电商价格比较
v1.0.0从京东、淘宝、天猫、拼多多等中国电商平台抓取商品价格并进行比较分析。当用户需要比较不同电商平台的商品价格、寻找最佳性价比、或监控商品价格变化时使用。支持关键词搜索、商品链接分析、价格历史追踪和购买建议。
⭐ 2· 1.4k·12 current·12 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
The skill description and SKILL.md claim support for 京东、淘宝、天猫、拼多多 and list multiple helper scripts (price_history.py, batch_compare.py, taobao_scraper.py, tmall_scraper.py, pdd_scraper.py). The provided code manifest contains only scripts/jd_scraper.py (and documentation/reference files). That means the published bundle does not actually include most platform scrapers or the advanced scripts the docs advertise, which is an important inconsistency between claimed purpose and delivered capabilities.
Instruction Scope
SKILL.md and references describe scraping strategies including browser automation (Playwright), API calls, proxies, user-agent rotation, caching, and potential captcha/anti‑scrape handling. Those instructions are consistent with a web-scraping price-comparison tool, but they also explicitly recommend evasion techniques (proxy rotation, UA changes) which increase operational and legal risk. The instructions reference several scripts that are not present, so runtime behavior described in docs cannot be fully verified from included files.
Install Mechanism
There is no install spec (instruction-only), which minimizes automatic install risk. However README and SKILL.md recommend installing Playwright and other Python packages (playwright, beautifulsoup4, requests, etc.). Playwright requires downloading browser binaries (playwright install chromium). The lack of an automated install means the user will perform these steps manually; this is not malicious but is heavier than the manifest implies.
Credentials
The skill declares no required environment variables or credentials, and the included jd_scraper.py uses only public JD endpoints and does not request secrets. The README shows an optional config.yaml (proxy credentials, request settings) — optional proxies or credentialed services could be configured by the user, but they are not required by the skill as published.
Persistence & Privilege
The skill does not request always:true or any elevated persistence. It does not attempt to modify other skills or system configs. Autonomous invocation is allowed by default but is not combined with broad privileges here.
What to consider before installing
Things to consider before installing or running this skill:
- Capability mismatch: The docs promise multi‑platform support and many helper scripts, but the package only includes jd_scraper.py. If you need Taobao/Tmall/PDD support, request the missing scripts or source before trusting results.
- Dependency burden: The README asks you to install Playwright (and browsers), Requests, BeautifulSoup, etc. Playwright downloads browser binaries—be prepared for that and run installs in a controlled environment.
- Anti‑scraping advice: The skill recommends proxies, UA rotation, and other evasion techniques. Those are functionally related to scraping but raise ethical, legal, and operational concerns; avoid using third‑party proxy services you don't trust and ensure scraping complies with each platform's terms of service and local law.
- Data & secrets: The skill does not request credentials, but config examples include proxy endpoints and potential login handling for platform-specific member prices. Do not supply platform account credentials to untrusted code.
- Test safely: Run the included jd_scraper.py in a sandbox/VM or review the code locally. If you expect full multi‑platform functionality, ask the publisher for the missing script files or a complete source repo and re-evaluate.
- If unsure: treat this package as incomplete rather than fully functional; request source provenance or a homepage, and prefer a vetted tool or official APIs for production use.Like a lobster shell, security has layers — review code before you run it.
latestvk97dhgv027x8mq0xavbqnw32jd81brk2
License
MIT-0
Free to use, modify, and redistribute. No attribution required.