eeaa9dcb4b
- Add multi-threaded keyword scheduler for periodic news collection - Create Keyword Manager API for CRUD operations and monitoring - Implement automatic pipeline triggering (RSS → Google → AI → Translation) - Add thread status monitoring and dynamic keyword management - Support priority-based execution and configurable intervals - Add comprehensive scheduler documentation guide - Default keywords: AI, 테크놀로지, 경제, 블록체인 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
230 lines
8.6 KiB
Python
230 lines
8.6 KiB
Python
"""
|
|
Translation Service
|
|
DeepL API를 사용한 번역 서비스
|
|
"""
|
|
import asyncio
|
|
import logging
|
|
import os
|
|
import sys
|
|
from typing import List, Dict, Any
|
|
import httpx
|
|
from motor.motor_asyncio import AsyncIOMotorClient
|
|
from datetime import datetime
|
|
|
|
# Import from shared module
|
|
from shared.models import PipelineJob, FinalArticle
|
|
from shared.queue_manager import QueueManager
|
|
|
|
logging.basicConfig(level=logging.INFO)
|
|
logger = logging.getLogger(__name__)
|
|
|
|
class TranslatorWorker:
|
|
def __init__(self):
|
|
self.queue_manager = QueueManager(
|
|
redis_url=os.getenv("REDIS_URL", "redis://redis:6379")
|
|
)
|
|
self.deepl_api_key = os.getenv("DEEPL_API_KEY", "3abbc796-2515-44a8-972d-22dcf27ab54a")
|
|
# DeepL Pro API 엔드포인트 사용
|
|
self.deepl_api_url = "https://api.deepl.com/v2/translate"
|
|
self.mongodb_url = os.getenv("MONGODB_URL", "mongodb://mongodb:27017")
|
|
self.db_name = os.getenv("DB_NAME", "ai_writer_db")
|
|
self.db = None
|
|
|
|
async def start(self):
|
|
"""워커 시작"""
|
|
logger.info("Starting Translator Worker")
|
|
|
|
# Redis 연결
|
|
await self.queue_manager.connect()
|
|
|
|
# MongoDB 연결
|
|
client = AsyncIOMotorClient(self.mongodb_url)
|
|
self.db = client[self.db_name]
|
|
|
|
# DeepL API 키 확인
|
|
if not self.deepl_api_key:
|
|
logger.error("DeepL API key not configured")
|
|
return
|
|
|
|
# 메인 처리 루프
|
|
while True:
|
|
try:
|
|
# 큐에서 작업 가져오기
|
|
job = await self.queue_manager.dequeue('translation', timeout=5)
|
|
|
|
if job:
|
|
await self.process_job(job)
|
|
|
|
except Exception as e:
|
|
logger.error(f"Error in worker loop: {e}")
|
|
await asyncio.sleep(1)
|
|
|
|
async def process_job(self, job: PipelineJob):
|
|
"""영어 버전 기사 생성 및 저장"""
|
|
try:
|
|
logger.info(f"Processing job {job.job_id} for translation")
|
|
|
|
# MongoDB에서 한국어 기사 가져오기
|
|
news_id = job.data.get('news_id')
|
|
if not news_id:
|
|
logger.error(f"No news_id in job {job.job_id}")
|
|
await self.queue_manager.mark_failed('translation', job, "No news_id")
|
|
return
|
|
|
|
# MongoDB에서 한국어 기사 조회 (articles_ko)
|
|
korean_article = await self.db.articles_ko.find_one({"news_id": news_id})
|
|
if not korean_article:
|
|
logger.error(f"Article {news_id} not found in MongoDB")
|
|
await self.queue_manager.mark_failed('translation', job, "Article not found")
|
|
return
|
|
|
|
# 영어로 번역
|
|
translated_title = await self._translate_text(
|
|
korean_article.get('title', ''),
|
|
target_lang='EN'
|
|
)
|
|
|
|
translated_summary = await self._translate_text(
|
|
korean_article.get('summary', ''),
|
|
target_lang='EN'
|
|
)
|
|
|
|
# Subtopics 번역
|
|
from shared.models import Subtopic
|
|
translated_subtopics = []
|
|
for subtopic in korean_article.get('subtopics', []):
|
|
translated_subtopic_title = await self._translate_text(
|
|
subtopic.get('title', ''),
|
|
target_lang='EN'
|
|
)
|
|
|
|
translated_content_list = []
|
|
for content_para in subtopic.get('content', []):
|
|
translated_para = await self._translate_text(
|
|
content_para,
|
|
target_lang='EN'
|
|
)
|
|
translated_content_list.append(translated_para)
|
|
await asyncio.sleep(0.2) # API 속도 제한
|
|
|
|
