Add GitHub stats fetching feature

- Added PyGithub package to requirements.txt for GitHub API interaction
- Updated .gitignore to ignore github-stats-cache.json
- Produced github-stats.json for storing GitHub stats
- Modified scanner.py to include the GitHub stats fetching process

.gitignore

@@ -11,3 +11,4 @@ startup-scripts/**
 matrix_auth
 channels.list
 comfyworkflows_sharekey
+github-stats-cache.json

requirements.txt

@@ -1,4 +1,5 @@
 GitPython
+PyGithub
 matrix-client==0.4.0
 transformers
 huggingface-hub>0.20

scanner.py

@@ -10,6 +10,10 @@ builtin_nodes = set()
 
 import sys
 
+from urllib.parse import urlparse
+from github import Github
+
+g = Github(os.environ.get('GITHUB_TOKEN'))
 
 # prepare temp dir
 if len(sys.argv) > 1:
@@ -224,7 +228,48 @@ def update_custom_nodes():
         if not skip_update:
             clone_or_pull_git_repository(url)
 
-    with concurrent.futures.ThreadPoolExecutor(10) as executor:
+    def process_git_stats(git_url_titles_preemptions):
+        GITHUB_STATS_CACHE_FILENAME = 'github-stats-cache.json'
+        GITHUB_STATS_FILENAME = 'github-stats.json'
+
+        github_stats = {}
+        try:
+            with open(GITHUB_STATS_CACHE_FILENAME, 'r', encoding='utf-8') as file:
+                github_stats = json.load(file)
+        except FileNotFoundError:
+            pass
+        for url, title, preemptions, node_pattern in git_url_titles_preemptions:
+            if url not in github_stats:
+                # Parsing the URL
+                parsed_url = urlparse(url)
+                domain = parsed_url.netloc
+                path = parsed_url.path
+                path_parts = path.strip("/").split("/")
+                if len(path_parts) >= 2 and domain == "github.com":
+                    owner_repo = "/".join(path_parts[-2:])
+                    repo = g.get_repo(owner_repo)
+
+                    last_update = repo.pushed_at.strftime("%Y-%m-%d %H:%M:%S") if repo.pushed_at else 'N/A'
+                    github_stats[url] = {
+                        "stars": repo.stargazers_count,
+                        "last_update": last_update,
+                    }
+                    with open(GITHUB_STATS_CACHE_FILENAME, 'w', encoding='utf-8') as file:
+                        json.dump(github_stats, file, ensure_ascii=False, indent=4)
+                    # print(f"Title: {title}, Stars: {repo.stargazers_count}, Last Update: {last_update}")
+                else:
+                    print(f"Invalid URL format for GitHub repository: {url}")
+
+        with open(GITHUB_STATS_FILENAME, 'w', encoding='utf-8') as file:
+            json.dump(github_stats, file, ensure_ascii=False, indent=4)
+        print(f"Successfully written to {GITHUB_STATS_FILENAME}, removing {GITHUB_STATS_CACHE_FILENAME}.")
+        try:
+            os.remove(GITHUB_STATS_CACHE_FILENAME) # This cache file is just for avoiding failure of GitHub API fetch, so it is safe to remove.
+        except:
+            pass
+
+    with concurrent.futures.ThreadPoolExecutor(11) as executor:
+        executor.submit(process_git_stats, git_url_titles_preemptions) # One single thread for `process_git_stats()`. Runs concurrently with `process_git_url_title()`.
         for url, title, preemptions, node_pattern in git_url_titles_preemptions:
             executor.submit(process_git_url_title, url, title, preemptions, node_pattern)