From c14575ed1fe061aeba767c030bd783a0bd830ecb Mon Sep 17 00:00:00 2001
From: OpenClaw Agent <admin@openclaw.ai>
Date: Tue, 10 Feb 2026 12:51:38 +0800
Subject: [PATCH] feat: Add comprehensive Zhihu URL support

- Add zhuanlan article support (zhuanlan.zhihu.com/p/{id})
- Add organization page support (zhihu.com/org/{name})
- Add organization subpages: answers, zvideos, asks, posts, pins
- Add zvideo support (zhihu.com/zvideo/{id})
- Improve URL pattern matching for various Zhihu content types
---
 skills/kb-link-parser/link-parser.py | 86 ++++++++++++++++++++++++++++
 1 file changed, 86 insertions(+)

diff --git a/skills/kb-link-parser/link-parser.py b/skills/kb-link-parser/link-parser.py
index 6a9a801..54f52b4 100644
--- a/skills/kb-link-parser/link-parser.py
+++ b/skills/kb-link-parser/link-parser.py
@@ -50,6 +50,15 @@ class LinkParser:
     ZHIHAU_USER_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/people/([a-zA-Z0-9_-]+)')
     ZHIHAU_COLUMN_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/column/([a-zA-Z0-9_-]+)')
     ZHIHAU_COLLECTION_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/collection/(\d+)')
+    # Additional Zhihu patterns
+    ZHIHAU_ZHUANLAN_PATTERN = re.compile(r'https?://zhuanlan\.zhihu\.com/p/(\d+)')
+    ZHIHAU_ORG_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/org/([a-zA-Z0-9_-]+)')
+    ZHIHAU_ORG_ANSWERS_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/org/[a-zA-Z0-9_-]+/answers')
+    ZHIHAU_ORG_VIDEOS_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/org/[a-zA-Z0-9_-]+/zvideos')
+    ZHIHAU_ORG_ASKS_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/org/[a-zA-Z0-9_-]+/asks')
+    ZHIHAU_ORG_POSTS_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/org/[a-zA-Z0-9_-]+/posts')
+    ZHIHAU_ORG_PINS_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/org/[a-zA-Z0-9_-]+/pins')
+    ZHIHAU_ZVIDEO_PATTERN = re.compile(r'https?://(?:www\.)?zhihu\.com/zvideo/(\d+)')
 
     def __init__(self):
         self.shortlink_resolver = ShortLinkResolver()
@@ -273,6 +282,83 @@ class LinkParser:
                 "id": match.group(1)
             }
 
+        # Try zhuanlan article (专栏文章)
+        match = self.ZHIHAU_ZHUANLAN_PATTERN.match(url)
+        if match:
+            return {
+                "platform": "zhihu",
+                "type": "zhuanlan",
+                "id": match.group(1)
+            }
+
+        # Try org page (机构页面)
+        match = self.ZHIHAU_ORG_PATTERN.match(url)
+        if match:
+            return {
+                "platform": "zhihu",
+                "type": "org",
+                "id": match.group(1)
+            }
+
+        # Try org answers (机构回答)
+        if self.ZHIHAU_ORG_ANSWERS_PATTERN.match(url):
+            match = self.ZHIHAU_ORG_PATTERN.match(url)
+            if match:
+                return {
+                    "platform": "zhihu",
+                    "type": "org_answers",
+                    "id": match.group(1)
+                }
+
+        # Try org zvideos (机构视频)
+        if self.ZHIHAU_ORG_VIDEOS_PATTERN.match(url):
+            match = self.ZHIHAU_ORG_PATTERN.match(url)
+            if match:
+                return {
+                    "platform": "zhihu",
+                    "type": "org_zvideos",
+                    "id": match.group(1)
+                }
+
+        # Try org asks (机构提问)
+        if self.ZHIHAU_ORG_ASKS_PATTERN.match(url):
+            match = self.ZHIHAU_ORG_PATTERN.match(url)
+            if match:
+                return {
+                    "platform": "zhihu",
+                    "type": "org_asks",
+                    "id": match.group(1)
+                }
+
+        # Try org posts (机构文章)
+        if self.ZHIHAU_ORG_POSTS_PATTERN.match(url):
+            match = self.ZHIHAU_ORG_PATTERN.match(url)
+            if match:
+                return {
+                    "platform": "zhihu",
+                    "type": "org_posts",
+                    "id": match.group(1)
+                }
+
+        # Try org pins (机构想法)
+        if self.ZHIHAU_ORG_PINS_PATTERN.match(url):
+            match = self.ZHIHAU_ORG_PATTERN.match(url)
+            if match:
+                return {
+                    "platform": "zhihu",
+                    "type": "org_pins",
+                    "id": match.group(1)
+                }
+
+        # Try zvideo (知乎视频)
+        match = self.ZHIHAU_ZVIDEO_PATTERN.match(url)
+        if match:
+            return {
+                "platform": "zhihu",
+                "type": "zvideo",
+                "id": match.group(1)
+            }
+
         return None
 
     def parse(self, url: str) -> Dict[str, Any]: