Skip to content

Commit 809cc68

Browse files
committed
cheerio: fix decode entities
1 parent 1447c6f commit 809cc68

2 files changed

Lines changed: 9 additions & 2 deletions

File tree

lib/plugins/system/cheerio.js

Lines changed: 7 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -17,7 +17,13 @@ export default {
1717
}
1818

1919
cb(null, {
20-
cheerio: cheerio.load(dom)
20+
cheerio: cheerio.load(dom, {
21+
// Routes $.html() through dom-serializer instead of renderWithParse5.
22+
// parse5's serializer hard-codes escaping of U+00A0 →   and ignores decodeEntities.
23+
_useHtmlParser2: true,
24+
// Fixes decoding html characters like   to UTF-8, we have own decoders.
25+
decodeEntities: false
26+
})
2127
});
2228
});
2329

lib/plugins/system/htmlparser/htmlparser.js

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -197,7 +197,8 @@ export default {
197197
};
198198
var parser = new Parser(handler, {
199199
lowerCaseTags: true,
200-
decodeEntities: false // Fixes decoding html characters like   to UTF-8, we have own decoders.
200+
// Fixes decoding html characters like   to UTF-8, we have own decoders.
201+
decodeEntities: false
201202
});
202203
handler.headers = headers;
203204
handler.abortController = abortController;

0 commit comments

Comments
 (0)