以下为本文档的中文说明企业联系信息与社交媒体链接提取技能能够自动从公开网络中提取企业的官方网站和社交媒体主页信息。它集成了两种 BrowserAct 模板以覆盖两种常见场景当用户提供公司名称时它通过 Google 搜索定位该公司的官方网站和社交渠道当用户提供网站 URL 时它直接抓取该页面中的社交媒体链接。使用场景非常广泛市场调研人员需要收集竞品的全平台社交媒体布局时销售团队需要为潜在客户建立联系数据库时招聘人员需要查找目标公司的人才品牌建设渠道时公关人员需要了解媒体对某品牌的跨平台覆盖情况时以及内容营销人员需要跟踪竞品的内容分发策略时。核心特点包括三个方面。首先是无需处理验证码——通过预设的工作流避免了 AI 幻觉和 CAPTCHA 验证问题确保数据提取的稳定性和准确性。其次是无需担心 IP 限制——设计上规避了区域 IP 封锁问题可以跨地域提取公开信息。第三是模板自动路由——系统会自动检测输入类型公司名还是网址并选择对应的处理模板。技能重点关注 LinkedIn、Facebook、X/Twitter、Instagram、YouTube、TikTok 等主流社交平台的主页 URL 提取输出格式统一便于后续导入 CRM 系统或联系数据库。它为商业情报收集提供了一个可靠的自动化入口。Business Contact Social Links Extractor Skill BriefThis skill integrates two BrowserAct templates to cover two common scenarios. When the user provides acompany name, it searches Google to extract the company’s official website and social media channels. When the user provides awebsite URL, it scrapes the site to extract social media profile links (LinkedIn, Facebook, X/Twitter, Instagram, YouTube, TikTok). The script auto-detects the input type and routes to the correct template.✨ FeaturesNo Hallucinations: Pre-set workflows avoid AI generative hallucinations, ensuring stable and precise data extraction.No Captcha Issues: No need to handle reCAPTCHA or other verification challenges.No IP Restrictions: No need to handle regional IP restrictions or geofencing.Faster Execution: Tasks execute faster compared to pure AI-driven browser automation solutions.Cost-Effective: Significantly lowers data acquisition costs compared to high-token-consuming AI solutions. API Key SetupBefore running, check theBROWSERACT_API_KEYenvironment variable. If not set, do not take other measures; ask and wait for the user to provide it.Agent must inform the user:“Since you haven’t configured the BrowserAct API Key yet, please visit the BrowserAct Console to get your Key.”️ Input ParametersThe agent should determine whether the input is a company name or a website URL and pass it to the script. The script automatically routes the request to the correct template.Target (Company Name or Website URL)Required: YesType:stringDescription: The name of the company to search for, or the direct website URL to scrape social links from.Example:OpenAIorhttps://www.rotorooter.com/ Invocation MethodAgent should execute the following command to invoke the skill:# Search by company namepython-u./scripts/business_contact_social_links.pyOpenAI# Scrape by website URLpython-u./scripts/business_contact_social_links.pyhttps://www.rotorooter.com/⏳ Execution MonitoringSince this task involves automated browser operations, it may take several minutes. The script outputstimestamped status logscontinuously (e.g.,[14:30:05] Task Status: running).Agent guidelines:Monitor the terminal output while waiting.As long as new status logs appear, the task is running normally; do not misjudge it as frozen.Only consider triggering retry if the status remains unchanged for a long time or output stops without a final result. Data OutputUpon successful execution, the script prints structured JSON data extracted from the API response.If a Company Name was provided, the output includes:Company Name: The official name of the company.Current Page URL: The official website URL.Social Media Information: A consolidated list of discovered social media profiles.If a Website URL was provided, the output includes an array of objects:platform: Platform name (e.g., LinkedIn, YouTube).url: Canonical URL of the external profile.⚠️ Error Handling RetryIf an error occurs during script execution (e.g., network fluctuations or task failure), the Agent should follow this logic:Check Output Content:If the outputcontainsInvalid authorization, it means the API Key is invalid or expired.Do not retry; guide the user to re-check and provide the correct API Key.If the outputcontainsconcurrentortoo many running tasks, it means the concurrent task limit has been reached.Do not retry; guide the user to upgrade their plan.Agent must inform the user:“The current task cannot be executed because your BrowserAct account has reached the concurrent task limit. Please visit the BrowserAct Plan Upgrade Page to upgrade your plan.”If the outputdoes not contain the above error keywordsbut the task failed (e.g., output starts withError:or returns empty results), the Agent shouldautomatically re-execute the script once.Retry Limit:Automatic retry is limited toone time. If the second attempt fails, stop retrying and report the specific error to the user. Typical Use CasesSales Lead Enrichment: Find the official website and social channels for a list of company names.Influencer Outreach: Extract all social media profiles from a creator’s personal website.Competitor Analysis: Discover which social media platforms a rival company prioritizes.CRM Data Cleaning: Verify and populate missing social links and official URLs for existing leads.Multi-Channel Marketing: Build targeted lists of businesses with active social media presence.Social Listening Setup: Quickly gather official handles to monitor brand mentions.B2B Prospecting: Combine with Yellow Pages data to build complete business intelligence profiles.Partner Vetting: Evaluate the digital footprint of a potential business partner using just their name.Directory Building: Automate the collection of website and social links for a local business directory.Brand Tracking: Track all official contact channels of specific brands across the web.
