diff options
| -rw-r--r-- | CHANGELOG.md | 1 | ||||
| -rw-r--r-- | src/Readability.php | 22 | ||||
| -rw-r--r-- | test/ReadabilityTest.php | 2 |
3 files changed, 17 insertions, 8 deletions
diff --git a/CHANGELOG.md b/CHANGELOG.md index d4d56dd..e0ceea1 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -7,6 +7,7 @@ All notable changes to this project will be documented in this file. - Added a safe check to avoid sending the DOMDocument as a node when scanning for node ancestors. - Fix issue #45: Small mistake in documentation - Fix issue #46: Added `data-src` as a image source path +- Fixed bug when extracting all the image of the article (Was extracting images from the original DOM instead of the parsed one) ## [v1.1.0](https://github.com/andreskrey/readability.php/releases/tag/v1.1.0) diff --git a/src/Readability.php b/src/Readability.php index 4695244..fc3eda6 100644 --- a/src/Readability.php +++ b/src/Readability.php @@ -29,9 +29,9 @@ class Readability protected $title = null; /** - * HTML content article. + * Final DOMDocument with the fully parsed HTML. * - * @var string|null + * @var DOMDocument|null */ protected $content = null; @@ -198,7 +198,7 @@ class Readability } } - $this->setContent($result->C14N()); + $this->setContent($result); $this->logger->info('*** Parse successful :)'); @@ -348,11 +348,11 @@ class Readability $result[] = $this->getImage(); } - if (null == $this->dom) { + if (null == $this->getContentObject()) { return $result; } - foreach ($this->dom->getElementsByTagName('img') as $img) { + foreach ($this->getContentObject()->getElementsByTagName('img') as $img) { if ($src = $img->getAttribute('src')) { $result[] = $src; } @@ -1564,13 +1564,21 @@ class Readability */ public function getContent() { + return $this->content->C14N(); + } + + /** + * @return DOMDocument|null + */ + public function getContentObject() + { return $this->content; } /** - * @param string $content + * @param DOMDocument $content */ - protected function setContent($content) + protected function setContent(DOMDocument $content) { $this->content = $content; } diff --git a/test/ReadabilityTest.php b/test/ReadabilityTest.php index d4c0a18..fe17b23 100644 --- a/test/ReadabilityTest.php +++ b/test/ReadabilityTest.php @@ -41,7 +41,7 @@ class ReadabilityTest extends \PHPUnit_Framework_TestCase foreach ($expectedMetadata as $key => $metadata) { $function = 'get' . $key; - $this->assertEquals($metadata, $readability->$function()); + $this->assertEquals($metadata, $readability->$function(), sprintf('Failed asserting %s metadata', $key)); } } |