← 返回 Skills 市场
jarryk

Job Search

作者 JarryK · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
78
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install china-job-search
功能描述
中国招聘平台搜索技能。支持BOSS直聘、智联招聘、前程无忧三大平台，提供关键词搜索、地点筛选、薪资范围过滤等功能。专门针对中国本土招聘市场设计。
使用说明 (SKILL.md)

招聘搜索技能

功能概述

专门用于在中国主流招聘平台（BOSS直聘、智联招聘、前程无忧）搜索岗位信息的技能。支持多条件筛选和结构化结果展示。

🚀 快速开始

基础搜索

搜索 [关键词] [地点]
示例：搜索 Python开发 北京

高级搜索

搜索 [关键词] [地点] [薪资下限]-[薪资上限]K [经验要求]
示例：搜索 Java开发 上海 15-30K 3-5年

平台指定搜索

搜索 [平台] [关键词] [地点]
示例：搜索 boss Python 北京
示例：搜索 智联 前端 上海
示例：搜索 前程无忧 测试 广州

📋 使用说明

搜索参数

  • 关键词: 职位名称或技能关键词
  • 地点: 城市名称（如：北京、上海、广州、深圳）
  • 薪资范围: 格式为"下限-上限K"（如：15-30K）
  • 经验要求: 格式为"下限-上限年"（如：3-5年）

支持平台

  1. BOSS直聘 (boss/zhipin) - 最活跃的互联网招聘平台
  2. 智联招聘 (zhilian/zhaopin) - 传统综合性招聘平台
  3. 前程无忧 (qiancheng/51job) - 大型综合招聘平台

🔧 技术实现

核心文件

  • scripts/job_searcher.py - 主搜索逻辑
  • scripts/boss_parser.py - BOSS直聘解析器
  • scripts/zhilian_parser.py - 智联招聘解析器
  • scripts/qiancheng_parser.py - 前程无忧解析器

依赖库

requests>=2.28.0
beautifulsoup4>=4.11.0
fake-useragent>=1.4.0

安装依赖

pip install -r scripts/requirements.txt

📊 输出格式

搜索结果以结构化表格形式展示，包含以下字段：

  • 平台
  • 职位标题
  • 公司名称
  • 薪资范围
  • 工作地点
  • 经验要求
  • 学历要求
  • 关键技能
  • 发布时间
  • 详情链接

⚠️ 注意事项

  1. 遵守平台规则: 尊重各平台的robots.txt，避免频繁请求
  2. 合理使用: 搜索结果仅供参考，请以官方信息为准
  3. 隐私保护: 不存储用户个人信息
  4. 延迟设置: 自动添加请求延迟，避免被封IP

🔄 更新日志

v1.0.0 (初始版本)

  • 支持三大主流招聘平台
  • 实现基础搜索和高级搜索
  • 结构化结果展示
  • 多条件筛选功能

📁 文件结构

job-search/
├── SKILL.md              # 技能说明文档
├── scripts/              # Python脚本目录
│   ├── job_searcher.py   # 主搜索逻辑
│   ├── boss_parser.py    # BOSS直聘解析器
│   ├── zhilian_parser.py # 智联招聘解析器
│   ├── qiancheng_parser.py # 前程无忧解析器
│   ├── config.json       # 配置文件
│   └── requirements.txt  # 依赖库列表
└── references/           # 参考文档
    └── API_REFERENCE.md  # API接口说明

💡 使用示例

示例1：简单搜索

用户：搜索 Python开发 北京
技能：正在搜索BOSS直聘、智联招聘、前程无忧的Python开发岗位（北京）...

示例2：高级搜索

用户：搜索 Java开发 上海 20-40K 5-8年
技能：正在搜索Java开发岗位（上海），薪资20-40K，经验5-8年...

示例3：指定平台

用户：搜索 boss 前端 杭州
技能：正在搜索BOSS直聘的前端开发岗位（杭州）...

