coveralls": "~0.6",
+        "friendsofphp/php-cs-fixer": "<2",
+        "monolog/monolog": "^1.13"
     },
     "autoload": {
         "psr-4": { "Readability\\": "src/" }

phpunit.xml.dist

@@ -26,7 +26,7 @@
         </whitelist>
     </filter>
 
-    <logging>
+    <!-- <logging>
         <log type="coverage-html" target="coverage" title="Readability" charset="UTF-8" yui="true" highlight="true" lowUpperBound="35" highLowerBound="70"/>
-    </logging>
+    </logging> -->
 </phpunit>

src/JSLikeHTMLElement.php

@@ -45,18 +45,19 @@ class JSLikeHTMLElement extends \DOMElement
      */
     public function __set($name, $value)
     {
-        if ($name == 'innerHTML') {
+        if ($name === 'innerHTML') {
             // first, empty the element
             for ($x = $this->childNodes->length - 1; $x >= 0; --$x) {
                 $this->removeChild($this->childNodes->item($x));
             }
 
             // $value holds our new inner HTML
-            if ($value != '') {
+            if ($value !== '') {
                 $f = $this->ownerDocument->createDocumentFragment();
 
                 // appendXML() expects well-formed markup (XHTML)
-                $result = @$f->appendXML($value); // @ to suppress PHP warnings
+                // @ to suppress PHP warnings
+                $result = @$f->appendXML($value);
                 if ($result) {
                     if ($f->hasChildNodes()) {
                         $this->appendChild($f);
@@ -71,10 +72,11 @@ class JSLikeHTMLElement extends \DOMElement
                     // We use it (and suppress the warning) because an HTML fragment will
                     // be wrapped around <html><body> tags which we don't really want to keep.
                     // Note: despite the warning, if loadHTML succeeds it will return true.
-                    $result = @$f->loadHTML('<htmlfragment>'.$value.'</htmlfragment>');
+                    $result = @$f->loadHTML('<htmlfragment>' . $value . '</htmlfragment>');
 
                     if ($result) {
                         $import = $f->getElementsByTagName('htmlfragment')->item(0);
+
                         foreach ($import->childNodes as $child) {
                             $importedNode = $this->ownerDocument->importNode($child, true);
                             $this->appendChild($importedNode);
@@ -87,7 +89,7 @@ class JSLikeHTMLElement extends \DOMElement
             }
         } else {
             $trace = debug_backtrace();
-            trigger_error('Undefined property via __set(): '.$name.' in '.$trace[0]['file'].' on line '.$trace[0]['line'], E_USER_NOTICE);
+            trigger_error('Undefined property via __set(): ' . $name . ' in ' . $trace[0]['file'] . ' on line ' . $trace[0]['line'], E_USER_NOTICE);
         }
     }
 
@@ -100,8 +102,9 @@ class JSLikeHTMLElement extends \DOMElement
      */
     public function __get($name)
     {
-        if ($name == 'innerHTML') {
+        if ($name === 'innerHTML') {
             $inner = '';
+
             foreach ($this->childNodes as $child) {
                 $inner .= $this->ownerDocument->saveXML($child);
             }
@@ -110,13 +113,13 @@ class JSLikeHTMLElement extends \DOMElement
         }
 
         $trace = debug_backtrace();
-        trigger_error('Undefined property via __get(): '.$name.' in '.$trace[0]['file'].' on line '.$trace[0]['line'], E_USER_NOTICE);
+        trigger_error('Undefined property via __get(): ' . $name . ' in ' . $trace[0]['file'] . ' on line ' . $trace[0]['line'], E_USER_NOTICE);
 
         return;
     }
 
     public function __toString()
     {
-        return '['.$this->tagName.']';
+        return '[' . $this->tagName . ']';
     }
 }

tests/ReadabilityTest.php

@@ -2,48 +2,74 @@
 
 namespace Tests\Readability;
 
+use Monolog\Handler\TestHandler;
+use Monolog\Logger;
 use Readability\Readability;
 
