Skip to content

Use DOMDocument for returning <body> HTML #102

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
Sep 17, 2025
Merged

Use DOMDocument for returning <body> HTML #102

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
046263c
Use DOMDocument for fetching HTML within body
n7studios Sep 9, 2025
8b9e3e4
Merge branch 'main' into use-domdocument-body-html
n7studios Sep 15, 2025
f1253ce
Merge branch 'main' into use-domdocument-body-html
n7studios Sep 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 25 additions & 0 deletions src/class-convertkit-api-traits.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1773,6 +1773,9 @@ public function convert_script_type(\DOMNodeList $elements)
*/
public function strip_html_head_body_tags(string $markup)
{
// Mark as deprecated in 2.1.0.
_deprecated_function( __FUNCTION__, '2.1.0', 'get_body_html()' );

$markup = str_replace('<html>', '', $markup);
$markup = str_replace('</html>', '', $markup);
$markup = str_replace('<head>', '', $markup);
Expand All @@ -1784,6 +1787,28 @@ public function strip_html_head_body_tags(string $markup)
return $markup;
}

/**
* Returns the HTML within the DOMDocument's <body> tag as a string.
*
* @param \DOMDocument $dom DOM Document.
*
* @since 2.1.0
*
* @return string
*/
public function get_body_html(\DOMDocument $dom) {

$body = $dom->getElementsByTagName( 'body' )->item( 0 );

$html = '';
foreach ( $body->childNodes as $child ) { // phpcs:ignore WordPress.NamingConventions.ValidVariableName.UsedPropertyNotSnakeCase
$html .= $dom->saveHTML( $child );
}

return $html;

}

/**
* Adds total count and pagination parameters to the given array of existing API parameters.
*
Expand Down
6 changes: 2 additions & 4 deletions src/class-convertkit-api-v4.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1251,10 +1251,8 @@ public function get_html( $url, $body_only = true ) {
return $html->saveHTML();
}

// Remove some HTML tags that DOMDocument adds, returning the output.
// We do this instead of using LIBXML_HTML_NOIMPLIED in loadHTML(), because Legacy Forms are not always contained in
// a single root / outer element, which is required for LIBXML_HTML_NOIMPLIED to correctly work.
return $this->strip_html_head_body_tags( $html->saveHTML() );
// Return the HTML within the DOMDocument's <body> tag as a string.
return $this->get_body_html( $html );

}

Expand Down