import json
from pathlib import Path

CLEANED_DIR = Path(r"c:\Users\Daniil\VS_Code\Trash\cleaned_backups")

# Let's inspect all posts mentioning MCP
results = []
for file_path in sorted(CLEANED_DIR.glob("*.jsonl")):
    with open(file_path, "r", encoding="utf-8") as f:
        for line in f:
            if not line.strip():
                continue
            post = json.loads(line)
            text = post.get("text", "")
            lower = text.lower()
            if "mcp" in lower or "model context protocol" in lower or "fastmcp" in lower:
                results.append(post)

print(f"Total raw MCP mentions: {len(results)}")

# Let's filter and analyze those that discuss creation, building, courses, SDKs, tutorials, writing servers
for i, post in enumerate(results, 1):
    text = post['text']
    lower = text.lower()
    
    # Classify relevance to "creation/development of MCP"
    creation_signals = [
        "созда", "написа", "разработ", "курс", "туториал", "гайд", "sdk", "библиотек",
        "tutorial", "guide", "build", "create", "server", "сервер", "fastmcp", "templates",
        "plugin", "плагин"
    ]
    matched_signals = [s for s in creation_signals if s in lower]
    
    print(f"=== [{i}] {post['channel']} | {post['date']} | ID: {post['message_id']} ===")
    print(f"Post link: {post['post_link']}")
    print(f"Matched signals: {matched_signals}")
    print(f"Links: {post['links']}")
    print("TEXT:")
    print(text)
    print("\n" + "="*60 + "\n")