-class ReadabilityTested extends Readability
-{
-    public function getDebugText()
-    {
-        return $this->debugText;
-    }
-
-    public function getDomainRegexp()
-    {
-        return $this->domainRegExp;
-    }
-}
-
 class ReadabilityTest extends \PHPUnit_Framework_TestCase
 {
+    public $logHandler;
+    public $logger;
+
+    private function getReadability($html, $url = null, $parser = 'libxml', $useTidy = true)
+    {
+        $readability = new Readability($html, $url, $parser, $useTidy);
+
+        $this->logHandler = new TestHandler();
+        $this->logger = new Logger('test', array($this->logHandler));
+        $readability->setLogger($this->logger);
+
+        return $readability;
+    }
+
+    /**
+     * @requires extension tidy
+     */
     public function testConstructDefault()
     {
-        $readability = new ReadabilityTested('');
+        $readability = $this->getReadability('');
 
         $this->assertNull($readability->url);
-        $this->assertContains('Parsing URL', $readability->getDebugText());
-        $this->assertContains('Tidying document', $readability->getDebugText());
-        $this->assertNull($readability->getDomainRegexp());
         $this->assertInstanceOf('DomDocument', $readability->dom);
     }
 
+    /**
+     * @requires extension tidy
+     */
     public function testConstructSimple()
     {
-        $readability = new ReadabilityTested('<html/>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<html/>', 'http://0.0.0.0');
 
         $this->assertEquals('http://0.0.0.0', $readability->url);
-        $this->assertContains('Parsing URL', $readability->getDebugText());
-        $this->assertContains('Tidying document', $readability->getDebugText());
-        $this->assertEquals('/0\.0\.0\.0/', $readability->getDomainRegexp());
         $this->assertInstanceOf('DomDocument', $readability->dom);
+        $this->assertEquals('<html/>', $readability->original_html);
+        $this->assertTrue($readability->tidied);
+    }
+
+    public function testConstructDefaultWithoutTidy()
+    {
+        $readability = $this->getReadability('', null, 'libxml', false);
+
+        $this->assertNull($readability->url);
+        $this->assertEquals('', $readability->original_html);
+        $this->assertFalse($readability->tidied);
+
+        $this->assertInstanceOf('DomDocument', $readability->dom);
+    }
+
+    public function testConstructSimpleWithoutTidy()
+    {
+        $readability = $this->getReadability('<html/>', 'http://0.0.0.0', 'libxml', false);
+
+        $this->assertEquals('http://0.0.0.0', $readability->url);
+        $this->assertInstanceOf('DomDocument', $readability->dom);
+        $this->assertEquals('<html/>', $readability->original_html);
+        $this->assertFalse($readability->tidied);
     }
 
     public function testInitNoContent()
     {
-        $readability = new ReadabilityTested('<html/>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<html/>', 'http://0.0.0.0');
         $res = $readability->init();
 
         $this->assertFalse($res);
@@ -55,7 +81,7 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
     public function testInitP()
     {
-        $readability = new ReadabilityTested(str_repeat('<p>This is the awesome content :)</p>', 7), 'http://0.0.0.0');
+        $readability = $this->getReadability(str_repeat('<p>This is the awesome content :)</p>', 7), 'http://0.0.0.0');
         $res = $readability->init();
 
         $this->assertTrue($res);
@@ -68,7 +94,7 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
     public function testInitDivP()
     {
-        $readability = new ReadabilityTested('<div>'.str_repeat('<p>This is the awesome content :)</p>', 7).'</div>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<div>' . str_repeat('<p>This is the awesome content :)</p>', 7) . '</div>', 'http://0.0.0.0');
         $res = $readability->init();
 
         $this->assertTrue($res);
@@ -81,7 +107,7 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
     public function testInitDiv()
     {
-        $readability = new ReadabilityTested('<div>'.str_repeat('This is the awesome content :)', 7).'</div>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<div>' . str_repeat('This is the awesome content :)', 7) . '</div>', 'http://0.0.0.0');
         $readability->debug = true;
         $res = $readability->init();
 
