{
  "schemaVersion": "1.0",
  "item": {
    "slug": "xpr-web-scraping",
    "name": "XPR Web Scraping",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/paulgnz/xpr-web-scraping",
    "canonicalUrl": "https://clawhub.ai/paulgnz/xpr-web-scraping",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/xpr-web-scraping",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=xpr-web-scraping",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "skill.json",
      "src/index.ts"
    ],
    "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/xpr-web-scraping"
    },
    "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/xpr-web-scraping",
    "agentPageUrl": "https://openagent3.xyz/skills/xpr-web-scraping/agent",
    "manifestUrl": "https://openagent3.xyz/skills/xpr-web-scraping/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/xpr-web-scraping/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": "Web Scraping",
        "body": "You have web scraping tools for fetching and extracting data from web pages:\n\nSingle page:\n\nscrape_url — fetch a URL and get cleaned text content + metadata (title, description, link count)\n\nUse format=\"text\" (default) for most tasks — strips all HTML\nUse format=\"markdown\" to preserve headings, links, lists, bold/italic\nUse format=\"html\" only when you need raw HTML\n\nLink discovery:\n\nextract_links — fetch a page and extract all links with text and type (internal/external)\n\nUse the pattern parameter to filter by regex (e.g. \"\\\\.pdf$\" for PDF links)\nLinks are deduplicated and resolved to absolute URLs\n\nMulti-page research:\n\nscrape_multiple — fetch up to 10 URLs in parallel for comparison/research\n\nOne failure doesn't block others (uses Promise.allSettled)\n\nBest practices:\n\nPrefer \"text\" format for content extraction, \"markdown\" for preserving structure\nDon't scrape the same domain more than 5 times per minute\nCombine with store_deliverable to save scraped content as job evidence\nFor very large pages, the content is limited to 5MB"
      }
    ],
    "body": "Web Scraping\n\nYou have web scraping tools for fetching and extracting data from web pages:\n\nSingle page:\n\nscrape_url — fetch a URL and get cleaned text content + metadata (title, description, link count)\nUse format=\"text\" (default) for most tasks — strips all HTML\nUse format=\"markdown\" to preserve headings, links, lists, bold/italic\nUse format=\"html\" only when you need raw HTML\n\nLink discovery:\n\nextract_links — fetch a page and extract all links with text and type (internal/external)\nUse the pattern parameter to filter by regex (e.g. \"\\\\.pdf$\" for PDF links)\nLinks are deduplicated and resolved to absolute URLs\n\nMulti-page research:\n\nscrape_multiple — fetch up to 10 URLs in parallel for comparison/research\nOne failure doesn't block others (uses Promise.allSettled)\n\nBest practices:\n\nPrefer \"text\" format for content extraction, \"markdown\" for preserving structure\nDon't scrape the same domain more than 5 times per minute\nCombine with store_deliverable to save scraped content as job evidence\nFor very large pages, the content is limited to 5MB"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/paulgnz/xpr-web-scraping",
    "publisherUrl": "https://clawhub.ai/paulgnz/xpr-web-scraping",
    "owner": "paulgnz",
    "version": "0.2.11",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/xpr-web-scraping",
    "downloadUrl": "https://openagent3.xyz/downloads/xpr-web-scraping",
    "agentUrl": "https://openagent3.xyz/skills/xpr-web-scraping/agent",
    "manifestUrl": "https://openagent3.xyz/skills/xpr-web-scraping/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/xpr-web-scraping/agent.md"
  }
}