zkr/ocups-kafka
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

rabbitmq

Browse Source
This commit is contained in:
李顺东
2026-01-15 21:20:57 +08:00
parent 0ed3c8f94d
commit 0976909cc8
14 changed files with 414 additions and 660 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
job_crawler/app/api/routes.py
View File

@@ -5,7 +5,7 @@ from typing import Optional
from fastapi import APIRouter, Query, BackgroundTasks, HTTPException
from fastapi.responses import StreamingResponse
from app.models import ApiResponse, ConsumeResponse, StatusResponse
from app.services import crawler_manager, kafka_service
from app.services import crawler_manager, rabbitmq_service
logger = logging.getLogger(__name__)
router = APIRouter()
@@ -84,29 +84,18 @@ async def stop_crawl(
@router.get("/consume", response_model=ConsumeResponse)
async def consume_data(
batch_size: int = Query(10, ge=1, le=100, description="批量大小"),
timeout: int = Query(5000, ge=1000, le=30000, description="超时时间(毫秒)")
batch_size: int = Query(10, ge=1, le=100, description="批量大小")
):
"""消费Kafka数据"""
"""消费RabbitMQ数据"""
try:
messages = kafka_service.consume(batch_size, timeout)
messages = rabbitmq_service.consume(batch_size)
return ConsumeResponse(data=messages, count=len(messages))
except Exception as e:
logger.error(f"消费数据失败: {e}")
raise HTTPException(status_code=500, detail=str(e))
@router.get("/consume/stream")
async def consume_stream():
"""SSE流式消费"""
async def event_generator():
consumer = kafka_service.get_consumer()
try:
for message in consumer:
data = json.dumps(message.value, ensure_ascii=False)
yield f"data: {data}\n\n"
except Exception as e:
logger.error(f"流式消费错误: {e}")
finally:
consumer.close()
return StreamingResponse(event_generator(), media_type="text/event-stream")
@router.get("/queue/size")
async def get_queue_size():
"""获取队列消息数量"""
return {"queue_size": rabbitmq_service.get_queue_size()}

15
job_crawler/app/core/config.py
View File

@@ -27,10 +27,13 @@ class ApiConfig(BaseModel):
tasks: List[TaskConfig] = []
class KafkaConfig(BaseModel):
bootstrap_servers: str = "localhost:9092"
topic: str = "job_data"
consumer_group: str = "job_consumer_group"
class RabbitMQConfig(BaseModel):
host: str = "localhost"
port: int = 5672
username: str = "guest"
password: str = "guest"
queue: str = "job_data"
message_ttl: int = 604800000 # 7天(毫秒)
class CrawlerConfig(BaseModel):
@@ -49,7 +52,7 @@ class Settings(BaseModel):
"""应用配置"""
app: AppConfig = AppConfig()
api: ApiConfig = ApiConfig()
kafka: KafkaConfig = KafkaConfig()
rabbitmq: RabbitMQConfig = RabbitMQConfig()
crawler: CrawlerConfig = CrawlerConfig()
database: DatabaseConfig = DatabaseConfig()
@@ -71,7 +74,7 @@ class Settings(BaseModel):
return cls(
app=AppConfig(**data.get('app', {})),
api=api_config,
kafka=KafkaConfig(**data.get('kafka', {})),
rabbitmq=RabbitMQConfig(**data.get('rabbitmq', {})),
crawler=CrawlerConfig(**data.get('crawler', {})),
database=DatabaseConfig(**data.get('database', {}))
)

4
job_crawler/app/main.py
View File

@@ -6,7 +6,7 @@ from fastapi import FastAPI
from app.core.config import settings
from app.core.logging import setup_logging
from app.api import router
from app.services import kafka_service
from app.services import rabbitmq_service
setup_logging()
logger = logging.getLogger(__name__)
@@ -28,7 +28,7 @@ async def lifespan(app: FastAPI):
logger.info("服务关闭中...")
from app.services import crawler_manager
crawler_manager.stop_all()
kafka_service.close()
rabbitmq_service.close()
app = FastAPI(

