李顺东
ae681575b9
- Add technical documentation (技术方案.md) with system architecture and design details - Create FastAPI application structure with modular organization (api, core, models, services, utils) - Implement job data crawler service with incremental collection from third-party API - Add Kafka service integration with Docker Compose configuration for message queue - Create data models for job listings, progress tracking, and API responses - Implement REST API endpoints for data consumption (/consume, /status) and task management - Add progress persistence layer using SQLite for tracking collection offsets - Implement date filtering logic to extract data published within 7 days - Create API client service for third-party data source integration - Add configuration management with environment-based settings - Include Docker support with Dockerfile and docker-compose.yml for containerized deployment - Add logging configuration and utility functions for date parsing - Include requirements.txt with all Python dependencies and README documentation
40 lines
766 B
Docker
40 lines
766 B
Docker
# Docker环境配置文件
|
||
# 复制此文件为 config.yml 并修改账号密码
|
||
|
||
# 应用配置
|
||
app:
|
||
name: job-crawler
|
||
version: 1.0.0
|
||
debug: false
|
||
|
||
# 八爪鱼API配置
|
||
api:
|
||
base_url: https://openapi.bazhuayu.com
|
||
username: "your_username"
|
||
password: "your_password"
|
||
batch_size: 100
|
||
# 多任务配置
|
||
tasks:
|
||
- id: "00f3b445-d8ec-44e8-88b2-4b971a228b1e"
|
||
name: "青岛招聘数据"
|
||
enabled: true
|
||
- id: "task-id-2"
|
||
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
|
||
|
||
# 采集配置
|
||
crawler:
|
||
interval: 300
|
||
filter_days: 7
|
||
max_workers: 5
|
||
|
||
# 数据库配置
|
||
database:
|
||
path: /app/data/crawl_progress.db
|