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

Do not set domainRegExp for local files

Browse Source 
`parse_url($this->url, \PHP_URL_HOST)` will return `null` for local filesystem path.
Casting it to `string` will produce an empty regular expression,
which would match any link when computing link density.
This commit is contained in:
Jan Tojnar
2025-03-03 23:26:30 +01:00
parent 4258559b8a
commit c7208f6ad2
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/Readability.php
+4 -1
View File
@@ -1383,7 +1383,10 @@ class Readability implements LoggerAwareInterface
$this->logger->debug('Parsing URL: ' . $this->url); $this->logger->debug('Parsing URL: ' . $this->url);
if ($this->url) { if ($this->url) {
$this->domainRegExp = '/' . strtr((string) preg_replace('/www\d*\./', '', (string) parse_url($this->url, \PHP_URL_HOST)), ['.' => '\.']) . '/'; $host = parse_url($this->url, \PHP_URL_HOST);
if (null !== $host) {
$this->domainRegExp = '/' . strtr((string) preg_replace('/www\d*\./', '', $host), ['.' => '\.']) . '/';
}
} }
mb_internal_encoding('UTF-8'); mb_internal_encoding('UTF-8');