@@ -95,7 +121,7 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
     public function testWithFootnotes()
     {
-        $readability = new ReadabilityTested('<div>'.str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7).'</div>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<div>' . str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7) . '</div>', 'http://0.0.0.0');
         $readability->debug = true;
         $readability->convertLinksToFootnotes = true;
         $res = $readability->init();
@@ -112,7 +138,7 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
     public function testStandardClean()
     {
-        $readability = new ReadabilityTested('<div><h2>Title</h2>'.str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7).'<a href="#nofollow" rel="nofollow">will NOT be removed</a></div>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<div><h2>Title</h2>' . str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7) . '<a href="#nofollow" rel="nofollow">will NOT be removed</a></div>', 'http://0.0.0.0');
         $readability->debug = true;
         $readability->lightClean = false;
         $res = $readability->init();
@@ -129,7 +155,7 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
     public function testWithIframe()
     {
-        $readability = new ReadabilityTested('<div><h2>Title</h2>'.str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7).'<p>This is an awesome text with some links, here there are <iframe src="http://youtube.com/test" href="#nofollow" rel="nofollow"></iframe><iframe>http://soundcloud.com/test</iframe></p></div>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<div><h2>Title</h2>' . str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7) . '<p>This is an awesome text with some links, here there are <iframe src="http://youtube.com/test" href="#nofollow" rel="nofollow"></iframe><iframe>http://soundcloud.com/test</iframe></p></div>', 'http://0.0.0.0');
         $readability->debug = true;
         $res = $readability->init();
 
@@ -144,7 +170,7 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
     public function testWithArticle()
     {
-        $readability = new ReadabilityTested('<article><p>'.str_repeat('This is an awesome text with some links, here there are: the awesome', 20).'</p><p>This is an awesome text with some links, here there are <iframe src="http://youtube.com/test" href="#nofollow" rel="nofollow"></iframe></p></article>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<article><p>' . str_repeat('This is an awesome text with some links, here there are: the awesome', 20) . '</p><p>This is an awesome text with some links, here there are <iframe src="http://youtube.com/test" href="#nofollow" rel="nofollow"></iframe></p></article>', 'http://0.0.0.0');
         $readability->debug = true;
         $res = $readability->init();
 
@@ -159,7 +185,22 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
     public function testWithAside()
     {
-        $readability = new ReadabilityTested('<article>'.str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7).'<footer><aside>'.str_repeat('<p>This is an awesome text with some links, here there are</p>', 8).'</aside></footer></article>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<article>' . str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7) . '<footer><aside>' . str_repeat('<p>This is an awesome text with some links, here there are</p>', 8) . '</aside></footer></article>', 'http://0.0.0.0');
+        $readability->debug = true;
+        $res = $readability->init();
+
+        $this->assertTrue($res);
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
+        $this->assertEmpty($readability->getTitle()->innerHTML);
+        $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
+        $this->assertNotContains('<aside>', $readability->getContent()->innerHTML);
+        $this->assertContains('<footer readability="4"/>', $readability->getContent()->innerHTML);
+    }
+
+    public function testWithClasses()
+    {
+        $readability = $this->getReadability('<article>' . str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7) . '<div style="display:none">' . str_repeat('<p class="clock">This text should be removed</p>', 10) . '</div></article>', 'http://0.0.0.0');
         $readability->debug = true;
         $res = $readability->init();
 
@@ -169,14 +210,14 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
         $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
         $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
-        $this->assertNotContains('<aside>', $readability->getContent()->innerHTML);
-        $this->assertContains('<footer/>', $readability->getContent()->innerHTML);
+        $this->assertNotContains('This text should be removed', $readability->getContent()->innerHTML);
     }
 
-    public function testWithClasses()
+    public function testWithClassesWithoutLightClean()
     {
-        $readability = new ReadabilityTested('<article>'.str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7).'<div style="display:none">'.str_repeat('<p class="clock">This text should be removed</p>', 10).'</div></article>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<article>' . str_repeat('<p>This is an awesome text with some links, here there are: <a href="http://0.0.0.0/test.html">the awesome</a></p>', 7) . '<div style="display:none">' . str_repeat('<p class="clock">This text should be removed</p>', 10) . '</div></article>', 'http://0.0.0.0');
         $readability->debug = true;
+        $readability->lightClean = false;
         $res = $readability->init();
 
