Boss Zhipin Scraper

What it does

When your agent uses it

• User wants to search/analyze jobs on BOSS直聘
• Tasks that involve Web scraping

Example prompts

• “/boss-zhipin-scraper”

Requirements

• Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1创建或复用持久隔离 Chrome profile
2. 2只关闭使用该隔离 profile 的旧 BOSS CDP Chrome，不关闭用户主 Chrome
3. 3以 CDP 模式启动 Chrome（--remote-debugging-port=9222）
4. 4等待 CDP 端口就绪（最多 30 秒）
5. 5打开 BOSS 登录页并等待登录完成，直到搜索接口返回明文 salaryDesc

What it can do on your machine

Read from SKILL.md and the folder at commit 573addc. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/, which the agent can run.

  Shell commands in SKILL.md call:

  • python3
  • curl
  • uv
  • pip
  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • zhipin.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Boss Zhipin Scraper loads about 2.6k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 572 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~77

When it runs · the whole SKILL.md, loaded when a task matches

~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from eatmoreduck/boss-zhipin-scraper at commit 573addc, republished under its MIT licence (© eatmoreduck). 572 words, ~2,628 tokens.

name

boss-zhipin-scraper

description

Scrape BOSS直聘 (job listing site) via Chrome CDP. Searches jobs by keyword/city/filters, fetches JD details, outputs structured JSON/CSV with plaintext salary, and can summarize scraped results into a job-market prompt. Use when user wants to search/analyze jobs on BOSS直聘 or zhipin.com.

version

2.3.0

author

eatmoreduck

license

MIT

platforms

macos, linux

# 方法 1：已知 skill 安装目录（推荐，macOS/Linux 通用）
SKILL_DIR="$(python3 -c "import os,sys;print(os.path.dirname(os.path.realpath(sys.argv[1])))" "$0")"
SCRIPT_PATH="$SKILL_DIR/scripts/boss_cdp_raw.py"
SUMMARY_PATH="$SKILL_DIR/scripts/job_summary.py"

# 方法 2：搜索 hermes skills 目录
SCRIPT_PATH=$(find ~/.hermes/skills -name "boss_cdp_raw.py" -type f 2>/dev/null | head -1)
SUMMARY_PATH=$(find ~/.hermes/skills -name "job_summary.py" -type f 2>/dev/null | head -1)

uv add websocket-client requests
# 或
pip install websocket-client requests

python3 "$SCRIPT_PATH" --check --cdp-port 9222

python3 "$SCRIPT_PATH" --setup-chrome --cdp-port 9222

python3 "$SCRIPT_PATH" --setup-edge --cdp-port 9222

python3 "$SCRIPT_PATH" --setup-chrome --copy-login-state --cdp-port 9222

# 基础搜索
python3 "$SCRIPT_PATH" --keyword "关键词" --city 城市 --pages 3 --output ~/.boss-zhipin-scraper/job-result/jobs.json

# 带 CSV 输出
python3 "$SCRIPT_PATH" --keyword "关键词" --city 城市 --pages 3 --format csv --output ~/.boss-zhipin-scraper/job-result/jobs.json

# 带详情 + 分析报告
python3 "$SCRIPT_PATH" --keyword "关键词" --city 城市 --pages 3 --detail --max-details 8 --analysis --format csv --output ~/.boss-zhipin-scraper/job-result/jobs.json

# 抓取后摘要 + 求职材料优化提示词（默认读取最新抓取结果）
python3 "$SUMMARY_PATH" --top 15

# 真实浏览器/API smoke test（不写结果文件）
python3 "$SCRIPT_PATH" --smoke-test --cdp-port 9222

# 合并多次抓取（去重）
python3 "$SCRIPT_PATH" --keyword "关键词" --city 北京 --pages 3 --merge ~/.boss-zhipin-scraper/job-result/jobs.json --output ~/.boss-zhipin-scraper/job-result/jobs_merged.json

