From d71c1d3aa37dd17de3664132f3f4cab065a88829 Mon Sep 17 00:00:00 2001
From: yusyus <yusufkaraaslan.yk@pm.me>
Date: Thu, 26 Mar 2026 23:44:52 +0300
Subject: [PATCH] fix: filter non-integer metadata from GitHub languages API
 response (#322)

PyGithub's get_languages() returns raw API JSON which in some environments
includes non-integer metadata keys (e.g., "url"), causing a TypeError in
sum(). Now filters to integer values only before calculating percentages.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---
 CHANGELOG.md                            |  3 +++
 CLAUDE.md                               |  2 +-
 src/skill_seekers/cli/github_scraper.py |  7 +++++++
 tests/test_github_scraper.py            | 25 +++++++++++++++++++++++++
 4 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index e6d5fe3..e8fd7ab 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+### Fixed
+- **GitHub language detection crashes with `TypeError`** when API response contains non-integer metadata keys (e.g., `"url"`) — now filters to integer values only (#322)
+
 ## [3.4.0] - 2026-03-21
 
 ### Added
diff --git a/CLAUDE.md b/CLAUDE.md
index b0c1cdf..ee62935 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -6,7 +6,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 **Skill Seekers** converts documentation from 17 source types into production-ready formats for 24+ AI platforms (LLM platforms, RAG frameworks, vector databases, AI coding assistants). Published on PyPI as `skill-seekers`.
 
-**Version:** 3.3.0 | **Python:** 3.10+ | **Website:** https://skillseekersweb.com/
+**Version:** 3.4.0 | **Python:** 3.10+ | **Website:** https://skillseekersweb.com/
 
 **Architecture:** See `docs/UML_ARCHITECTURE.md` for UML diagrams and module overview. StarUML project at `docs/UML/skill_seekers.mdj`.
 
diff --git a/src/skill_seekers/cli/github_scraper.py b/src/skill_seekers/cli/github_scraper.py
index 4e8b4d9..e027930 100644
--- a/src/skill_seekers/cli/github_scraper.py
+++ b/src/skill_seekers/cli/github_scraper.py
@@ -519,6 +519,13 @@ class GitHubScraper:
 
         try:
             languages = self.repo.get_languages()
+            # Filter out non-integer metadata (e.g., "url" key from some API configurations)
+            non_lang_keys = {k for k, v in languages.items() if not isinstance(v, int)}
+            if non_lang_keys:
+                logger.debug(
+                    f"Filtered non-language keys from API response: {non_lang_keys}"
+                )
+                languages = {k: v for k, v in languages.items() if isinstance(v, int)}
             total_bytes = sum(languages.values())
 
             self.extracted_data["languages"] = {
diff --git a/tests/test_github_scraper.py b/tests/test_github_scraper.py
index 9909233..0341364 100644
--- a/tests/test_github_scraper.py
+++ b/tests/test_github_scraper.py
@@ -230,6 +230,31 @@ class TestLanguageDetection(unittest.TestCase):
             self.assertIn("languages", scraper.extracted_data)
             self.assertEqual(scraper.extracted_data["languages"], {})
 
+    def test_extract_languages_filters_non_integer_metadata(self):
+        """Test that non-integer metadata keys (e.g., 'url') are filtered out (#322)"""
+        config = {"repo": "xyflow/xyflow", "name": "xyflow", "github_token": None}
+
+        with patch("skill_seekers.cli.github_scraper.Github"):
+            scraper = self.GitHubScraper(config)
+            scraper.repo = Mock()
+            scraper.repo.get_languages.return_value = {
+                "TypeScript": 707330,
+                "Svelte": 95784,
+                "url": "https://api.github.com/repos/xyflow/xyflow/languages",
+            }
+
+            scraper._extract_languages()
+
+            self.assertIn("languages", scraper.extracted_data)
+            self.assertIn("TypeScript", scraper.extracted_data["languages"])
+            self.assertIn("Svelte", scraper.extracted_data["languages"])
+            self.assertNotIn("url", scraper.extracted_data["languages"])
+
+            # Percentages should be calculated only from real languages
+            ts_data = scraper.extracted_data["languages"]["TypeScript"]
+            total = 707330 + 95784
+            self.assertEqual(ts_data["percentage"], round(707330 / total * 100, 2))
+
 
 class TestIssuesExtraction(unittest.TestCase):
     """Test GitHub Issues extraction (C1.7)"""