Files
bangwen/collectors/config.example.toml
T
bitfennec 1059be1b62 feat: initialize bangwen recruitment aggregation and search engine
- Rust core engine with HTTP ingestion gateway, hybrid search, and white-box resume matching
- Python edge collectors supporting declarative TOML and specialized adapters
- PostgreSQL schema migrations with pgvector embedding support
- Hardened security controls: strict CSP, terminal sanitization, and input boundary validation
- Multi-service container orchestration with dedicated non-root execution
2026-10-23 23:44:10 +08:00

32 lines
1.2 KiB
TOML

# ==============================================================================
# Bangwen 采集器配置文件模板 (TOML)
# ==============================================================================
[runner]
# 自动采集周期(小时)
schedule_interval_hours = 6
# 并发抓取的不同目标域名数(同一域名内部严格排队串行,防止政务网封禁 IP)
domain_concurrency = 3
# 同一域名下连续抓取不同栏目时的礼貌等待时间(秒)
domain_delay_seconds = 3.0
# 核心网关推流地址
core_ingest_url = "http://core:8080/api/v1/ingest"
[filter]
# 1. 启用的省份 (两字母代码,如 "yn", "sc";留空表示全部省份全量收录)
provinces = ["yn", "sc"]
# 2. 包含的来源通配符 (如 ["yn.*", "sc.chengdu.*"];留空表示不限制)
include = []
# 3. 来源站点性质标签 (如 ["sydw", "gwy", "provincial", "municipal"];留空表示不限制)
# 注意:医疗、教师等具体岗位通常包含在综合招考网中,采集层应保持全量抓取,
# 具体的医疗/教育岗位请在「检索端」或「推送端」按岗位内容/专业进行筛选。
tags = []
# 4. 排除的来源黑名单 (如 ["*.deprecated"];优先剔除)
exclude = []