← 返回 Skills 市场
Social Media Content Scraper Pro
作者
baolige2023
· GitHub ↗
· v1.0.0
· MIT-0
132
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install wechat-content-scraper-intl
功能描述
Social Media Content Bulk Scraper, extract articles/posts from WeChat, Instagram, TikTok, YouTube, export to Markdown/HTML with full metadata. $0.005 USDT pe...
安全使用建议
This skill is inconsistent and risky in several ways. Before installing or running it: 1) Don't trust the embedded API key/SECRET_KEY — treat them as exposed. Ask the author to remove hard-coded secrets and require credentials via environment variables. 2) Confirm provenance and the SkillPay billing integration (whose API key is embedded) — avoid using that key; use your own account or sandbox. 3) Expect the backend to be WeChat-only and mostly simulated, despite UI claims for other platforms — request a clear feature matrix and working endpoints. 4) Run the code in an isolated sandbox (no sensitive network access, no production credentials) to inspect runtime behavior. 5) Require dependency listing (requirements.txt) and fix mismatched frontend/backend routes and obvious bugs (e.g., missing timedelta import). 6) Consider legal/ToS risks: bulk scraping social platforms may violate terms of service or copyright law. If you need a reliable scraper, ask the developer for a corrected, dependency-declared release, removal/rotation of embedded secrets, and proof that external billing/account keys are legitimate.
功能分析
Type: OpenClaw Skill
Name: wechat-content-scraper-intl
Version: 1.0.0
The skill bundle is classified as suspicious because it implements a mandatory payment gate and hardcodes a sensitive API key ('SKILLPAY_API_KEY') and 'SECRET_KEY' in 'scripts/app.py', while the core functionality is deceptive. The scraping logic in 'scripts/app.py' consists entirely of mock data despite the 'Pro' branding and USDT pricing mentioned in 'SKILL.md'. Additionally, the frontend ('templates/index.html') and backend are functionally disconnected, with JavaScript calling non-existent routes like '/start' and '/tasks', suggesting the bundle is either a broken template or a low-effort attempt to solicit payments for non-functional software.
能力评估
Purpose & Capability
The README and UI advertise scraping WeChat, Instagram, TikTok, YouTube, and Twitter/X, but the server code only accepts and simulates mp.weixin.qq.com (WeChat) URLs and returns generated sample content. The frontend templates list multiple platforms, but backend route names and behavior are inconsistent (frontend calls endpoints like /start, /tasks, /task while backend defines /create_task, /task_status/<id>, /articles/<id>, etc.). This mismatch means the skill does not implement the multi-platform capabilities it advertises.
Instruction Scope
SKILL.md instructs a payment flow and entering profile URLs, which aligns with the included app, but the code will run a Flask web server, accept arbitrary profile URLs, download and store scraped content and images to a local data folder, and call external billing endpoints. The skill claims '100% safe and secure local data storage' despite storing arbitrary external HTML/content locally and serving it back via templates (possible XSS or serving of copyrighted/private content). Also the SKILL.md tells reviewers to 'review included files' — the code contains logic that will perform network calls and file writes not fully disclosed in SKILL.md.
Install Mechanism
There is no install specification even though the code imports third-party Python packages (requests, bs4/BeautifulSoup, pandas). Missing dependency declarations means runtime surprises. There is no external download/install step (low supply-chain risk), but the skill runs a web server and writes data to a local data directory — behavior not captured by an install manifest.
Credentials
The skill declares no required environment variables, yet the code contains hard-coded sensitive values: a SECRET_KEY and a SKILLPAY_API_KEY embedded in the source. Hard-coded API keys are a red flag (exposes credentials and indicates the skill will communicate with an external billing service). No justification is provided for embedding secrets or for not using environment variables. The skill also makes outbound HTTP requests to skillpay.me and arbitrary profile URLs.
Persistence & Privilege
always:false (default) and the skill does not request elevated platform privileges. It persists data in a local data directory and runs a Flask app; this is normal for a web tool but means the agent will create files and open a listening web interface if executed. That persistence is not inherently malicious but increases blast radius if combined with embedded secrets or network access.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install wechat-content-scraper-intl - 安装完成后，直接呼叫该 Skill 的名称或使用
/wechat-content-scraper-intl触发 - 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
Initial release of Social Media Content Scraper Pro.
- Bulk scraping for WeChat, Instagram, TikTok, and YouTube official accounts/profiles.
- Exports content to Markdown, HTML, or plain text with full metadata.
- Supports auto deduplication and batch image download.
- Offers local data storage for privacy and a simple, no-code user interface.
- Pricing: $0.005 USDT per scrape or $4.99 lifetime unlimited access.
元数据
常见问题
Social Media Content Scraper Pro 是什么？
Social Media Content Bulk Scraper, extract articles/posts from WeChat, Instagram, TikTok, YouTube, export to Markdown/HTML with full metadata. $0.005 USDT pe... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 132 次。
如何安装 Social Media Content Scraper Pro？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install wechat-content-scraper-intl」即可一键安装，无需额外配置。
Social Media Content Scraper Pro 是免费的吗？
是的，Social Media Content Scraper Pro 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Social Media Content Scraper Pro 支持哪些平台？
Social Media Content Scraper Pro 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 Social Media Content Scraper Pro？
由 baolige2023（@baolige2023）开发并维护，当前版本 v1.0.0。
推荐 Skills