
Boss Job Search
- 297 installs
- 47 repo stars
- Updated February 12, 2026
- agentbay-ai/agentbay-skills
boss-job-search is an agent skill that automates BOSS Zhipin job discovery, filtering, and structured listing extraction via browser automation for developers who need to scope target roles and compare openings efficient
About
boss-job-search in agentbay-ai/agentbay-skills drives BOSS Zhipin (zhipin.com) job research through the wuying-agentbay-sdk and a bundled browser-use.py script. Agents execute natural-language step lists to search keywords such as AI Infra or Python engineer, apply filters like company size (10,000+ employees) or salary bands, and extract up to 15 listings per run with title, company, size, salary, location, publish date, and summary. Output is markdown tables plus optional aggregate stats (count, average and min/max salary). The skill documents three worked examples, captcha and timeout handling, and a 1–2 minute runtime expectation per search. Developers reach for boss-job-search when evaluating China's tech job market, comparing compensation bands, or building agent workflows that need structured job data without manual browsing. Triggers include requests to search Boss Zhipin, filter by company scale, or pull latest role requirements.
- BOSS Zhipin query automation
- Role filtering and ranking
- Application workflow assistance
- Candidate targeting scoping
- Search criteria refinement
Boss Job Search by the numbers
- 297 all-time installs (skills.sh)
- Ranked #490 of 2,715 Automation & Workflows skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/agentbay-ai/agentbay-skills --skill boss-job-searchAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 297 |
|---|---|
| repo stars | ★ 47 |
| Last updated | February 12, 2026 |
| Repository | agentbay-ai/agentbay-skills ↗ |
How do you automate BOSS Zhipin job search?
Automate BOSS Zhipin job discovery, filtering, and application prep so agents help candidates scope targets, compare roles, and draft tailored outreach efficiently.
Who is it for?
Developers job-hunting on BOSS Zhipin who want agent-driven keyword search, company-size filtering, and structured role comparison without manual browsing.
Skip if: Recruiters needing bulk applicant outreach, teams outside China without BOSS Zhipin access, or workflows requiring guaranteed login-free full job descriptions.
When should I use this skill?
User asks to search Boss Zhipin, filter jobs by company size or salary, or extract structured listings for a role keyword.
What you get
Markdown job listing tables, per-role metadata fields, and optional salary summary statistics from zhipin.com.
- Markdown job listing tables
- Salary summary statistics
- Structured role metadata
By the numbers
- Extracts up to 15 job listings per search run
- Documents 3 example search workflows in SKILL.md
- Typical browser automation runtime is 1–2 minutes per query
Files
Boss直聘职位搜索
依赖
python3 -m pip install wuying-agentbay-sdk安装步骤
在使用此技能之前,请确保已安装必要的依赖包:
python3 -m pip install wuying-agentbay-sdk使用场景
- 用户想搜索Boss直聘上的特定职位
- 用户想筛选特定公司规模的岗位
- 用户想了解某类职位的薪资范围和要求
- 用户想获取最新的职位招聘信息
使用方法
python3 scripts/browser-use.py "<任务执行步骤>"快速示例
示例1:搜索AI Infra工程师职位(公司规模10000人以上)
python3 scripts/browser-use.py " \
1. 前往Boss直聘网站 https://www.zhipin.com/ \
2. 等待页面加载完成,确认首页搜索框及导航栏显示正常 \
3. 定位顶部职位搜索框,输入关键词'AI Infra工程师' \
4. 点击搜索按钮(标注'搜索'或放大镜图标),进入职位列表页 \
5. 定位页面左侧筛选栏'公司规模'选项,展开下拉列表 \
6. 勾选'10000人以上'(若存在'10000人及以上'选项则勾选对应项) \
7. 等待页面自动刷新,筛选出符合公司规模条件的职位 \
8. 遍历前15条职位信息(若不足15条则获取全部) \
9. 提取每条职位的:职位名称、公司名称、公司规模、薪资范围、工作地点、职位发布时间、职位简介 \
10. 以markdown格式返回所有符合条件的职位信息
"示例2:搜索Python工程师职位(不限公司规模)
python3 scripts/browser-use.py " \
1. 访问Boss直聘 https://www.zhipin.com/ \
2. 在搜索框中输入'Python工程师' \
3. 点击搜索进入职位列表页 \
4. 提取前10条职位的详细信息 \
5. 以markdown格式整理返回
"示例3:搜索产品经理职位(筛选薪资和经验)
python3 scripts/browser-use.py " \
1. 打开Boss直聘网站 https://www.zhipin.com/ \
2. 搜索'产品经理' \
3. 在筛选栏中选择薪资范围'20-40K' \
4. 在筛选栏中选择经验要求'3-5年' \
5. 提取前15条符合条件的职位信息 \
6. 返回markdown格式的职位列表
"输出格式
## Boss直聘职位搜索 - [搜索关键词]
### 职位列表
1. **职位名称**
