feat: Implement automated keyword-based news pipeline scheduler
- 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>
This commit is contained in:
jungwoo choi
320
services/pipeline/translator/multi_translator.py
Normal file
320
services/pipeline/translator/multi_translator.py
Normal file
@ -0,0 +1,320 @@
|
||||
"""
|
||||
Multi-Language Translation Service
|
||||
다국어 번역 서비스 - 설정 기반 다중 언어 지원
|
||||
"""
|
||||
import asyncio
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
import json
|
||||
from typing import List, Dict, Any
|
||||
import httpx
|
||||
import redis.asyncio as redis
|
||||
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 MultiLanguageTranslator:
|
||||
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")
|
||||
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
|
||||
self.languages_config = None
|
||||
self.config_path = "/app/config/languages.json"
|
||||
|
||||
async def load_config(self):
|
||||
"""언어 설정 파일 로드"""
|
||||
try:
|
||||
if os.path.exists(self.config_path):
|
||||
with open(self.config_path, 'r', encoding='utf-8') as f:
|
||||
self.languages_config = json.load(f)
|
||||
else:
|
||||
# 기본 설정 (영어만)
|
||||
self.languages_config = {
|
||||
"enabled_languages": [
|
||||
{
|
||||
"code": "en",
|
||||
"name": "English",
|
||||
"deepl_code": "EN",
|
||||
"collection": "articles_en",
|
||||
"enabled": True
|
||||
}
|
||||
],
|
||||
"source_language": {
|
||||
"code": "ko",
|
||||
"name": "Korean",
|
||||
"collection": "articles_ko"
|
||||
},
|
||||
"translation_settings": {
|
||||
"batch_size": 5,
|
||||
"delay_between_languages": 2.0,
|
||||
"delay_between_articles": 0.5,
|
||||
"max_retries": 3
|
||||
}
|
||||
}
|
||||
logger.info(f"Loaded language config: {len(self.get_enabled_languages())} languages enabled")
|
||||
except Exception as e:
|
||||
logger.error(f"Error loading config: {e}")
|
||||
raise
|
||||
|
||||
def get_enabled_languages(self) -> List[Dict]:
|
||||
"""활성화된 언어 목록 반환"""
|
||||
return [lang for lang in self.languages_config["enabled_languages"] if lang["enabled"]]
|
||||
|
||||
async def start(self):
|
||||
"""워커 시작"""
|
||||
logger.info("Starting Multi-Language Translator Worker")
|
||||
|
||||
# 설정 로드
|
||||
await self.load_config()
|
||||
|
||||
# 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):
|
||||
"""모든 활성 언어로 번역"""
|
||||
try:
|
||||
logger.info(f"Processing job {job.job_id} for multi-language 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
|
||||
|
||||
# 원본 컬렉션에서 기사 조회
|
||||
source_collection = self.languages_config["source_language"]["collection"]
|
||||
korean_article = await self.db[source_collection].find_one({"news_id": news_id})
|
||||
|
||||
if not korean_article:
|
||||
logger.error(f"Article {news_id} not found in {source_collection}")
|
||||
await self.queue_manager.mark_failed('translation', job, "Article not found")
|
||||
return
|
||||
|
||||
# 활성화된 모든 언어로 번역
|
||||
enabled_languages = self.get_enabled_languages()
|
||||
settings = self.languages_config["translation_settings"]
|
||||
|
||||
for lang_config in enabled_languages:
|
||||
try:
|
||||
logger.info(f"Translating article {news_id} to {lang_config['name']}")
|
||||
|
||||
# 이미 번역되었는지 확인
|
||||
existing = await self.db[lang_config["collection"]].find_one({"news_id": news_id})
|
||||
if existing:
|
||||
logger.info(f"Article {news_id} already translated to {lang_config['code']}")
|
||||
continue
|
||||
|
||||
# 번역 수행
|
||||
await self.translate_article(
|
||||
korean_article,
|
||||
lang_config,
|
||||
job
|
||||
)
|
||||
|
||||
# 언어 간 지연
|
||||
if settings.get("delay_between_languages"):
|
||||
await asyncio.sleep(settings["delay_between_languages"])
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error translating to {lang_config['code']}: {e}")
|
||||
continue
|
||||
|
||||
# 파이프라인 완료 로그
|
||||
logger.info(f"Translation pipeline completed for news_id: {news_id}")
|
||||
|
||||
# 완료 표시
|
||||
job.stages_completed.append('translation')
|
||||
await self.queue_manager.mark_completed('translation', job.job_id)
