李顺东
3acc0a9221
- Add comprehensive sequence diagrams documenting container startup, task initialization, and incremental crawling flow - Implement reverse-order crawling logic (from latest to oldest) to optimize performance by processing new data first - Add real-time Kafka message publishing after each batch filtering instead of waiting for task completion - Update progress tracking to store last_start_offset for accurate incremental crawling across sessions - Enhance crawler service with improved offset calculation and batch processing logic - Update configuration files to support new crawling parameters and Kafka integration - Add progress model enhancements to track crawling state and handle edge cases - Improve main application initialization to properly handle lifespan events and task auto-start This change enables efficient incremental data collection where new data is prioritized and published immediately, reducing latency and improving system responsiveness.
44 lines
980 B
YAML
44 lines
980 B
YAML
# 招聘数据采集服务配置文件
|
|
|
|
# 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: "13051331101"
|
|
password: "abc19910515"
|
|
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
|
|
- id: "task-id-3"
|
|
name: "任务3"
|
|
enabled: false
|
|
|
|
# Kafka配置
|
|
kafka:
|
|
bootstrap_servers: kafka:29092
|
|
topic: job_data
|
|
consumer_group: job_consumer_group
|
|
|
|
# 采集配置
|
|
crawler:
|
|
interval: 300 # 采集间隔(秒)
|
|
filter_days: 7 # 过滤天数
|
|
max_workers: 5 # 最大并行任务数
|
|
max_expired_batches: 3 # 连续过期批次阈值（首次采集时生效）
|
|
auto_start: true # 容器启动时自动开始采集
|
|
|
|
# 数据库配置
|
|
database:
|
|
path: data/crawl_progress.db
|