         $this->assertTrue($res);
@@ -190,28 +231,26 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
     public function testWithTd()
     {
-        $readability = new ReadabilityTested('<table><tr>'.str_repeat('<td><p>This is an awesome text with some links, here there are the awesome</td>', 7).'</tr></table>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<table><tr>' . str_repeat('<td><p>This is an awesome text with some links, here there are the awesome</td>', 7) . '</tr></table>', 'http://0.0.0.0');
         $readability->debug = true;
         $res = $readability->init();
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
-        $this->assertContains('alt="tr"', $readability->getContent()->innerHTML);
         $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
     }
 
     public function testWithSameClasses()
     {
-        $readability = new ReadabilityTested('<article class="awesomecontent">'.str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7).'<div class="awesomecontent">This text is also an awesome text and you should know that !</div></article>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<article class="awesomecontent">' . str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7) . '<div class="awesomecontent">This text is also an awesome text and you should know that !</div></article>', 'http://0.0.0.0');
         $readability->debug = true;
         $res = $readability->init();
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
-        $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
         $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
         $this->assertContains('This text is also an awesome text and you should know that', $readability->getContent()->innerHTML);
@@ -219,14 +258,13 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
     public function testWithScript()
     {
-        $readability = new ReadabilityTested('<article class="awesomecontent">'.str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7).'<p><script>This text is also an awesome text and you should know that !</script></p></article>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<article class="awesomecontent">' . str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7) . '<p><script>This text is also an awesome text and you should know that !</script></p></article>', 'http://0.0.0.0');
         $readability->debug = true;
         $res = $readability->init();
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
-        $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
         $this->assertEmpty($readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
         $this->assertNotContains('This text is also an awesome text and you should know that', $readability->getContent()->innerHTML);
@@ -234,14 +272,13 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
     public function testTitle()
     {
-        $readability = new ReadabilityTested('<title>this is my title</title><article class="awesomecontent">'.str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7).'<p></p></article>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<title>this is my title</title><article class="awesomecontent">' . str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7) . '<p></p></article>', 'http://0.0.0.0');
         $readability->debug = true;
         $res = $readability->init();
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
-        $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
         $this->assertEquals('this is my title', $readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
         $this->assertNotContains('This text is also an awesome text and you should know that', $readability->getContent()->innerHTML);
@@ -249,14 +286,13 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
     public function testTitleWithDash()
     {
-        $readability = new ReadabilityTested('<title> title2 - title3 </title><article class="awesomecontent">'.str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7).'<p></p></article>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<title> title2 - title3 </title><article class="awesomecontent">' . str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7) . '<p></p></article>', 'http://0.0.0.0');
         $readability->debug = true;
         $res = $readability->init();
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
-        $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
         $this->assertEquals('title2 - title3', $readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
         $this->assertNotContains('This text is also an awesome text and you should know that', $readability->getContent()->innerHTML);
@@ -264,14 +300,13 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
     public function testTitleWithDoubleDot()
     {
-        $readability = new ReadabilityTested('<title> title2 : title3 </title><article class="awesomecontent">'.str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7).'<p></p></article>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<title> title2 : title3 </title><article class="awesomecontent">' . str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7) . '<p></p></article>', 'http://0.0.0.0');
         $readability->debug = true;
         $res = $readability->init();
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
-        $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
         $this->assertEquals('title2 : title3', $readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
         $this->assertNotContains('This text is also an awesome text and you should know that', $readability->getContent()->innerHTML);
@@ -279,14 +314,13 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
     public function testTitleTooShortUseH1()
     {
-        $readability = new ReadabilityTested('<title>too short</title><h1>this is my h1 title !</h1><article class="awesomecontent">'.str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7).'<p></p></article>', 'http://0.0.0.0');
+        $readability = $this->getReadability('<title>too short</title><h1>this is my h1 title !</h1><article class="awesomecontent">' . str_repeat('<p>This is an awesome text with some links, here there are the awesome</p>', 7) . '<p></p></article>', 'http://0.0.0.0');
         $readability->debug = true;
         $res = $readability->init();
 
         $this->assertTrue($res);
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
         $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
-        $this->assertContains('alt="article"', $readability->getContent()->innerHTML);
         $this->assertEquals('this is my h1 title !', $readability->getTitle()->innerHTML);
         $this->assertContains('This is an awesome text with some links, here there are', $readability->getContent()->innerHTML);
         $this->assertNotContains('This text is also an awesome text and you should know that', $readability->getContent()->innerHTML);
@@ -294,13 +328,9 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
 
     // public function testConstructParser()
     // {
-    //     $readability = new ReadabilityTested('<html/>', 'http://0.0.0.0', 'html5lib');
+    //     $readability = $this->getReadability('<html/>', 'http://0.0.0.0', 'html5lib');
 