- 公司名称: xxx
- 公司规模: xxx人
- 薪资范围: xx-xxK
- 工作地点: xxx
- 发布时间: xxxx-xx-xx
- 职位简介: xxxxx
2. **职位名称**
- 公司名称: xxx
- 公司规模: xxx人
- 薪资范围: xx-xxK
- 工作地点: xxx
- 发布时间: xxxx-xx-xx
- 职位简介: xxxxx
### 统计信息
- 总计: xx条职位
- 平均薪资: xx-xxK
- 最高薪资: xxK
- 最低薪资: xxK异常处理
- 若搜索关键词无匹配职位,反馈"无相关职位",终止任务
- 若筛选栏选项不可选或页面异常,记录异常信息,尝试刷新页面后重试
- 若页面出现验证码,提示需要人工协助验证,暂停任务
- 若页面加载超时,增加等待时间或重新访问
注意事项
- 始终注明信息来源为Boss直聘
- 不需要创建新的脚本,用skill目录下的browser-use.py
- 如果页面加载较慢,请耐心等待
- 任务执行需要1~2分钟,请耐心等待观察,也不要重试
- skill调用后,控制台会打印出asp流化链接(可视化的url),可告知用户查看
- 职位信息会实时更新,以抓取时刻的数据为准
- 部分职位详情可能需要登录才能查看完整信息
- Boss直聘可能有反爬虫机制,遇到验证码请人工协助
import os
os.environ["AGENTBAY_LOG_LEVEL"]="CRITICAL"
import logging
logging.disable(logging.CRITICAL)
from agentbay import AgentBay
from agentbay import CreateSessionParams
import asyncio
def get_api_key():
from pathlib import Path
file_path = Path.home() / ".config" / "agentbay" / "api_key"
file_path.parent.mkdir(parents=True, exist_ok=True)
if not file_path.exists():
file_path.touch()
if os.environ.get("AGENTBAY_API_KEY"):
with open(file_path, "w", encoding="utf-8") as f:
f.write(os.environ.get("AGENTBAY_API_KEY"))
try:
with open(file_path, "r", encoding="utf-8") as f:
api_key = f.read().strip()
if not api_key:
api_key = None
except Exception as e:
api_key = None
return api_key
async def main():
import argparse
# 创建解析器
parser = argparse.ArgumentParser(description='wuying-browser-use')
# 添加参数
parser.add_argument('task', help='任务描述') # 位置参数(必需)
args = parser.parse_args()
api_key = get_api_key()
if not api_key:
raise RuntimeError(
"AGENTBAY_API_KEY environment variable is not set. "
"Please visit https://agentbay.console.aliyun.com/service-management to obtain your API key."
)
agent_bay = AgentBay(api_key=api_key)
# Create a session (use an image with browser preinstalled)
params = CreateSessionParams(image_id="browser_latest")
session_result = agent_bay.create(params)
if not session_result.success:
raise RuntimeError(f"Failed to create session: {session_result.error_message}")
session = session_result.session
print(f"asp流化链接: {session.resource_url}")
agent = session.agent
max_try_times = int(os.environ.get("AGENT_TASK_TIMEOUT", 200))
print(f"🚀 Executing task: {args.task}")
result = agent.browser.execute_task(args.task, use_vision=True)
if not result.success:
raise RuntimeError(f"Task execution failed: {result.error_message}")
# 轮询任务状态直到完成
retry_times = 0
query_result = None
while retry_times < max_try_times:
query_result = agent.browser.get_task_status(result.task_id)
if not query_result.success:
raise RuntimeError(f"Task status check failed: {query_result.error_message}")
print(
f"⏳ Task {query_result.task_id} status: {query_result.task_status}, "
f"action: {query_result.task_action}"
)
if query_result.task_status == "finished" or query_result.task_status == "failed":
break
retry_times += 1
await asyncio.sleep(3)
# 检查是否超时
if retry_times >= max_try_times:
raise TimeoutError("Task did not finish within the allowed time")
# 输出最终结果
logging.info(f"✅ Task completed successfully!")
logging.info(f"📊 Task result: {query_result.task_product}")
session.delete()
return query_result.task_product
result = asyncio.run(main())
print(f"Final result: {result}")
Related skills
How it compares
Pick boss-job-search for live BOSS Zhipin browser extraction; pick generic web-scraper skills when the target site is not zhipin.com.
FAQ
What data does boss-job-search extract?
boss-job-search returns markdown job tables with title, company, company size, salary range, location, publish date, and role summary for up to 15 listings per search run on zhipin.com.
How does boss-job-search run searches?
boss-job-search calls browser-use.py with a natural-language step list after installing wuying-agentbay-sdk, automating navigation, filters, and extraction on the BOSS Zhipin website.
What happens when BOSS Zhipin shows a captcha?
boss-job-search pauses and requests manual captcha assistance, then resumes extraction once verification completes, documenting this as expected anti-bot behavior on zhipin.com.