airkjw/blog-writer
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

debug: _fetch_sources_content 로그 추가

Browse Source
This commit is contained in:
JOUNGWOOK KWON
2026-03-30 16:24:03 +09:00
parent e077b593c9
commit 8c66d9b9e0
1 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
bots/scheduler.py
View File

@@ -245,7 +245,9 @@ def _build_openclaw_prompt(topic_data: dict) -> tuple[str, str]:
def _fetch_sources_content(topic_data: dict) -> dict: def _fetch_sources_content(topic_data: dict) -> dict:
"""idea/manual 소스의 경우 글 작성 전 실제 기사 내용 크롤링""" """idea/manual 소스의 경우 글 작성 전 실제 기사 내용 크롤링"""
logger.info(f"[fetch_sources] source={topic_data.get('source')}, sources={len(topic_data.get('sources', []))}")
if topic_data.get('source') not in ('idea', 'manual'): if topic_data.get('source') not in ('idea', 'manual'):
logger.info(f"[fetch_sources] 스킵 (source={topic_data.get('source')})")
return topic_data return topic_data
import requests import requests
@@ -258,14 +260,17 @@ def _fetch_sources_content(topic_data: dict) -> dict:
# 소스가 없거나 Google 뉴스 URL만 있는 경우 → 키워드로 재검색 # 소스가 없거나 Google 뉴스 URL만 있는 경우 → 키워드로 재검색
need_search = not existing_sources or all('news.google.com' in s.get('url', '') for s in existing_sources) need_search = not existing_sources or all('news.google.com' in s.get('url', '') for s in existing_sources)
logger.info(f"[fetch_sources] need_search={need_search}, existing={len(existing_sources)}")
if need_search: if need_search:
try: try:
search_url = f"https://news.google.com/rss/search?q={quote(topic)}&hl=ko&gl=KR&ceid=KR:ko" search_url = f"https://news.google.com/rss/search?q={quote(topic)}&hl=ko&gl=KR&ceid=KR:ko"
logger.info(f"[fetch_sources] RSS 검색: {topic[:40]}")
feed = feedparser.parse(search_url) feed = feedparser.parse(search_url)
logger.info(f"[fetch_sources] RSS 결과: {len(feed.entries)}개")
existing_sources = [{'url': e.get('link', ''), 'title': e.get('title', ''), 'date': e.get('published', '')} existing_sources = [{'url': e.get('link', ''), 'title': e.get('title', ''), 'date': e.get('published', '')}
for e in feed.entries[:5]] for e in feed.entries[:5]]
except Exception: except Exception as e:
pass logger.warning(f"[fetch_sources] RSS 검색 실패: {e}")
# 각 소스 URL 변환 + 내용 크롤링 (최대 3개, 각 5초 타임아웃) # 각 소스 URL 변환 + 내용 크롤링 (최대 3개, 각 5초 타임아웃)
enriched_sources = [] enriched_sources = []