     //     $this->assertEquals('http://0.0.0.0', $readability->url);
-    //     $this->assertContains('Parsing URL', $readability->getDebugText());
-    //     $this->assertContains('Tidying document', $readability->getDebugText());
-    //     $this->assertEquals('/0\.0\.0\.0/', $readability->getDomainRegexp());
-    //     $this->assertInstanceOf('DomDocument', $readability->dom);
     // }
 
     // dummy function to be used to the next test
@@ -340,7 +370,7 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
             </body>
             </html>';
 
-        $readability = new ReadabilityTested($data, 'http://iosgames.ru/?p=22030');
+        $readability = $this->getReadability($data, 'http://iosgames.ru/?p=22030');
         $readability->debug = true;
 
         $res = $readability->init();
@@ -351,4 +381,100 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase
         $this->assertContains('<iframe src="https://www.youtube.com/embed/PUep6xNeKjA" width="560" height="315" frameborder="0" allowfullscreen="allowfullscreen"> </iframe>', $readability->getContent()->innerHTML);
         $this->assertContains('3D Touch', $readability->getTitle()->innerHTML);
     }
+
+    /**
+     * This should generate an Exception "DOMElement::setAttribute(): ID post-60 already defined".
+     */
+    public function testAppendIdAlreadyHere()
+    {
+        $data = '<!DOCTYPE html>
+            <html lang="fr">
+            <head>
+                <meta charset="utf-8">
+                <meta name="viewport" content="width=device-width, user-scalable=yes, initial-scale=1.0">
+            </head>
+            <body>
+                <div class="container">
+                    <header class="header sml-text-center med-text-left" role="banner">
+                        <h1 class="no-margin"><a class="maintitle" href="https://0.0.0.0" title="Bloc-notes">Bloc-notes</a></h1>
+                        <h2 class="h5 no-margin"></h2>
+                    </header>
+
+                    <nav class="nav" role="navigation">
+                        <div class="responsive-menu">
+                            <label for="menu">Menu</label>
+                            <input type="checkbox" id="menu">
+                        </div>
+                    </nav>
+
+                    <article class="article" role="article" id="post-60">
+                        <section>
+                            This is an awesome text with some links, here there are<br/>
+                            This is an awesome text with some links, here there are<br/>
+                            This is an awesome text with some links, here there are<br/>
+                            This is an awesome text with some links, here there are<br/>
+                            This is an awesome text with some links, here there are<br/>
+                            This is an awesome text with some links, here there are<br/>
+                            This is an awesome text with some links, here there are<br/>
+                            This is an awesome text with some links, here there are<br/>
+                            This is an awesome text with some links, here there are<br/>
+                            This is an awesome text with some links, here there are<br/>
+                            This is an awesome text with some links, here there are
+                        </section>
+                        <footer>
+                            <small>
+                                Classé dans : <a class="noactive" title="Services réseaux">Services réseaux</a>
+                            </small>
+                        </footer>
+                    </article>
+                </div>
+            </body>
+            </html>';
+
+        $readability = $this->getReadability($data, 'http://0.0.0.0');
+        $readability->debug = true;
+
+        $res = $readability->init();
+
+        $this->assertTrue($res);
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getContent());
+        $this->assertInstanceOf('Readability\JSLikeHTMLElement', $readability->getTitle());
+    }
+
+    public function testPostFilters()
+    {
+        $readability = $this->getReadability('<div>' . str_repeat('<p>This <b>is</b> the awesome content :)</p>', 7) . '</div>', 'http://0.0.0.0');
+        $readability->addPostFilter('!<strong[^>]*>(.*?)</strong>!is', '');
+
+        $res = $readability->init();
+
+        $this->assertTrue($res);
+        $this->assertContains('This  the awesome content :)', $readability->getContent()->innerHTML);
+    }
+
+    public function testPreFilters()
+    {
+        $this->markTestSkipped('Won\'t work until loadHtml() is moved in init() instead of __construct()');
+
+        $readability = $this->getReadability('<div>' . str_repeat('<p>This <b>is</b> the awesome and WONDERFUL content :)</p>', 7) . '</div>', 'http://0.0.0.0');
+        $readability->addPreFilter('!<b[^>]*>(.*?)</b>!is', '');
+
+        $res = $readability->init();
+
+        $this->assertTrue($res);
+        $this->assertContains('This the awesome and WONDERFUL content :)', $readability->getContent()->innerHTML);
+    }
+
+    public function testChildNodeGoneNull()
+    {
+        // from http://www.ayyaantuu.net/ethiopia-targets-opposition-lawmakers/
+        $html = file_get_contents('tests/fixtures/childNodeGoesNull.html');
+
+        $readability = $this->getReadability($html, 'http://0.0.0.0');
+        $readability->debug = true;
+        $readability->convertLinksToFootnotes = true;
+        $res = $readability->init();
+
+        $this->assertTrue($res);
+    }
 }

