infong/php-readability
1
0
Fork 0
mirror of https://github.com/j0k3r/php-readability.git synced 2026-09-27 06:26:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add routine to remove invisible nodes

Browse Source 
Readability was previously removing (was trying to actually, see next
section) invisible nodes using a pattern from `unlikelyCandidates`. This
was quite hacky and was removed during a backport of logics from
mozilla/readability. There is still a need to remove them so here we
are. We still use a pattern but specifically against the style
attribute. We also remove nodes with the attribute `hidden`.

The clean feature of tidy actually replaces inline style attributes
with css classes thus preventing readability to detect invisible nodes,
see https://github.com/htacg/tidy-html5/blob/5.6.0/src/clean.c#L1488
We therefore set clean configuration to false.

Signed-off-by: Kevin Decherf <kevin@kdecherf.com>
This commit is contained in:
Kevin Decherf
2022-02-04 01:23:11 +01:00
parent b580cf216d
commit a44c4e5482
2 changed files with 66 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/Readability.php
+24 -1
View File
@@ -55,6 +55,7 @@ class Readability implements LoggerAwareInterface
'media' => '!//(?:[^\.\?/]+\.)?(?:youtu(?:be)?|giphy|soundcloud|dailymotion|vimeo|pornhub|xvideos|twitvid|rutube|openload\.co|viddler)\.(?:com|be|org|net)/!i',
'skipFootnoteLink' => '/^\s*(\[?[a-z0-9]{1,2}\]?|^|edit|citation needed)\s*$/i',
'hasContent' => '/\S$/',
'isNotVisible' => '/display\s*:\s*none/',
];
public $defaultTagsToScore = ['section', 'h2', 'h3', 'h4', 'h5', 'h6', 'p', 'td', 'pre'];
// The commented out elements qualify as phrasing content but tend to be
@@ -74,7 +75,7 @@ class Readability implements LoggerAwareInterface
'numeric-entities' => false,
// 'preserve-entities' => true,
'break-before-br' => false,
'clean' => true,
'clean' => false,
'output-xhtml' => true,
'logical-emphasis' => true,
'show-body-only' => false,
@@ -922,6 +923,14 @@ class Readability implements LoggerAwareInterface
continue;
}
// Remove invisible nodes
if (!$this->isNodeVisible($node)) {
$this->logger->debug('Removing invisible node ' . $node->getNodePath());
$node->parentNode->removeChild($node);
--$nodeIndex;
continue;
}
// Remove unlikely candidates
$unlikelyMatchString = $node->getAttribute('class') . ' ' . $node->getAttribute('id') . ' ' . $node->getAttribute('style');
@@ -1474,4 +1483,18 @@ class Readability implements LoggerAwareInterface
return 0 === \count($a);
}
/**
* Return whether a given node is visible or not.
*
* Tidy must be configured to not clean the input for this function to
* work as expected, see $this->tidy_config['clean']
*/
private function isNodeVisible(\DOMElement $node): bool
{
return !($node->hasAttribute('style')
&& preg_match($this->regexps['isNotVisible'], $node->getAttribute('style'))
)
&& !$node->hasAttribute('hidden');
}
}