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:
bitfennec
2026-10-23 23:44:10 +08:00
commit 1059be1b62
61 changed files with 10489 additions and 0 deletions
+24
View File
@@ -0,0 +1,24 @@
[site]
id = "sc.myrsks"
name = "绵阳人事考试网"
province = "四川省"
city = "绵阳市"
employer = "绵阳市人事考试中心"
employer_type = "事业单位"
tags = ["sydw", "gwy", "municipal"]
allowed_domains = ["myrsks.com.cn", "mianyang.gov.cn"]
[template]
item_selector = "span.news_Title a"
url_pattern = "/newsDetail/\\d+\\.html"
title_selector = "h1, h2, title"
body_selector = "div.detailContent, div#content, div.content, div.article"
date_regex = "(\\d{4}[-/年]\\d{1,2}[-/月]\\d{1,2})"
attachment_extensions = [".xlsx", ".xls", ".pdf", ".docx", ".doc", ".zip"]
[[channels]]
id = ""
name = "招考公告"
start_url = "http://www.myrsks.com.cn/"
keywords = ["招聘", "考试", "公告", "公示", "选拔", "录用"]
tags = ["sydw", "gwy"]
+24
View File
@@ -0,0 +1,24 @@
[site]
id = "sc.zgrsks"
name = "自贡人事考试网"
province = "四川省"
city = "自贡市"
employer = "自贡市人力资源和社会保障局 / 考试评价中心"
employer_type = "事业单位"
tags = ["sydw", "gwy", "municipal"]
allowed_domains = ["zgrsks.com.cn", "zg.gov.cn"]
[template]
item_selector = "a"
url_pattern = "/newsDetail/\\d+\\.html"
title_selector = "h1, h2, title"
body_selector = "div.detailContent, div#content, div.content, 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 = ""
name = "招考公告"
start_url = "http://www.zgrsks.com.cn/"
keywords = ["招聘", "考试", "公告", "公示", "选拔", "录用"]
tags = ["sydw", "gwy"]