# 关闭 BOSS 专用 Chrome（只关隔离 profile，不碰主 Chrome）
python3 "$SCRIPT_PATH" --stop-chrome --cdp-port 9222

# 或：让本次抓取正常结束就自动关闭
python3 "$SCRIPT_PATH" --keyword "关键词" --city 城市 --pages 3 --close-chrome

python3 "$SUMMARY_PATH" \
  --input ~/.boss-zhipin-scraper/job-result/boss_jobs_20260625_1200.json \
  --details ~/.boss-zhipin-scraper/job-result/boss_details_20260625_1200.json \
  --top 15

{
  "keyword": "AI Agent",
  "city": "上海",
  "total": 60,
  "jobs": [
    {
      "job_id": "c4420e8bce3a6e25",
      "title": "AI Agent工程师",
      "salary": "30-60K·15薪",
      "location": "上海·闵行区·虹桥",
      "tags": "5-10年 | 本科",
      "boss_name": "SHEIN",
      "boss_title": "招聘者",
      "company_scale": "10000人以上",
      "company_stage": "D轮及以上",
      "company_industry": "电子商务",
      "skills": "Java | Spring | AI",
      "job_link": "https://www.zhipin.com/job_detail/xxx.html",
      "company_link": "https://www.zhipin.com/gongsi/xxx.html",
      "welfare": "节日福利 | 零食下午茶 | 定期体检"
    }
  ]
}

python3 "$SCRIPT_PATH" --setup-chrome --reset-chrome-profile --cdp-port 9222

# 推荐：curl 一键安装
mkdir -p ~/.hermes/skills/data-science/boss-zhipin-scraper/scripts && \
curl -sL https://raw.githubusercontent.com/eatmoreduck/boss-zhipin-scraper/master/SKILL.md \
  -o ~/.hermes/skills/data-science/boss-zhipin-scraper/SKILL.md && \
curl -sL https://raw.githubusercontent.com/eatmoreduck/boss-zhipin-scraper/master/scripts/boss_cdp_raw.py \
  -o ~/.hermes/skills/data-science/boss-zhipin-scraper/scripts/boss_cdp_raw.py && \
curl -sL https://raw.githubusercontent.com/eatmoreduck/boss-zhipin-scraper/master/scripts/job_summary.py \
  -o ~/.hermes/skills/data-science/boss-zhipin-scraper/scripts/job_summary.py && \
mkdir -p ~/.hermes/skills/data-science/boss-zhipin-scraper/data && \
curl -sL https://raw.githubusercontent.com/eatmoreduck/boss-zhipin-scraper/master/data/city_codes.json \
  -o ~/.hermes/skills/data-science/boss-zhipin-scraper/data/city_codes.json

git clone https://github.com/eatmoreduck/boss-zhipin-scraper.git
mkdir -p ~/.hermes/skills/data-science/boss-zhipin-scraper/scripts
cp boss-zhipin-scraper/SKILL.md ~/.hermes/skills/data-science/boss-zhipin-scraper/
cp boss-zhipin-scraper/scripts/boss_cdp_raw.py ~/.hermes/skills/data-science/boss-zhipin-scraper/scripts/
cp boss-zhipin-scraper/scripts/job_summary.py ~/.hermes/skills/data-science/boss-zhipin-scraper/scripts/
mkdir -p ~/.hermes/skills/data-science/boss-zhipin-scraper/data
cp boss-zhipin-scraper/data/city_codes.json ~/.hermes/skills/data-science/boss-zhipin-scraper/data/

© eatmoreduck, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 24 other files (scripts, assets) in the repository root of eatmoreduck/boss-zhipin-scraper.

• SKILL.md
• .github/ISSUE_TEMPLATE/bug_report.yml
• .github/ISSUE_TEMPLATE/feature_request.yml
• .github/ISSUE_TEMPLATE/question.yml
• .github/workflows/ci.yml
• .github/workflows/pullfrog.yml
• .gitignore
• AGENTS.md
• CHANGELOG.md
• CONTRIBUTING.md
• LICENSE
• README.en.md
• README.md
• assets/reward-qr.png
• cover.png
• data/city_codes.json
• … and 9 more

Open the folder on GitHubat commit 573addc