239 lines
7.2 KiB
Python
239 lines
7.2 KiB
Python
"""
|
|
Telegram Group Filter — scours 100+ groups for interesting messages.
|
|
Runs as: t-youtube venv + Pyrogram session.
|
|
|
|
Scoring: mentions, links, code blocks, media, keywords → score ≥ threshold → saved.
|
|
Delivers to: hermes_telegram_bot or stdout.
|
|
"""
|
|
|
|
import asyncio
|
|
import os
|
|
import re
|
|
import json
|
|
import sqlite3
|
|
import logging
|
|
from datetime import datetime, timezone, timedelta
|
|
from pyrogram import Client
|
|
from pyrogram.types import Message
|
|
from typing import Optional
|
|
|
|
logging.basicConfig(
|
|
level=logging.INFO,
|
|
format="%(asctime)s [%(levelname)s] %(message)s",
|
|
datefmt="%H:%M:%S",
|
|
)
|
|
log = logging.getLogger("tg_filter")
|
|
|
|
# === CONFIG ===
|
|
PHONE = open("/tmp/tg_phone.txt").read().strip()
|
|
API_ID = 2040
|
|
API_HASH = "b18441a1ff607e10a989891a5462e627"
|
|
WORKDIR = "/Users/jimmyg"
|
|
DB_PATH = os.path.join(WORKDIR, ".hermes", "tg_filter.db")
|
|
|
|
# Scoring
|
|
SCORE_MENTION = 30 # @username or reply to user
|
|
SCORE_KEYWORD = 15 # Interesting keyword match
|
|
SCORE_LINK = 10 # Contains URL
|
|
SCORE_MEDIA = 8 # Photo/video/file
|
|
SCORE_CODE = 12 # Code block
|
|
SCORE_LONG_TEXT = 5 # ≥200 chars of substance
|
|
THRESHOLD = 20 # Minimum score to forward
|
|
|
|
# Keywords that signal interesting content
|
|
INTERESTING_KEYWORDS = [
|
|
"ai", "llm", "gpt", "deepseek", "claude", "gemini", "qwen", "openai",
|
|
"docker", "kubernetes", "k8s", "tailscale", "wireguard", "vps", "nas",
|
|
"self-host", "homelab", "server", "deploy", "ci/cd", "gitea", "git",
|
|
"api", "automation", "script", "python", "rust", "go", "typescript",
|
|
"svelte", "react", "nextjs", "fastapi", "sveltekit",
|
|
"tutorial", "guide", "how to", "free", "open source", "github",
|
|
"security", "vulnerability", "cve", "patch", "update",
|
|
"opportunity", "合作", "项目", "招聘", "job", "remote",
|
|
"startup", "saas", "mvp", "产品", "产品发布",
|
|
]
|
|
|
|
# Groups to always ignore (IDs or title substrings)
|
|
IGNORE_PATTERNS = [
|
|
"合租社群",
|
|
"黄油派对",
|
|
]
|
|
|
|
def score_message(msg: Message) -> int:
|
|
"""Score a message for interestingness."""
|
|
score = 0
|
|
text = msg.text or msg.caption or ""
|
|
|
|
# Mentions
|
|
if msg.entities:
|
|
for e in msg.entities:
|
|
if e.type in ("mention", "text_mention"):
|
|
score += SCORE_MENTION
|
|
if e.type == "url":
|
|
score += SCORE_LINK
|
|
if e.type == "code" or e.type == "pre":
|
|
score += SCORE_CODE
|
|
|
|
# Media
|
|
if msg.photo or msg.video or msg.document or msg.audio:
|
|
score += SCORE_MEDIA
|
|
|
|
# Links in plain text
|
|
if re.search(r'https?://[^\s]+', text):
|
|
score += SCORE_LINK
|
|
|
|
# Keyword matches
|
|
text_lower = text.lower()
|
|
for kw in INTERESTING_KEYWORDS:
|
|
if kw in text_lower:
|
|
score += SCORE_KEYWORD
|
|
|
|
# Long substantive text
|
|
if len(text.strip()) >= 200:
|
|
score += SCORE_LONG_TEXT
|
|
|
|
# Forwarded messages are often interesting
|
|
if msg.forward_from or msg.forward_from_chat:
|
|
score += 5
|
|
|
|
# Reply to user's own messages (engagement)
|
|
if msg.reply_to_message_id:
|
|
score += 3
|
|
|
|
return score
|
|
|
|
|
|
def should_ignore(chat_title: str) -> bool:
|
|
"""Check if a chat should be ignored entirely."""
|
|
if not chat_title:
|
|
return False
|
|
for pat in IGNORE_PATTERNS:
|
|
if pat in chat_title:
|
|
return True
|
|
return False
|
|
|
|
|
|
def init_db():
|
|
"""Create DB + table for tracking processed messages."""
