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
This commit is contained in:
@@ -0,0 +1,24 @@
|
||||
[site]
|
||||
id = "yn.yuxi"
|
||||
name = "玉溪市人民政府"
|
||||
province = "云南省"
|
||||
city = "玉溪市"
|
||||
employer = "玉溪市相关用人单位"
|
||||
employer_type = "事业单位"
|
||||
tags = ["municipal"]
|
||||
allowed_domains = ["yuxi.gov.cn", "yxrc.cn", "mp.weixin.qq.com"]
|
||||
|
||||
[template]
|
||||
item_selector = ".common-list-container a"
|
||||
url_pattern = "(article\\.g|wz-detail|/yxs/rszk/\\d+|mp\\.weixin\\.qq\\.com)"
|
||||
title_selector = "h1, h2, title"
|
||||
body_selector = "div.view_content, div.content-txt, div#js_content, div.rich_media_content, div.article-content, div#content"
|
||||
date_regex = "(\\d{4}[-/年]\\d{1,2}[-/月]\\d{1,2})"
|
||||
attachment_extensions = [".xlsx", ".xls", ".pdf", ".docx", ".doc", ".zip"]
|
||||
|
||||
[[channels]]
|
||||
id = "rszk"
|
||||
name = "人事招考"
|
||||
start_url = "https://www.yuxi.gov.cn/yxs/rszk/"
|
||||
keywords = ["招聘", "招考", "选拔", "录用", "公示", "选聘", "考试"]
|
||||
tags = ["sydw", "gwy"]
|
||||
Reference in New Issue
Block a user