559342-9607/laravel-cision-feed
1
0 Fork 0
Code Issues Pull Requests Actions 10 Packages Projects Releases 6 Wiki Activity

2.0 #1

Merged
mathiaspalmqvist merged 10 commits from 2.0 into main 2025-07-04 19:22:40 +00:00
Conversation 0 Commits 10 Files Changed 32
+8 -23
1 changed files with 8 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 0c54185f1f - Show all commits
src/Support/HtmlCleaner.php
+8 -23
View File
@@ -9,7 +9,7 @@ use DOMElement;
class HtmlCleaner
{
/**
* Render a DOM node into safe HTML, preserving allowed block and inline tags.
* Renders a DOM node into safe HTML, preserving only allowed tags.
*/
public static function renderNode(DOMNode $node, array $allowedTags, array $allowedInline, string $parentTag = ''): ?string
{
@@ -23,7 +23,6 @@ class HtmlCleaner
$tag = $node->nodeName;
// Special case: handle <br> within <p>
if ($tag === 'br') {
if ($parentTag === 'p') {
$prev = $node->previousSibling;
@@ -36,13 +35,11 @@ class HtmlCleaner
return '<br>';
}
}
// Skip all other <br>
return null;
}
// Recursively render children
$inner = '';
foreach ($node->childNodes as $child) {
$rendered = self::renderNode($child, $allowedTags, $allowedInline, $tag);
if ($rendered !== null) {
@@ -50,7 +47,6 @@ class HtmlCleaner
}
}
// Handle block tags
if (in_array($tag, $allowedTags)) {
if ($tag === 'p') {
$html = $node->C14N();
@@ -58,31 +54,24 @@ class HtmlCleaner
$class = $isItalic ? ' class="italic"' : '';
return "<p{$class}>" . trim($inner) . "</p>";
}
return "<{$tag}>" . trim($inner) . "</{$tag}>";
}
// Handle inline tags
if (in_array($tag, $allowedInline)) {
return "<{$tag}>{$inner}</{$tag}>";
}
// Unknown tags are ignored but their content is preserved
return $inner;
}
/**
* Clean a raw HTML string: remove unwanted tags, empty elements, garbage phrases, and excessive whitespace.
* Cleans a raw HTML string: removes unwanted content, empty tags, and excess whitespace.
*/
public static function clean(string $html): string
{
// Remove first <h1>
$html = preg_replace('/<h1\b[^>]*>.*?<\/h1>/i', '', $html, 1);
// Remove empty tags like <i></i>, <span></span>
$html = preg_replace('/<(\w+)[^>]*>\s*<\/\1>/', '', $html);
// Remove specific garbage strings
$unwantedStrings = [
'Report this content',
'<p><strong>Taggar:</strong></p>',
@@ -92,16 +81,12 @@ class HtmlCleaner
$html = str_replace($str, '', $html);
}
// Remove localized date lines like: fre, jul 04, 2025 09:55 CET
$html = preg_replace('/\b[a-z]{3},\s[a-z]{3}\s\d{2},\s\d{4}\s\d{2}:\d{2}\sCET\b/i', '', $html);
$html = str_replace(["\u{A0}", "\t", "\r"], ' ', $html);
$html = preg_replace('/[ ]{2,}/', ' ', $html);
$html = preg_replace("/(\n\s*){2,}/", "\n", $html);
$html = str_replace([' ', ' \n'], '', $html);
// Normalize whitespace
$html = str_replace(["\u{A0}", "\t", "\r"], ' ', $html); // Remove non-breaking spaces and tabs
$html = preg_replace('/[ ]{2,}/', ' ', $html); // Collapse double spaces
$html = preg_replace("/(\n\s*){2,}/", "\n", $html); // Collapse multiple newlines
$html = str_replace([' ', ' \n'], '', $html); // Additional spacing clean
$html = trim($html);
return $html;
return trim($html);
}
}