68
job_crawler/app/models/job.py
View File

@@ -1,60 +1,24 @@
"""招聘数据模型"""
from pydantic import BaseModel
from datetime import datetime
import uuid
class JobData(BaseModel):
"""招聘数据模型"""
id: str = ""
task_id: str = "" # 任务ID
job_category: str = "" # Std_class - 职位分类
job_title: str = "" # aca112 - 职位名称
company: str = "" # AAB004 - 公司名称
company_type: str = "" # AAB019 - 企业类型
salary: str = "" # acb241 - 薪资范围
location: str = "" # aab302 - 工作地点
address: str = "" # AAE006 - 详细地址
publish_date: str = "" # aae397 - 发布日期
collect_time: str = "" # Collect_time - 采集时间
url: str = "" # ACE760 - 职位链接
description: str = "" # acb22a - 职位描述
experience: str = "" # Experience - 经验要求
education: str = "" # aac011 - 学历要求
headcount: str = "" # acb240 - 招聘人数
industry: str = "" # AAB022 - 行业
company_size: str = "" # Num_employers - 公司规模
contact: str = "" # AAE004 - 联系人
company_intro: str = "" # AAB092 - 公司简介
crawl_time: str = "" # 入库时间
class JobData:
"""招聘数据 - 保留原始数据格式"""
def __init__(self, **data):
super().__init__(**data)
if not self.id:
self.id = str(uuid.uuid4())
if not self.crawl_time:
self.crawl_time = datetime.now().isoformat()
def __init__(self, raw_data: dict, task_id: str = ""):
self.raw_data = raw_data
self.task_id = task_id
# 添加元数据
self.raw_data["_id"] = str(uuid.uuid4())
self.raw_data["_task_id"] = task_id
self.raw_data["_crawl_time"] = datetime.now().isoformat()
def to_dict(self) -> dict:
"""转换为字典（原始数据 + 元数据）"""
return self.raw_data
@classmethod
def from_raw(cls, raw: dict) -> "JobData":
"""从原始API数据转换"""
return cls(
job_category=raw.get("Std_class", ""),
job_title=raw.get("aca112", ""),
company=raw.get("AAB004", ""),
company_type=raw.get("AAB019", "").strip(),
salary=raw.get("acb241", ""),
location=raw.get("aab302", ""),
address=raw.get("AAE006", ""),
publish_date=raw.get("aae397", ""),
collect_time=raw.get("Collect_time", ""),
url=raw.get("ACE760", ""),
description=raw.get("acb22a", ""),
experience=raw.get("Experience", ""),
education=raw.get("aac011", ""),
headcount=raw.get("acb240", ""),
industry=raw.get("AAB022", ""),
company_size=raw.get("Num_employers", ""),
contact=raw.get("AAE004", ""),
company_intro=raw.get("AAB092", ""),
)
def from_raw(cls, raw: dict, task_id: str = "") -> "JobData":
"""从原始API数据创建"""
return cls(raw.copy(), task_id)

2
job_crawler/app/models/progress.py
View File

@@ -18,7 +18,7 @@ class CrawlStatus(BaseModel):
total: int
last_start_offset: Optional[int] = None
progress: str
kafka_lag: int = 0
queue_size: int = 0
status: str
last_update: str
filtered_count: int = 0

4
job_crawler/app/services/__init__.py
View File

@@ -1,12 +1,12 @@
"""服务模块"""
from .api_client import api_client, BazhuayuClient
from .kafka_service import kafka_service, KafkaService
from .rabbitmq_service import rabbitmq_service, RabbitMQService
from .progress_store import progress_store, ProgressStore
from .crawler import crawler_manager, CrawlerManager, TaskCrawler
__all__ = [
"api_client", "BazhuayuClient",
"kafka_service", "KafkaService",
"rabbitmq_service", "RabbitMQService",
"progress_store", "ProgressStore",
"crawler_manager", "CrawlerManager", "TaskCrawler"
]

13
job_crawler/app/services/crawler.py
View File

@@ -4,7 +4,7 @@ import logging
from typing import Dict, Optional
from concurrent.futures import ThreadPoolExecutor
from app.services.api_client import api_client
from app.services.kafka_service import kafka_service
from app.services.rabbitmq_service import rabbitmq_service
from app.services.progress_store import progress_store
from app.utils import is_within_days
from app.models import JobData
@@ -134,21 +134,20 @@ class TaskCrawler:
aae397 = raw.get("aae397", "")
collect_time = raw.get("Collect_time", "")
if is_within_days(aae397, collect_time, self.filter_days):
job = JobData.from_raw(raw)
job.task_id = self.task_id
job = JobData.from_raw(raw, self.task_id)
filtered_jobs.append(job)
valid_count = len(filtered_jobs)
expired_count = len(data_list) - valid_count
self._total_filtered += valid_count
# 立即发送到Kafka
# 立即发送到RabbitMQ
produced = 0
if filtered_jobs:
produced = kafka_service.produce_batch(filtered_jobs)
produced = rabbitmq_service.produce_batch(filtered_jobs)
self._total_produced += produced
logger.info(f"[{self.task_name}] offset={offset}, 获取={len(data_list)}, 有效={valid_count}, 过期={expired_count}, 发送Kafka={produced}")
logger.info(f"[{self.task_name}] offset={offset}, 获取={len(data_list)}, 有效={valid_count}, 过期={expired_count}, 发送MQ={produced}")
return valid_count
@@ -236,7 +235,7 @@ class CrawlerManager:
return crawler.get_status() if crawler else {}
return {
"tasks": [c.get_status() for c in self._crawlers.values()],
"kafka_lag": kafka_service.get_lag(),
"queue_size": rabbitmq_service.get_queue_size(),
"running_count": sum(1 for c in self._crawlers.values() if c.is_running)
}

