diff options
author | alecpl <alec@alec.pl> | 2008-06-03 17:07:53 +0000 |
---|---|---|
committer | alecpl <alec@alec.pl> | 2008-06-03 17:07:53 +0000 |
commit | 68217c548a024f3f7d7d667ce4b825cf61ae46a9 (patch) | |
tree | 75b2e9b75c70531f3215a3a4bea1bed8ba9ef144 /program | |
parent | 02548b976c092f0e2b8680627adbc04303ff5d67 (diff) |
-add convert encoding before html parsing
Diffstat (limited to 'program')
-rw-r--r-- | program/lib/washtml.php | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/program/lib/washtml.php b/program/lib/washtml.php index 82ccc0cd5..f45fd458a 100644 --- a/program/lib/washtml.php +++ b/program/lib/washtml.php @@ -187,6 +187,7 @@ class washtml //Charset seems to be ignored (probably if defined in the HTML document) $node = new DOMDocument('1.0', $config['charset']); $full = true; + $html = mb_convert_encoding($html, 'HTML-ENTITIES', 'UTF-8'); @$node->loadHTML($html); return self::dumpHtml($node, $config, $full); } |