1
0
mirror of https://git.tt-rss.org/git/tt-rss.git synced 2025-12-13 00:05:56 +00:00

domdocument: remove old meta charset unicode hacks, replace with shorter xml preamble utf8 hack (on loadhtml where it makes sense)

af_readability: better (?) charset hack for non-unicode pages
This commit is contained in:
Andrew Dolgov
2019-03-21 21:08:02 +03:00
parent 3bd3324e5a
commit 671f4cee65
8 changed files with 15 additions and 46 deletions

View File

@@ -329,7 +329,7 @@ class Handler_Public extends Handler {
if (!$og_image) {
$tmpdoc = new DOMDocument();
if (@$tmpdoc->loadHTML(mb_substr($content, 0, 131070))) {
if (@$tmpdoc->loadHTML('<?xml encoding="UTF-8">' . mb_substr($content, 0, 131070))) {
$tmpxpath = new DOMXPath($tmpdoc);
$imgs = $tmpxpath->query("//img");