diff --git a/app/core/crawl_politeness.py b/app/core/crawl_politeness.py index d54687d..d61e030 100644 --- a/app/core/crawl_politeness.py +++ b/app/core/crawl_politeness.py @@ -12,7 +12,6 @@ SSRF 차단은 core.url_validator.validate_feed_url 재사용 (redirect target """ import asyncio -import logging import random import time import urllib.robotparser @@ -21,8 +20,10 @@ from urllib.parse import urljoin, urlparse import httpx from core.url_validator import validate_feed_url +from core.utils import setup_logger -logger = logging.getLogger("crawl_politeness") +# bare getLogger 는 root(WARNING) 상속이라 INFO 대기/차단 로그가 드랍됨 — 타 워커와 동일 설정 +logger = setup_logger("crawl_politeness") # 정직 식별 UA + 연락처 — 차단 전 연락 통로 (A-4) CRAWL_UA = "HyungiPKM-Archiver/1.0 (personal archive; +mailto:hyun49196@gmail.com)"