{ "schemaVersion": "1.0", "item": { "slug": "scrape", "name": "Scrape", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/ivangdavila/scrape", "canonicalUrl": "https://clawhub.ai/ivangdavila/scrape", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/scrape", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=scrape", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.md", "code.md" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/scrape" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/scrape", "agentPageUrl": "https://openagent3.xyz/skills/scrape/agent", "manifestUrl": "https://openagent3.xyz/skills/scrape/agent.json", "briefUrl": "https://openagent3.xyz/skills/scrape/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Pre-Scrape Compliance Checklist", "body": "Before writing any scraping code:\n\nrobots.txt — Fetch {domain}/robots.txt, check if target path is disallowed. If yes, stop.\nTerms of Service — Check /terms, /tos, /legal. Explicit scraping prohibition = need permission.\nData type — Public factual data (prices, listings) is safer. Personal data triggers GDPR/CCPA.\nAuthentication — Data behind login is off-limits without authorization. Never scrape protected content.\nAPI available? — If site offers an API, use it. Always. Scraping when API exists often violates ToS." }, { "title": "Legal Boundaries", "body": "Public data, no login — Generally legal (hiQ v. LinkedIn 2022)\nBypassing barriers — CFAA violation risk (Van Buren v. US 2021)\nIgnoring robots.txt — Gray area, often breaches ToS (Meta v. Bright Data 2024)\nPersonal data without consent — GDPR/CCPA violation\nRepublishing copyrighted content — Copyright infringement" }, { "title": "Request Discipline", "body": "Rate limit: Minimum 2-3 seconds between requests. Faster = server strain = legal exposure.\nUser-Agent: Real browser string + contact email: Mozilla/5.0 ... (contact: you@email.com)\nRespect 429: Exponential backoff. Ignoring 429s shows intent to harm.\nSession reuse: Keep connections open to reduce server load." }, { "title": "Data Handling", "body": "Strip PII immediately — Don't collect names, emails, phones unless legally justified.\nNo fingerprinting — Don't combine data to identify individuals indirectly.\nMinimize storage — Cache only what you need, delete what you don't.\nAudit trail — Log what, when, where. Evidence of good faith if challenged.\n\nFor code patterns and robots.txt parser, see code.md" } ], "body": "Pre-Scrape Compliance Checklist\n\nBefore writing any scraping code:\n\nrobots.txt — Fetch {domain}/robots.txt, check if target path is disallowed. If yes, stop.\nTerms of Service — Check /terms, /tos, /legal. Explicit scraping prohibition = need permission.\nData type — Public factual data (prices, listings) is safer. Personal data triggers GDPR/CCPA.\nAuthentication — Data behind login is off-limits without authorization. Never scrape protected content.\nAPI available? — If site offers an API, use it. Always. Scraping when API exists often violates ToS.\nLegal Boundaries\nPublic data, no login — Generally legal (hiQ v. LinkedIn 2022)\nBypassing barriers — CFAA violation risk (Van Buren v. US 2021)\nIgnoring robots.txt — Gray area, often breaches ToS (Meta v. Bright Data 2024)\nPersonal data without consent — GDPR/CCPA violation\nRepublishing copyrighted content — Copyright infringement\nRequest Discipline\nRate limit: Minimum 2-3 seconds between requests. Faster = server strain = legal exposure.\nUser-Agent: Real browser string + contact email: Mozilla/5.0 ... (contact: you@email.com)\nRespect 429: Exponential backoff. Ignoring 429s shows intent to harm.\nSession reuse: Keep connections open to reduce server load.\nData Handling\nStrip PII immediately — Don't collect names, emails, phones unless legally justified.\nNo fingerprinting — Don't combine data to identify individuals indirectly.\nMinimize storage — Cache only what you need, delete what you don't.\nAudit trail — Log what, when, where. Evidence of good faith if challenged.\n\nFor code patterns and robots.txt parser, see code.md" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/ivangdavila/scrape", "publisherUrl": "https://clawhub.ai/ivangdavila/scrape", "owner": "ivangdavila", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/scrape", "downloadUrl": "https://openagent3.xyz/downloads/scrape", "agentUrl": "https://openagent3.xyz/skills/scrape/agent", "manifestUrl": "https://openagent3.xyz/skills/scrape/agent.json", "briefUrl": "https://openagent3.xyz/skills/scrape/agent.md" } }