From 73f77a543a38cea3897cd3912e57849e477e9444 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Thu, 10 Oct 2024 14:06:47 +0200
Subject: [PATCH] [generic] ensure 'path' metadata is always defined

fixes None directory names when 'path' is empty and got removed
---
 gallery_dl/extractor/generic.py | 49 +++++++++++++++++----------------
 1 file changed, 26 insertions(+), 23 deletions(-)

diff --git a/gallery_dl/extractor/generic.py b/gallery_dl/extractor/generic.py
index a6c1d5ae..370cd433 100644
--- a/gallery_dl/extractor/generic.py
+++ b/gallery_dl/extractor/generic.py
@@ -89,30 +89,33 @@ class GenericExtractor(Extractor):
 
     def metadata(self, page):
         """Extract generic webpage metadata, return them in a dict."""
-        data = {}
-        data['path'] = self.path.replace("/", "")
-        data['pageurl'] = self.url
-        data['title'] = text.extr(page, '<title>', "</title>")
-        data['description'] = text.extr(
-            page, '<meta name="description" content="', '"')
-        data['keywords'] = text.extr(
-            page, '<meta name="keywords" content="', '"')
-        data['language'] = text.extr(
-            page, '<meta name="language" content="', '"')
-        data['name'] = text.extr(
-            page, '<meta itemprop="name" content="', '"')
-        data['copyright'] = text.extr(
-            page, '<meta name="copyright" content="', '"')
-        data['og_site'] = text.extr(
-            page, '<meta property="og:site" content="', '"')
-        data['og_site_name'] = text.extr(
-            page, '<meta property="og:site_name" content="', '"')
-        data['og_title'] = text.extr(
-            page, '<meta property="og:title" content="', '"')
-        data['og_description'] = text.extr(
-            page, '<meta property="og:description" content="', '"')
+        data = {
+            "title"         : text.extr(
+                page, "<title>", "</title>"),
+            "description"   : text.extr(
+                page, '<meta name="description" content="', '"'),
+            "keywords"      : text.extr(
+                page, '<meta name="keywords" content="', '"'),
+            "language"      : text.extr(
+                page, '<meta name="language" content="', '"'),
+            "name"          : text.extr(
+                page, '<meta itemprop="name" content="', '"'),
+            "copyright"     : text.extr(
+                page, '<meta name="copyright" content="', '"'),
+            "og_site"       : text.extr(
+                page, '<meta property="og:site" content="', '"'),
+            "og_site_name"  : text.extr(
+                page, '<meta property="og:site_name" content="', '"'),
+            "og_title"      : text.extr(
+                page, '<meta property="og:title" content="', '"'),
+            "og_description": text.extr(
+                page, '<meta property="og:description" content="', '"'),
 
-        data = {k: text.unescape(data[k]) for k in data if data[k] != ""}
+        }
+
+        data = {k: text.unescape(v) for k, v in data.items() if v}
+        data["path"] = self.path.replace("/", "")
+        data["pageurl"] = self.url
 
         return data