|
|
os.makedirs(os.path.dirname(DB_PATH), exist_ok=True)
|
|
db = sqlite3.connect(DB_PATH)
|
|
db.execute("""
|
|
CREATE TABLE IF NOT EXISTS processed (
|
|
chat_id INTEGER,
|
|
message_id INTEGER,
|
|
PRIMARY KEY (chat_id, message_id)
|
|
)
|
|
""")
|
|
db.execute("""
|
|
CREATE TABLE IF NOT EXISTS interesting (
|
|
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
|
chat_id INTEGER,
|
|
chat_title TEXT,
|
|
message_id INTEGER,
|
|
sender TEXT,
|
|
text TEXT,
|
|
score INTEGER,
|
|
captured_at TEXT,
|
|
delivered INTEGER DEFAULT 0
|
|
)
|
|
""")
|
|
db.commit()
|
|
return db
|
|
|
|
|
|
async def scan_and_report(dry_run: bool = False) -> list:
|
|
"""Scan dialogs for interesting messages. Returns list of interesting items."""
|
|
db = init_db()
|
|
processed_ids = set()
|
|
for row in db.execute("SELECT chat_id, message_id FROM processed"):
|
|
processed_ids.add((row[0], row[1]))
|
|
|
|
c = Client("pyro_session", API_ID, API_HASH, workdir=WORKDIR)
|
|
await c.start()
|
|
me = await c.get_me()
|
|
log.info(f"Scanned as: {me.first_name}")
|
|
|
|
interesting = []
|
|
total_read = 0
|
|
total_skipped = 0
|
|
|
|
async for dialog in c.get_dialogs():
|
|
chat = dialog.chat
|
|
chat_id = chat.id
|
|
chat_title = chat.title or chat.first_name or "Unknown"
|
|
|
|
if should_ignore(chat_title):
|
|
continue
|
|
|
|
if not dialog.unread_messages_count:
|
|
continue
|
|
|
|
# Read recent messages (up to 50 per chat)
|
|
async for msg in c.get_chat_history(chat_id, limit=50):
|
|
if (chat_id, msg.id) in processed_ids:
|
|
continue
|
|
total_read += 1
|
|
|
|
score = score_message(msg)
|
|
if score >= THRESHOLD:
|
|
sender = None
|
|
if msg.from_user:
|
|
sender = msg.from_user.first_name or msg.from_user.username or str(msg.from_user.id)
|
|
text = (msg.text or msg.caption or "")[:2000]
|
|
|
|
item = {
|
|
"chat_id": chat_id,
|
|
"chat_title": chat_title,
|
|
"message_id": msg.id,
|
|
"sender": sender,
|
|
"text": text,
|
|
"score": score,
|
|
"has_media": bool(msg.photo or msg.video or msg.document),
|
|
"url": f"https://t.me/c/{str(chat_id).replace('-100', '')}/{msg.id}" if chat_id < 0 else None,
|
|
}
|
|
interesting.append(item)
|
|
|
|
# Save to DB
|
|
db.execute(
|
|
"INSERT OR IGNORE INTO interesting (chat_id, chat_title, message_id, sender, text, score, captured_at) VALUES (?, ?, ?, ?, ?, ?, ?)",
|
|
(chat_id, chat_title, msg.id, sender, text, score, datetime.now(timezone.utc).isoformat()),
|
|
)
|
|
else:
|
|
total_skipped += 1
|
|
|
|
# Mark as processed
|
|
db.execute("INSERT OR IGNORE INTO processed (chat_id, message_id) VALUES (?, ?)", (chat_id, msg.id))
|
|
|
|
db.commit()
|
|
|
|
await c.stop()
|
|
db.close()
|
|
|
|
log.info(f"Read {total_read} messages, skipped {total_skipped}, found {len(interesting)} interesting")
|
|
|
|
if not dry_run and interesting:
|
|
for item in interesting:
|
|
_print_item(item)
|
|
|
|
return interesting
|
|
|
|
|
|
def _print_item(item: dict):
|
|
"""Print an interesting item for delivery."""
|
|
print(f"\n{'='*50}")
|
|
print(f"📌 {item['chat_title']} [{item['score']}pts]")
|
|
if item['sender']:
|
|
print(f"👤 {item['sender']}")
|
|
if item['has_media']:
|
|
print(f"📎 [has media]")
|
|
if item['url']:
|
|
print(f"🔗 {item['url']}")
|
|
print(f"\n{item['text'][:500]}")
|
|
print(f"{'='*50}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
import sys
|
|
dry_run = "--dry-run" in sys.argv
|
|
asyncio.run(scan_and_report(dry_run=dry_run))
|