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 +1,29 @@
|
||||
[site]
|
||||
id = "yn.hrss"
|
||||
name = "云南省人力资源和社会保障厅"
|
||||
province = "云南省"
|
||||
city = "省级"
|
||||
employer = "云南省人力资源和社会保障厅"
|
||||
employer_type = "机关"
|
||||
tags = ["provincial"]
|
||||
allowed_domains = ["hrss.yn.gov.cn", "yn.gov.cn", "ynrsksw.com"]
|
||||
|
||||
[template]
|
||||
item_selector = "a"
|
||||
url_pattern = "NewsView\\.aspx"
|
||||
title_selector = "h1, h2, title"
|
||||
body_selector = "span#Body_ltl_newsContent, div#newsContent, div.view_content, div.detailContent, div.article-content"
|
||||
date_regex = "(\\d{4}[-/年]\\d{1,2}[-/月]\\d{1,2})"
|
||||
attachment_extensions = [".xlsx", ".xls", ".pdf", ".docx", ".doc", ".zip"]
|
||||
|
||||
[[channels]]
|
||||
id = "602"
|
||||
name = "事业单位公开招聘"
|
||||
start_url = "https://hrss.yn.gov.cn/NewsLsit.aspx?ClassID=602"
|
||||
tags = ["sydw"]
|
||||
|
||||
[[channels]]
|
||||
id = "458"
|
||||
name = "招考招聘公告"
|
||||
start_url = "https://hrss.yn.gov.cn/NewsLsit.aspx?ClassID=458"
|
||||
tags = ["gwy", "sydw"]
|
||||
Reference in New Issue
Block a user