tests/fixtures/childNodeGoesNull.html

@@ -0,0 +1,137 @@
+<div id="main-sidebar-container">
+
+            <!-- #main Starts -->
+                        <section id="main">
+<?php if (function_exists ('adinserter')) echo adinserter (1); ?><article class="post-23842 post type-post status-publish format-standard hentry category-ethiopia">
+    <header>
+    <h1 class="title entry-title">Ethiopia targets opposition who met with European lawmakers</h1>  </header>
+<div class="post-meta"><span class="Small"><abbr class="date time published updated" title="2017-01-09T15:25:17-0500">January 9, 2017</abbr>  <span class="Small">in</span> <span class="categories"><a href="http://www.ayyaantuu.net/category/horn-of-africa/ethiopia/" title="View all items in Ethiopia">Ethiopia</a></span>  </div>
+    <section class="entry">
+<div id="fb-root"></div>
+<p><strong>Ethiopia targets opposition who met with European lawmakers</strong></p>
+<p><span class="dateline"><img class="alignleft wp-image-22789 size-full" src="http://www.ayyaantuu.net/wp-content/uploads/2016/12/Ana-Gomes-Merera-Gudina.jpg" alt="Ethiopia targets opposition who met with European lawmakers" width="300" height="160" srcset="http://www.ayyaantuu.net/wp-content/uploads/2016/12/Ana-Gomes-Merera-Gudina.jpg 300w, http://www.ayyaantuu.net/wp-content/uploads/2016/12/Ana-Gomes-Merera-Gudina-200x107.jpg 200w" sizes="(max-width: 300px) 100vw, 300px" />ADDIS ABABA (<a href="http://www.foxnews.com/world/2017/01/09/ethiopia-targets-opposition-who-met-with-european-lawmakers.html">Fox News</a>)  –  </span>Ethiopia says it will not release a leading opposition figure detained under the country’s state of emergency after meeting with European lawmakers in Belgium.</p>
+<!-- WP QUADS Content Ad Plugin v. 1.3.9 -->
+<div class="quads-location quads-ad2" id="quads-ad2" style="float:left;margin:2px 2px 2px 0;">
+<script async src="//pagead2.googlesyndication.com/pagead/js/adsbygoogle.js"></script>
+<!-- Ad2016_12_14_3 -->
+<ins class="adsbygoogle"
+     style="display:inline-block;width:336px;height:280px"
+     data-ad-client="ca-pub-6953193962442323"
+     data-ad-slot="4950645476"></ins>
+<script>
+(adsbygoogle = window.adsbygoogle || []).push({});
+</script>
+</div>
+
+<p>Prime Minister Hailemariam Desalegn told reporters on Monday that Merara Gudina of the Oromo Federalist Congress party instead will face justice.</p>
+<p>The prime minister says “individuals in the European Parliament who are harboring anti-peace elements cannot save those who trespass the law of the country.”</p>
+<p>Merara is one of 22,000 people the prime minister says were detained under the state of emergency declared in October after widespread anti-government protests.</p>
+<p>Merara was arrested immediately after he returned from Belgium. He was accused of meeting with members of an armed Ethiopian opposition group in Brussels, an act banned under the emergency law.</p>
+
+<div style="font-size:0px;height:0px;line-height:0px;margin:0;padding:0;clear:both"></div><aside class="mashsb-container mashsb-main "><div class="mashsb-box"><div class="mashsb-count mash-small" style="float:left;"><div class="counts mashsbcount">0</div><span class="mashsb-sharetext">SHARES</span></div><div class="mashsb-buttons"><a  class="mashicon-facebook mash-small" href="http://www.facebook.com/sharer.php?u=http%3A%2F%2Fwww.ayyaantuu.net%2Fethiopia-targets-opposition-lawmakers%2F" target="_blank" rel="nofollow"><span class="icon"></span><span class="text">Share</span></a><a  class="mashicon-twitter mash-small" href="https://twitter.com/intent/tweet?text=Ethiopia%20targets%20opposition%20who%20met%20with%20European%20lawmakers&url=http://www.ayyaantuu.net/?p=23842&via= ayyaantuu" target="_blank" rel="nofollow"><span class="icon"></span><span class="text">Tweet</span></a><div class="onoffswitch mash-small"></div><div class="secondary-shares" style="display:none;"><a  class="mashicon-subscribe mash-small" href="#" target="_blank" rel="nofollow"><span class="icon"></span><span class="text">Subscribe</span></a><div class="onoffswitch2 mash-small" style="display:none;"></div></div></div>
