[naver] unescape post 'title' and 'description'

mikf · Mar 5, 2024 · f296067 · f296067
1 parent a71cdab
commit f296067
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 4 deletions.
diff --git a/gallery_dl/extractor/naver.py b/gallery_dl/extractor/naver.py
@@ -47,8 +47,10 @@ def metadata(self, page):
         extr = text.extract_from(page)
         data = {
             "post": {
-                "title"      : extr('"og:title" content="', '"'),
-                "description": extr('"og:description" content="', '"'),
+                "title"      : text.unescape(extr(
+                    '"og:title" content="', '"')),
+                "description": text.unescape(extr(
+                    '"og:description" content="', '"')).replace("&nbsp;", " "),
                 "num"        : text.parse_int(self.post_id),
             },
             "blog": {

diff --git a/test/results/naver.py b/test/results/naver.py
@@ -41,9 +41,9 @@
     },
     "post": {
         "date"       : "dt:2013-03-05 17:48:00",
-        "description": "&amp;nbsp;◈ &amp;nbsp; &amp;nbsp; PROMOTER&amp;nbsp;：핑수 ˚ 아담 EDITOR：핑수 &amp;nbsp; 넵：이크：핑수...",
+        "description": " ◈     PROMOTER ：핑수 ˚ 아담 EDITOR：핑수   넵：이크：핑수...",
         "num"        : 70161391809,
-        "title"      : "[공유] {&#8201;합작}&#8201; OH, MY GOD! ~ 아 또 무슨 종말을 한다 그래~"
+        "title"      : "[공유] { 합작}  OH, MY GOD! ~ 아 또 무슨 종말을 한다 그래~",
     },
     "count"    : 2,
     "num"      : range(1, 2),