3
job_crawler/app/services/kafka_service.py
View File

@@ -66,7 +66,8 @@ class KafkaService:
def produce(self, job_data: JobData) -> bool:
"""发送消息到Kafka"""
try:
future = self.producer.send(self.topic, key=job_data.id, value=job_data.model_dump())
data = job_data.to_dict()
future = self.producer.send(self.topic, key=data.get("_id"), value=data)
future.get(timeout=10)
return True
except KafkaError as e:

13
job_crawler/config/config.yml
View File

@@ -24,11 +24,14 @@ api:
name: "任务3"
enabled: false
# Kafka配置
kafka:
bootstrap_servers: kafka:29092
topic: job_data
consumer_group: job_consumer_group
# RabbitMQ配置
rabbitmq:
host: rabbitmq
port: 5672
username: guest
password: guest
queue: job_data
message_ttl: 604800000 # 消息过期时间：7天(毫秒)
# 采集配置
crawler:

13
job_crawler/config/config.yml.docker
View File

@@ -22,11 +22,14 @@ api:
name: "任务2"
enabled: false
# Kafka配置（Docker内部网络）
kafka:
bootstrap_servers: kafka:29092
topic: job_data
consumer_group: job_consumer_group
# RabbitMQ配置
rabbitmq:
host: rabbitmq
port: 5672
username: guest
password: guest
queue: job_data
message_ttl: 604800000 # 消息过期时间：7天(毫秒)
# 采集配置
crawler:

51
job_crawler/docker-compose.yml
View File

@@ -1,51 +1,23 @@
version: '3.8'
services:
zookeeper:
image: confluentinc/cp-zookeeper:7.5.0
container_name: job-zookeeper
rabbitmq:
image: rabbitmq:3.12-management
container_name: job-rabbitmq
ports:
- "2181:2181"
- "5672:5672"
- "15672:15672"
environment:
ZOOKEEPER_CLIENT_PORT: 2181
ZOOKEEPER_TICK_TIME: 2000
RABBITMQ_DEFAULT_USER: guest
RABBITMQ_DEFAULT_PASS: guest
volumes:
- zookeeper_data:/var/lib/zookeeper/data
- rabbitmq_data:/var/lib/rabbitmq
healthcheck:
test: ["CMD", "nc", "-z", "localhost", "2181"]
test: ["CMD", "rabbitmq-diagnostics", "check_running"]
interval: 10s
timeout: 5s
retries: 5
networks:
- job-network
kafka:
image: confluentinc/cp-kafka:7.5.0
container_name: job-kafka
ports:
- "9092:9092"
- "29092:29092"
environment:
KAFKA_BROKER_ID: 1
KAFKA_ZOOKEEPER_CONNECT: zookeeper:2181
KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://kafka:29092,PLAINTEXT_HOST://localhost:9092
KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: PLAINTEXT:PLAINTEXT,PLAINTEXT_HOST:PLAINTEXT
KAFKA_INTER_BROKER_LISTENER_NAME: PLAINTEXT
KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
KAFKA_AUTO_CREATE_TOPICS_ENABLE: "true"
volumes:
- kafka_data:/var/lib/kafka/data
depends_on:
zookeeper:
condition: service_healthy
healthcheck:
test: ["CMD", "kafka-topics", "--bootstrap-server", "localhost:9092", "--list"]
interval: 10s
timeout: 10s
retries: 5
networks:
- job-network
app:
image: job-crawler:latest
container_name: job-crawler
@@ -57,7 +29,7 @@ services:
- ./config:/app/config:ro
- app_data:/app/data
depends_on:
kafka:
rabbitmq:
condition: service_healthy
restart: unless-stopped
networks:
@@ -68,6 +40,5 @@ networks:
driver: bridge
volumes:
zookeeper_data:
kafka_data:
rabbitmq_data:
app_data:

3
job_crawler/requirements.txt
View File

@@ -1,8 +1,7 @@
fastapi==0.109.0
uvicorn==0.27.0
httpx==0.27.0
kafka-python==2.0.2
pika==1.3.2
apscheduler==3.10.4
pydantic==2.5.3
python-dotenv==1.0.0
PyYAML==6.0.1