+            </div>
+                <div style="clear:both;"></div><div class="mashsb-toggle-container"></div></aside>
+            <!-- Share buttons by mashshare.net - Version: 3.3.6--> </section><!-- /.entry -->
+    <div class="fix"></div>
+        <aside id="connect">
+        <h3>Subscribe</h3>
+
+        <div class="col-left">
+            <p>Subscribe to our e-mail newsletter to receive updates.</p>
+
+
+
+                        <div class="social">
+                                <a href="http://www.ayyaantuu.net/feed/" class="subscribe" title="RSS"></a>
+
+                                <a target="_blank" href="https://twitter.com/ayyaantuu" class="twitter" title="Twitter"></a>
+
+                                <a target="_blank" href="https://www.facebook.com/ayyaantuu.oromiyaa" class="facebook" title="Facebook"></a>
+
+                            </div>
+
+        </div><!-- col-left -->
+
+                <div class="related-posts col-right">
+            <h4>Related Posts:</h4>
+            <div class="woo-sc-related-posts">
+<ul>
+<li class="post-id-23812">
+
+<a href="http://www.ayyaantuu.net/country-new-african-millionaire/" title="Africa Business: The life of TPLF millionaire in Oromia/Ethiopia?" class="related-title"><span>Africa Business: The life of TPLF millionaire in Oromia/Ethiopia?</span></a>
+</li>
+<li class="post-id-23794">
+
+<a href="http://www.ayyaantuu.net/ethiopian-girl-band-funding-axed-uk/" title="Ethiopian girl band Yegna&#8217;s funding axed by UK &#8211; BBC News" class="related-title"><span>Ethiopian girl band Yegna&#8217;s funding axed by UK &#8211; BBC News</span></a>
+</li>
+<li class="post-id-23783">
+
+<a href="http://www.ayyaantuu.net/infrastructure-led-chinese-approach/" title="Ethiopia’s political ripple a big test for infrastructure-led Chinese approach" class="related-title"><span>Ethiopia’s political ripple a big test for infrastructure-led Chinese approach</span></a>
+</li>
+<li class="post-id-23766">
+
+<a href="http://www.ayyaantuu.net/defense-witness-testimonials/" title="Defense Witness Testimonials on Yonatan Tesfaye’s Terrorism Charges" class="related-title"><span>Defense Witness Testimonials on Yonatan Tesfaye’s Terrorism Charges</span></a>
+</li>
+<li class="post-id-23745">
+
+<a href="http://www.ayyaantuu.net/foreign-government-internet-shutdowns-soared-2016/" title="Foreign government internet shutdowns soared in 2016" class="related-title"><span>Foreign government internet shutdowns soared in 2016</span></a>
+</li>
+</ul>
+<div class="fix"></div><!--/.fix-->
+</div><!--/.woo-sc-related-posts-->     </div><!-- col-right -->
+
+        <div class="fix"></div>
+    </aside>
+    <div class="post-utility"></div>
+</article><!-- /.post -->
+            <div class="post-entries">
+                <div class="nav-prev fl"><a href="http://www.ayyaantuu.net/many-bombs-united-states-dropped-2016/" rel="prev"><i class="fa fa-angle-left"></i> How Many Bombs the United States Dropped in 2016?</a></div>
+                <div class="nav-next fr"><a href="http://www.ayyaantuu.net/rockefeller-conspiracy-one-world-order/" rel="next">David Rockefeller Says Conspiracy About ‘One World Order’ Is True <i class="fa fa-angle-right"></i></a></div>
+                <div class="fix"></div>
+            </div>
+
+        <?php if (function_exists ('adinserter')) echo adinserter (1); ?><div id="comments">            <h3 id="comments-title">One Response to <em>Ethiopia targets opposition who met with European lawmakers</em></h3>
+            <ol class="commentlist">
+
+        <li id="comment-30772" class="comment even thread-even depth-1">
+
+            <div id="li-comment-30772" class="comment-container">
+
+                                    <div class="avatar"></div>
+
+                <div class="comment-head">
+