translated_subtopics.append(Subtopic(
|
|
title=translated_subtopic_title,
|
|
content=translated_content_list
|
|
))
|
|
|
|
# 카테고리 번역
|
|
translated_categories = []
|
|
for category in korean_article.get('categories', []):
|
|
translated_cat = await self._translate_text(category, target_lang='EN')
|
|
translated_categories.append(translated_cat)
|
|
await asyncio.sleep(0.2) # API 속도 제한
|
|
|
|
# Entities 번역 (선택적)
|
|
from shared.models import Entities
|
|
entities_data = korean_article.get('entities', {})
|
|
translated_entities = Entities(
|
|
people=entities_data.get('people', []), # 인명은 번역하지 않음
|
|
organizations=entities_data.get('organizations', []), # 조직명은 번역하지 않음
|
|
groups=entities_data.get('groups', []),
|
|
countries=entities_data.get('countries', []),
|
|
events=entities_data.get('events', [])
|
|
)
|
|
|
|
# 레퍼런스 가져오기 (번역하지 않음)
|
|
from shared.models import NewsReference
|
|
references = []
|
|
for ref_data in korean_article.get('references', []):
|
|
references.append(NewsReference(**ref_data))
|
|
|
|
# 영어 버전 기사 생성 - 같은 news_id 사용
|
|
english_article = FinalArticle(
|
|
news_id=news_id, # 원본과 같은 news_id 사용
|
|
title=translated_title,
|
|
summary=translated_summary,
|
|
subtopics=translated_subtopics,
|
|
categories=translated_categories,
|
|
entities=translated_entities,
|
|
source_keyword=job.keyword,
|
|
source_count=korean_article.get('source_count', 1),
|
|
references=references, # 원본 레퍼런스 그대로 사용
|
|
job_id=job.job_id,
|
|
keyword_id=job.keyword_id,
|
|
pipeline_stages=job.stages_completed.copy() + ['translation'],
|
|
processing_time=korean_article.get('processing_time', 0),
|
|
language='en', # 영어
|
|
ref_news_id=None # 같은 news_id를 사용하므로 ref 불필요
|
|
)
|
|
|
|
# MongoDB에 영어 버전 저장 (articles_en)
|
|
result = await self.db.articles_en.insert_one(english_article.model_dump())
|
|
english_article_id = str(result.inserted_id)
|
|
|
|
logger.info(f"English article saved with _id: {english_article_id}, news_id: {news_id}, language: en")
|
|
|
|
# 원본 한국어 기사 업데이트 - 번역 완료 표시
|
|
await self.db.articles_ko.update_one(
|
|
{"news_id": news_id},
|
|
{
|
|
"$addToSet": {
|
|
"pipeline_stages": "translation"
|
|
}
|
|
}
|
|
)
|
|
|
|
# 완료 표시
|
|
job.stages_completed.append('translation')
|
|
await self.queue_manager.mark_completed('translation', job.job_id)
|
|
|
|
logger.info(f"Translation completed for job {job.job_id}")
|
|
|
|
except Exception as e:
|
|
logger.error(f"Error processing job {job.job_id}: {e}")
|
|
await self.queue_manager.mark_failed('translation', job, str(e))
|
|
|
|
async def _translate_text(self, text: str, target_lang: str = 'EN') -> str:
|
|
"""DeepL API를 사용한 텍스트 번역"""
|
|
try:
|
|
if not text:
|
|
return ""
|
|
|
|
async with httpx.AsyncClient() as client:
|
|
response = await client.post(
|
|
self.deepl_api_url,
|
|
data={
|
|
'auth_key': self.deepl_api_key,
|
|
'text': text,
|
|
'target_lang': target_lang,
|
|
'source_lang': 'KO'
|
|
},
|
|
timeout=30
|
|
)
|
|
|
|
if response.status_code == 200:
|
|
result = response.json()
|
|
return result['translations'][0]['text']
|
|
else:
|
|
logger.error(f"DeepL API error: {response.status_code}")
|
|
return text # 번역 실패시 원본 반환
|
|
|
|
except Exception as e:
|
|
logger.error(f"Error translating text: {e}")
|
|
return text # 번역 실패시 원본 반환
|
|
|
|
async def stop(self):
|
|
"""워커 중지"""
|
|
await self.queue_manager.disconnect()
|
|
logger.info("Translator Worker stopped")
|
|
|
|
async def main():
|
|
"""메인 함수"""
|
|
worker = TranslatorWorker()
|
|
|
|
try:
|
|
await worker.start()
|
|
except KeyboardInterrupt:
|
|
logger.info("Received interrupt signal")
|
|
finally:
|
|
await worker.stop()
|
|
|
|
if __name__ == "__main__":
|
|
asyncio.run(main()) |