|
||||
|
||||
logger.info(f"Multi-language 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_article(self, korean_article: Dict, lang_config: Dict, job: PipelineJob):
|
||||
"""특정 언어로 기사 번역"""
|
||||
try:
|
||||
# 제목 번역
|
||||
translated_title = await self._translate_text(
|
||||
korean_article.get('title', ''),
|
||||
target_lang=lang_config["deepl_code"]
|
||||
)
|
||||
|
||||
# 요약 번역
|
||||
translated_summary = await self._translate_text(
|
||||
korean_article.get('summary', ''),
|
||||
target_lang=lang_config["deepl_code"]
|
||||
)
|
||||
|
||||
# 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=lang_config["deepl_code"]
|
||||
)
|
||||
|
||||
translated_content_list = []
|
||||
for content_para in subtopic.get('content', []):
|
||||
translated_para = await self._translate_text(
|
||||
content_para,
|
||||
target_lang=lang_config["deepl_code"]
|
||||
)
|
||||
translated_content_list.append(translated_para)
|
||||
|
||||
# API 속도 제한
|
||||
settings = self.languages_config["translation_settings"]
|
||||
if settings.get("delay_between_articles"):
|
||||
await asyncio.sleep(settings["delay_between_articles"])
|
||||
|
||||
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=lang_config["deepl_code"]
|
||||
)
|
||||
translated_categories.append(translated_cat)
|
||||
|
||||
# Entities와 References는 원본 유지
|
||||
from shared.models import Entities, NewsReference
|
||||
entities_data = korean_article.get('entities', {})
|
||||
translated_entities = Entities(**entities_data) if entities_data else Entities()
|
||||
|
||||
references = []
|
||||
for ref_data in korean_article.get('references', []):
|
||||
references.append(NewsReference(**ref_data))
|
||||
|
||||
# 번역된 기사 생성
|
||||
translated_article = FinalArticle(
|
||||
news_id=korean_article.get('news_id'), # 같은 news_id 사용
|
||||
title=translated_title,
|
||||
summary=translated_summary,
|
||||
subtopics=translated_subtopics,
|
||||
categories=translated_categories,
|
||||
entities=translated_entities,
|
||||
source_keyword=job.keyword if hasattr(job, 'keyword') else korean_article.get('source_keyword'),
|
||||
source_count=korean_article.get('source_count', 1),
|
||||
references=references,
|
||||
job_id=job.job_id,
|
||||
keyword_id=job.keyword_id if hasattr(job, 'keyword_id') else None,
|
||||
pipeline_stages=korean_article.get('pipeline_stages', []) + ['translation'],
|
||||
processing_time=korean_article.get('processing_time', 0),
|
||||
language=lang_config["code"],
|
||||
ref_news_id=None, # 같은 news_id 사용하므로 불필요
|
||||
rss_guid=korean_article.get('rss_guid'), # RSS GUID 유지
|
||||
image_prompt=korean_article.get('image_prompt'), # 이미지 프롬프트 유지
|
||||
images=korean_article.get('images', []), # 이미지 URL 리스트 유지
|
||||
translated_languages=korean_article.get('translated_languages', []) # 번역 언어 목록 유지
|
||||
)
|
||||
|
||||
# MongoDB에 저장
|
||||
collection_name = lang_config["collection"]
|
||||
result = await self.db[collection_name].insert_one(translated_article.model_dump())
|
||||
|
||||
logger.info(f"Article saved to {collection_name} with _id: {result.inserted_id}, language: {lang_config['code']}")
|
||||
|
||||
# 원본 기사에 번역 완료 표시
|
||||
await self.db[self.languages_config["source_language"]["collection"]].update_one(
|
||||
{"news_id": korean_article.get('news_id')},
|
||||
{
|
||||
"$addToSet": {
|
||||
"translated_languages": lang_config["code"]
|
||||
}
|
||||
}
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Error translating article to {lang_config['code']}: {e}")
|
||||
raise
|
||||
|
||||
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("Multi-Language Translator Worker stopped")
|
||||
|
||||
async def main():
|
||||
"""메인 함수"""
|
||||
worker = MultiLanguageTranslator()
|
||||
|
||||
try:
|
||||
await worker.start()
|
||||
except KeyboardInterrupt:
|
||||
logger.info("Received interrupt signal")
|
||||
finally:
|
||||
await worker.stop()
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
Reference in New Issue
Block a user