+                    <span class="name">Addis Zemen</span>
+                    <span class="date">January 9, 2017 at 5:57 pm</span>
+                    <span class="perma"><a href="http://www.ayyaantuu.net/ethiopia-targets-opposition-lawmakers/#comment-30772" title="Direct link to this comment">#</a></span>
+                    <span class="edit"></span>
+
+                </div><!-- /.comment-head -->
+
+                <div class="comment-entry">
+
+                <p>10,000 people that were areested in Oromia got released. When the people were arrested it was under the assumption “Violence broke out during an Oromo religious festival, and in some instances foreigners seem to have been targeted. ”</p>
+<p>But now many prosecutors agree Violence was not the case. The people at the Erecha celebration thought aliens invaded their country. They thought the foreigners were aliens from another planet.<br />
+Close to a thousand threw themselves of a cliff just because they saw a helicopter flying near them. Many are paralized hundreds died. Now the injured are trying to blame the helicopter pilot for their injuries by saying the pilot caused their injuries by scaring them, flying like an alien abductor UFO would . After the prosecutor agreed it was an accident or suicide that caused the deaths of hundreds of people at the Erecha celebration, the suspected 10,000 prisoners got released. The prosecutors are blaming those that spoke with the European parliament for spreading false information about what really happened at the Erecha celebration.</p>
+
+
+                    <div class="reply">
+                        <a rel='nofollow' class='comment-reply-link' href='http://www.ayyaantuu.net/ethiopia-targets-opposition-lawmakers/?replytocom=30772#respond' onclick='return addComment.moveForm( "comment-30772", "30772", "respond", "23842" )' aria-label='Reply to Addis Zemen'>Reply</a>                   </div><!-- /.reply -->
+
+                </div><!-- /comment-entry -->
+
+            </div><!-- /.comment-container -->
+
+    </li><!-- #comment-## -->
+            </ol>
+            </div>  <div id="respond" class="comment-respond">
+        <h3 id="reply-title" class="comment-reply-title">Leave a Reply <small><a rel="nofollow" id="cancel-comment-reply-link" href="/ethiopia-targets-opposition-lawmakers/#respond" style="display:none;">Click here to cancel reply.</a></small></h3>            <form action="http://www.ayyaantuu.net/wp-comments-post.php" method="post" id="commentform" class="comment-form">
+                <p class="comment-form-comment"><label class="hide" for="comment">Comment</label> <textarea tabindex="4" id="comment" name="comment" cols="50" rows="10" maxlength="65525" aria-required="true" required="required"></textarea></p><p class="comment-form-author"><input id="author" name="author" type="text" class="txt" tabindex="1" value="" size="30" aria-required='true' /><label for="author">Name <span class="required">(required)</span></label> </p>
+<p class="comment-form-email"><input id="email" name="email" type="text" class="txt" tabindex="2" value="" size="30" aria-required='true' /><label for="email">Email (will not be published) <span class="required">(required)</span></label> </p>
+<p class="comment-form-url"><input id="url" name="url" type="text" class="txt" tabindex="3" value="" size="30" /><label for="url">Website</label></p>
+<p class="form-submit"><input name="submit" type="submit" id="submit" class="submit" value="Submit Comment" /> <input type='hidden' name='comment_post_ID' value='23842' id='comment_post_ID' />
+<input type='hidden' name='comment_parent' id='comment_parent' value='0' />
+</p><p style="display: none;"><input type="hidden" id="akismet_comment_nonce" name="akismet_comment_nonce" value="39bacbf69e" /></p><p style="display: none;"><input type="hidden" id="ak_js" name="ak_js" value="66"/></p>         </form>
+            </div><!-- #respond -->
+
+            </section><!-- /#main -->