From 76b04ddaf225a154056f5a2c4eb6b0f5b5abcbde Mon Sep 17 00:00:00 2001
From: "itdrui.de" <view@it-drui.de>
Date: Tue, 24 Feb 2026 18:50:31 +0100
Subject: [PATCH] dev: normalize filter.genre_* labels in genre parsing

---
 addon/plugins/aniworld_plugin.py     | 26 ++++++++++++++--
 addon/plugins/serienstream_plugin.py | 46 ++++++++++++++++++++++++++--
 2 files changed, 68 insertions(+), 4 deletions(-)

diff --git a/addon/plugins/aniworld_plugin.py b/addon/plugins/aniworld_plugin.py
index 943e865..03f85da 100644
--- a/addon/plugins/aniworld_plugin.py
+++ b/addon/plugins/aniworld_plugin.py
@@ -357,6 +357,28 @@ def _get_soup_simple(url: str) -> BeautifulSoupT:
     return BeautifulSoup(body, "html.parser")
 
 
+def _normalize_genre_label(raw: str) -> str:
+    text = unescape(re.sub(r"\s+", " ", str(raw or ""))).strip()
+    if not text:
+        return ""
+    key_prefix = "filter.genre_"
+    if text.casefold().startswith(key_prefix):
+        slug = text[len(key_prefix) :].strip().casefold()
+        slug = slug.replace("_", "-")
+        slug = re.sub(r"[^a-z0-9-]+", "-", slug).strip("-")
+        if not slug:
+            return ""
+        special = {
+            "doku-soap": "Doku-Soap",
+            "scifi": "SciFi",
+            "fighting-shounen": "Fighting-Shounen",
+        }
+        if slug in special:
+            return special[slug]
+        return " ".join(chunk.capitalize() for chunk in slug.split("-") if chunk)
+    return text
+
+
 def _extract_genre_names_from_html(body: str) -> List[str]:
     names: List[str] = []
     seen: set[str] = set()
@@ -366,7 +388,7 @@ def _extract_genre_names_from_html(body: str) -> List[str]:
     )
     for match in pattern.finditer(body or ""):
         text = re.sub(r"<[^>]+>", " ", match.group(1) or "")
-        text = unescape(re.sub(r"\s+", " ", text)).strip()
+        text = _normalize_genre_label(text)
         if not text:
             continue
         key = text.casefold()
@@ -1193,7 +1215,7 @@ class AniworldPlugin(BasisPlugin):
             genre_blocks = soup.select("div.genre")
         for genre_block in genre_blocks:
             name_node = genre_block.select_one(".seriesGenreList h3")
-            genre_name = (name_node.get_text(" ", strip=True) if name_node else "").strip()
+            genre_name = _normalize_genre_label(name_node.get_text(" ", strip=True) if name_node else "")
             if not genre_name:
                 continue
             entries: List[SeriesResult] = []
diff --git a/addon/plugins/serienstream_plugin.py b/addon/plugins/serienstream_plugin.py
index aebfe1b..8600b30 100644
--- a/addon/plugins/serienstream_plugin.py
+++ b/addon/plugins/serienstream_plugin.py
@@ -468,6 +468,27 @@ def _get_soup_simple(url: str) -> BeautifulSoupT:
 
 
 def _extract_genre_names_from_html(body: str) -> List[str]:
+    def _normalize_genre_label(raw: str) -> str:
+        text = unescape(re.sub(r"\s+", " ", str(raw or ""))).strip()
+        if not text:
+            return ""
+        key_prefix = "filter.genre_"
+        if text.casefold().startswith(key_prefix):
+            slug = text[len(key_prefix) :].strip().casefold()
+            slug = slug.replace("_", "-")
+            slug = re.sub(r"[^a-z0-9-]+", "-", slug).strip("-")
+            if not slug:
+                return ""
+            special = {
+                "doku-soap": "Doku-Soap",
+                "scifi": "SciFi",
+                "fighting-shounen": "Fighting-Shounen",
+            }
+            if slug in special:
+                return special[slug]
+            return " ".join(chunk.capitalize() for chunk in slug.split("-") if chunk)
+        return text
+
     names: List[str] = []
     seen: set[str] = set()
     pattern = re.compile(
@@ -476,7 +497,7 @@ def _extract_genre_names_from_html(body: str) -> List[str]:
     )
     for match in pattern.finditer(body or ""):
         text = re.sub(r"<[^>]+>", " ", match.group(1) or "")
-        text = unescape(re.sub(r"\s+", " ", text)).strip()
+        text = _normalize_genre_label(text)
         if not text:
             continue
         key = text.casefold()
@@ -726,11 +747,32 @@ def parse_series_catalog(soup: BeautifulSoupT) -> Dict[str, List[SeriesResult]]:
     """Parst die Serien-Übersicht (/serien) und liefert Genre -> Serienliste."""
     catalog: Dict[str, List[SeriesResult]] = {}
 
+    def _normalize_genre_label(raw: str) -> str:
+        text = re.sub(r"\s+", " ", str(raw or "")).strip()
+        if not text:
+            return ""
+        key_prefix = "filter.genre_"
+        if text.casefold().startswith(key_prefix):
+            slug = text[len(key_prefix) :].strip().casefold()
+            slug = slug.replace("_", "-")
+            slug = re.sub(r"[^a-z0-9-]+", "-", slug).strip("-")
+            if not slug:
+                return ""
+            special = {
+                "doku-soap": "Doku-Soap",
+                "scifi": "SciFi",
+                "fighting-shounen": "Fighting-Shounen",
+            }
+            if slug in special:
+                return special[slug]
+            return " ".join(chunk.capitalize() for chunk in slug.split("-") if chunk)
+        return text
+
     # Neues Layout (Stand: 2026-01): Gruppen-Header + Liste.
     # - Header: `div.background-1 ...` mit `h3`
     # - Einträge: `ul.series-list` -> `li.series-item[data-search]` -> `a[href]`
     for header in soup.select("div.background-1 h3"):
-        group = (header.get_text(strip=True) or "").strip()
+        group = _normalize_genre_label(header.get_text(strip=True))
         if not group:
             continue
         list_node = header.parent.find_next_sibling("ul", class_="series-list")