🛠️ 开发指南

如需扩展功能或添加新平台，请参考：

  1. 在scripts/目录下创建新的解析器
  2. 在job_searcher.py中注册新平台
  3. 更新config.json配置文件
  4. 测试新功能并更新文档
安全使用建议
This package is functionally coherent for scraping Chinese job sites, but it goes beyond simple query/formatting: it includes instructions and code for saving raw HTML, persisting results to DB/files, scheduling repeated searches, sending notifications, and explicitly suggests proxies and Selenium to evade anti-bot defenses. Before installing or running: 1) Review the Python scripts (especially any that call requests.get, write files, use proxies or schedule tasks) and run them in a sandboxed environment. 2) Do not supply production credentials (SMTP, proxy) unless you trust the source; prefer ephemeral test credentials. 3) Ensure you comply with each target site's robots.txt and terms of service — the code shows explicit evasion strategies which may be illegal or breach ToS. 4) If you only need one-off, read-only queries, restrict use to simple search scripts (e.g., demo_simple.py) and avoid enabling scheduled jobs or Selenium/proxy code. 5) Because the skill author/source is unknown, prefer obtaining similar functionality from a vetted/trusted repository or review the code thoroughly before granting it network access or enabling autonomous invocation.
能力评估
ℹ Purpose & Capability
Name/description (search BOSS/智联/51job) align with the shipped code: multiple platform parsers, JobSearcher, and run/test scripts. The declared dependencies (requests, BeautifulSoup, fake-useragent) match scraping functionality. However the repository also contains production/optimized searchers, persistence (SQLite/file export), email notification examples, proxy support and explicit suggestions to use Selenium/proxies to bypass anti-scraping — capabilities beyond a minimal search helper. Those extra capabilities are plausible for a production scraper but are broader than a simple 'search' skill and deserve attention.
⚠ Instruction Scope
SKILL.md itself stays on-topic (how to query and install deps), but additional documentation and scripts (DEPLOYMENT_GUIDE, direct_test, analyze_51job, many searcher variants) instruct the user how to: save raw HTML to disk, rotate User-Agent, use proxies, add delays, run Selenium to bypass anti-bot, persist results, schedule periodic tasks, and send email notifications. These instructions expand scope from one-off queries to persistent, automated scraping that can evade protections. The skill does not instruct reading unrelated system secrets, but it does write files and can persist/search data locally.
✓ Install Mechanism
There is no install spec; it's an instruction-and-code bundle. Dependencies are standard Python scraping libraries (requests, bs4, fake-useragent) listed in a requirements.txt. No downloads from untrusted URLs or archive extraction were observed in the provided metadata. Risk is primarily from running the Python code itself, not from an external installer.
ℹ Credentials
The skill declares no required environment variables or credentials, which is consistent with basic scraping. However multiple files show optional support for proxies and an email-notification function (smtplib example) and examples referencing SMTP/proxy endpoints. Those features would require credentials/configuration if used but are not declared as required — a mild mismatch. No evidence of the skill attempting to read hidden system credential paths or other skills' configs was found.
ℹ Persistence & Privilege
always:false (normal). The code includes examples and utilities to persist results (SQLite, JSON, CSV), write saved HTML pages to disk, export files, and create scheduled tasks that run periodic searches and append to local files. It does not appear to modify other skills or global agent settings. Autonomous invocation is allowed by default; combined with scheduling/persistence and the documented guidance for evasion, that increases the potential blast radius if you enable automated runs.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install china-job-search
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /china-job-search 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
china-job-search v1.0.0 初始发布 - 支持在BOSS直聘、智联招聘、前程无忧三大平台进行职位搜索 - 提供关键词、地点、薪资范围、经验等多条件筛选功能 - 实现基础搜索、高级搜索和平台指定搜索 - 输出结构化、表格化的岗位信息 - 自动请求延迟，保护用户隐私并避免频繁请求
元数据
Slug china-job-search
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Job Search 是什么？

中国招聘平台搜索技能。支持BOSS直聘、智联招聘、前程无忧三大平台，提供关键词搜索、地点筛选、薪资范围过滤等功能。专门针对中国本土招聘市场设计。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 78 次。

如何安装 Job Search？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install china-job-search」即可一键安装，无需额外配置。

Job Search 是免费的吗？

是的，Job Search 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Job Search 支持哪些平台？

Job Search 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Job Search？

由 JarryK（@jarryk）开发并维护，当前版本 v1.0.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463815 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259802 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200680 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191345 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190333 · by oswalpalash

💬 留言讨论