From 76f564ae83f9c47ebcf0e75b0b41d17039d62fbd Mon Sep 17 00:00:00 2001
From: Remora <remora@dilain.com>
Date: Mon, 9 Feb 2026 19:29:07 +0100
Subject: [PATCH] Fix: Clean GitHub README markdown properly (remove images,
 code, links)

---
 bot.py | 41 ++++++++++++++++++++++++++++++-----------
 1 file changed, 30 insertions(+), 11 deletions(-)

diff --git a/bot.py b/bot.py
index 4aff5ca..46ca311 100644
--- a/bot.py
+++ b/bot.py
@@ -162,14 +162,15 @@ def get_github_content(url):
     """Fetch GitHub repo README via API"""
     logger.debug(f"    Fetching GitHub repo info from API")
     
-    match = re.search(r'github\.com/([^/]+)/([^/]+)', url)
+    match = re.search(r'github\.com/([^/]+)/([^/]+?)(/|$)', url)
     if not match:
         return None
     
-    owner, repo = match.groups()
+    owner, repo = match.groups()[:2]
+    repo = repo.rstrip('/')
     
     try:
-        # Try to get README
+        # Try to get README as raw markdown
         response = requests.get(
             f"https://api.github.com/repos/{owner}/{repo}/readme",
             headers={"Accept": "application/vnd.github.v3.raw"},
@@ -177,11 +178,20 @@ def get_github_content(url):
         )
         
         if response.status_code == 200:
-            content = response.text[:2000]
-            logger.debug(f"    Got README: {len(content)} chars")
-            return content
+            content = response.text
+            # Clean markdown: remove images, code blocks, links
+            content = re.sub(r'!\[.*?\]\(.*?\)', '', content)  # Remove images
+            content = re.sub(r'```.*?```', '', content, flags=re.DOTALL)  # Remove code blocks
+            content = re.sub(r'\[([^\]]+)\]\([^\)]+\)', r'\1', content)  # Convert markdown links to text
+            content = re.sub(r'#{1,6}\s+', '', content)  # Remove headers
+            content = re.sub(r'[*_-]{3,}', '', content)  # Remove horizontal rules
+            content = re.sub(r'\s+', ' ', content).strip()  # Clean whitespace
+            
+            if len(content) > 50:
+                logger.debug(f"    Got README: {len(content)} chars after cleaning")
+                return content[:2000]
         
-        # Fallback: get repo info from API
+        # Fallback: get repo info JSON
         response = requests.get(
             f"https://api.github.com/repos/{owner}/{repo}",
             timeout=5
@@ -189,10 +199,19 @@ def get_github_content(url):
         
         if response.status_code == 200:
             data = response.json()
-            desc = data.get("description", "")
-            if desc:
-                logger.debug(f"    Got repo description: {desc}")
-                return desc
+            # Collect useful info
+            parts = []
+            if data.get("description"):
+                parts.append(data["description"])
+            if data.get("topics"):
+                parts.append(f"Topics: {', '.join(data['topics'][:3])}")
+            if data.get("language"):
+                parts.append(f"Language: {data['language']}")
+            
+            content = " ".join(parts)
+            if content:
+                logger.debug(f"    Got repo info: {len(content)} chars")
+                return content
     
     except Exception as e:
         logger.warning(f"    GitHub API error: {e}")