业务联系侦察
- 作者仓库星标 0
- 作者仓库 nano-core
- 领域
- 数据
- 作者声明的智能体
- 未找到明确声明;不据此推断已兼容或已测试
- 静态检查
- 88 / 100 · 启发式扫描,不代表运行安全
- 运行环境证据
- 未执行;当前没有隔离运行测试证据
- 作者 / 版本 / 许可证
- @0-CYBERDYNE-SYSTEMS-0 · 未声明许可证
- 上下文用量评级
- 低消耗
- 接入复杂程度
- 即装即用
- 是否需要外部接口密钥
- 不需要
- 兼容的系统
- 未声明(默认跨平台)
- 运行环境要求
- Python
- 检测到的文件与系统行为
-
- 只读
- 允许写入 / 修改
- 网络行为
- 仅限本地
- 安装命令数
- 无(仅作为资料)
需要注意: 未声明工具权限范围;实际权限由运行环境决定。
第一阶段:发现
定义目标参数(地区、关键字、行业) 运行网络搜索以发现企业 按位置/相关性过滤 编译种子列表
第 2 阶段:验证
交叉引用每个企业: 社交存在(LinkedIn、网站、社交链接) 评论活动(Google、Yelp) 最近提及的内容(新闻、博客) 政府记录(国家商业登记处)
第三阶段:接触者提取
对于经过验证的企业:抓取网站联系页面(尊重 robots.txt) 查找 LinkedIn 公司页面 → 提取关键人员 使用基于模式的电子邮件猜测 (first@business.com)
第四阶段:输出
生成具有标准化字段的 CSV。
# Business Contact Reconnaissance Skill
## When not to use this skill
- Do not use when another skill is a better direct match for the task.
- Do not use when the request is outside this skill's scope.
## When to Use
Build targeted outreach lists using free public data sources:
- Sales lead generation by region/industry
- Business validation before contact attempts
- Discovering key personnel (owners, managers, decision-makers)
- Regional/niche market research
## Prerequisites
```bash
# Core dependencies
pip install requests beautifulsoup4 lxml python-dateutil
# Optional (for advanced extraction)
pip install linkedin-api # Free tier with limitations
```
**No paid APIs required.** All sources in this skill are free.
## Core Workflow
### Phase 1: Discovery
1. Define target parameters (region, keywords, industry)
2. Run web searches to discover businesses
3. Filter by location/relevance
4. Compile seed list
### Phase 2: Validation
Cross-reference each business:
- Social presence (LinkedIn, website, social links)
- Review activity (Google, Yelp)
- Recent mentions (news, blogs)
- Government records (state biz registries)
- Forum/community signals
### Phase 3: Contact Extraction
For validated businesses:
1. Scrape website contact pages (respect robots.txt)
2. Find LinkedIn company page → extract key personnel
3. Use pattern-based email guessing (first@business.com)
### Phase 4: Output
Generate CSV with standardized fields.
## Available Scripts
| Script | Purpose |
|--------|---------|
| `scripts/discover_businesses.py` | DuckDuckGo + web discovery |
| `scripts/validate_activity.py` | Multi-signal validation |
| `scripts/extract_contacts.py` | Contact extraction from websites |
| `scripts/linkedin_extract.py` | Free LinkedIn company/person data |
| `scripts/build_csv.py` | Generate CRM-ready CSV |
## Free Data Sources Priority
1. **Search engines**: DuckDuckGo (no tracking, no API limits)
2. **Business listings**: Google Maps, Yelp (public pages)
3. **Social**: LinkedIn (public profiles only, no scraping)
4. **Government**: State Secretary of State business databases
5. **Domains**: WHOIS lookup, website analysis
6. **News**: RSS feeds, Google News alerts
## Compliance & Safety
### ✅ Allowed (Free Tier)
- Public business listings and directories
- Website contact pages (respect rate limits)
- LinkedIn public profiles
- Government records (public domain)
- DuckDuckGo/Google search results
### ⚠️ Use Caution
- Website scraping: 1 req/sec max, respect robots.txt
- Email pattern guessing: verify before sending
- LinkedIn: no automation tools, manual data only
### ❌ Never Do
- Credential stuffing or account takeover
- Bypassing CAPTCHAs or rate limits
- Scraping behind login walls
- Harvesting personal phone numbers
- Using paid APIs you don't have keys for
## Output Format
```csv
business_name,website,phone,email,contact_name,title,linkedin_url,source,confidence,last_verified,notes
Joe's Plumbing,https://joesplumbing.com,555-0123,joe@joesplumbing.com,Joe Smith,Owner,,website+hunter,high,2026-02-06,"Local SEO present"
```
## Rate Limiting
- **Search engines**: 1 query per 3 seconds (DuckDuckGo is lenient)
- **Websites**: 1 request per second
- **LinkedIn**: Manual extraction only (no API/scripted access)
- **General**: Be respectful, don't impact target sites
## Reference Documentation
- [Free Data Sources](references/free_sources.md) - Detailed guide to all free APIs and databases
- [Industry Templates](references/industry_templates.md) - Pre-built search patterns by industry
- [Compliance Guidelines](references/compliance.md) - Do's and don'ts for ethical OSINT
- [CSV Schema](references/csv_schema.md) - Field definitions and validation rules
章节与文件索引
按说明文件中的顺序排列。
什么时候不应该使用这个技能
何时使用
先决条件
第一阶段:发现
第 2 阶段:验证
文件/命令 -> scripts/discover_businesses.py · scripts/validate_activity.py · scripts/extract_contacts.py · scripts/linkedin_extract.py · scripts/build_csv.py
内容校验值 -> 9a40d4ae8f38
当前原文的自动摘译,尚未人工审校。
什么时候不应该使用这个技能
当其他技能更适合该任务时,请勿使用。当请求超出该技能的范围时请勿使用。
何时使用
使用免费的公共数据源构建有针对性的外展列表: 按地区/行业生成销售线索 在尝试联系之前进行业务验证 发现关键人员(所有者、经理、决策者) 地区/利基市场研究
先决条件
无需付费 API。该技能的所有来源都是免费的。