{ "schemaVersion": "1.0", "item": { "slug": "smart-web-scraper", "name": "Smart Web Scraper", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/mariusfit/smart-web-scraper", "canonicalUrl": "https://clawhub.ai/mariusfit/smart-web-scraper", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/smart-web-scraper", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=smart-web-scraper", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "_meta.json", "scripts/scraper.py" ], "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "slug": "smart-web-scraper", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-09T03:25:25.716Z", "expiresAt": "2026-05-16T03:25:25.716Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=smart-web-scraper", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=smart-web-scraper", "contentDisposition": "attachment; filename=\"smart-web-scraper-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "smart-web-scraper" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/smart-web-scraper" }, "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/smart-web-scraper", "agentPageUrl": "https://openagent3.xyz/skills/smart-web-scraper/agent", "manifestUrl": "https://openagent3.xyz/skills/smart-web-scraper/agent.json", "briefUrl": "https://openagent3.xyz/skills/smart-web-scraper/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Smart Web Scraper", "body": "Extract structured data from web pages into clean JSON or CSV." }, { "title": "Quick Start", "body": "# Scrape a page, extract all text content\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract \"https://example.com\"\n\n# Extract specific elements with CSS selector\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract \"https://example.com/products\" -s \".product-card\"\n\n# Auto-detect and extract tables\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py tables \"https://example.com/pricing\"\n\n# Extract all links from a page\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py links \"https://example.com\"\n\n# Extract structured data (title, meta, headings, links)\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py structure \"https://example.com\"\n\n# Output as JSON\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract \"https://example.com\" -s \".item\" -f json\n\n# Output as CSV\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract \"https://example.com\" -s \"table tr\" -f csv\n\n# Save to file\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract \"https://example.com\" -s \".product\" -f json -o products.json\n\n# Multi-page scrape (follow pagination)\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py crawl \"https://example.com/page/1\" --pages 5 -s \".article\"" }, { "title": "Commands", "body": "CommandArgsDescriptionextract [-s selector] [-f format] [-o file]Extract content, optionally filtered by CSS selectortables [-f format] [-o file]Auto-detect and extract all HTML tableslinks [--external] [--internal]Extract all links (href + text)structureExtract page structure: title, meta, headings, images, linkscrawl --pages N [-s selector] [-f format] [-o file]Follow pagination links, extract from multiple pages" }, { "title": "Output Formats", "body": "FormatFlagDescriptionText-f textPlain text (default)JSON-f jsonStructured JSON arrayCSV-f csvComma-separated valuesMarkdown-f mdMarkdown-formatted" }, { "title": "Extract product listings", "body": "uv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract \"https://shop.example.com\" -s \".product\" -f json\n\nOutput:\n\n[\n {\"text\": \"Widget Pro - $29.99\", \"tag\": \"div\", \"class\": \"product\"},\n {\"text\": \"Widget Max - $49.99\", \"tag\": \"div\", \"class\": \"product\"}\n]" }, { "title": "Extract pricing table", "body": "uv run --with beautifulsoup4 --with lxml python scripts/scraper.py tables \"https://example.com/pricing\" -f csv" }, { "title": "Get all external links", "body": "uv run --with beautifulsoup4 --with lxml python scripts/scraper.py links \"https://example.com\" --external" }, { "title": "Rate Limiting", "body": "Default: 1 request per second (respectful crawling)\nOverride with --delay 0.5 (seconds between requests)\nRespects robots.txt by default (override with --ignore-robots)" }, { "title": "Notes", "body": "Requires beautifulsoup4 and lxml (auto-installed by uv run --with)\nUses a standard browser User-Agent to avoid blocks\nHandles redirects, encoding detection, and error pages gracefully\nNo JavaScript rendering (use for static HTML pages)" } ], "body": "Smart Web Scraper\n\nExtract structured data from web pages into clean JSON or CSV.\n\nQuick Start\n# Scrape a page, extract all text content\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract \"https://example.com\"\n\n# Extract specific elements with CSS selector\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract \"https://example.com/products\" -s \".product-card\"\n\n# Auto-detect and extract tables\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py tables \"https://example.com/pricing\"\n\n# Extract all links from a page\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py links \"https://example.com\"\n\n# Extract structured data (title, meta, headings, links)\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py structure \"https://example.com\"\n\n# Output as JSON\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract \"https://example.com\" -s \".item\" -f json\n\n# Output as CSV\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract \"https://example.com\" -s \"table tr\" -f csv\n\n# Save to file\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract \"https://example.com\" -s \".product\" -f json -o products.json\n\n# Multi-page scrape (follow pagination)\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py crawl \"https://example.com/page/1\" --pages 5 -s \".article\"\n\nCommands\nCommand\tArgs\tDescription\nextract\t [-s selector] [-f format] [-o file]\tExtract content, optionally filtered by CSS selector\ntables\t [-f format] [-o file]\tAuto-detect and extract all HTML tables\nlinks\t [--external] [--internal]\tExtract all links (href + text)\nstructure\t\tExtract page structure: title, meta, headings, images, links\ncrawl\t --pages N [-s selector] [-f format] [-o file]\tFollow pagination links, extract from multiple pages\nOutput Formats\nFormat\tFlag\tDescription\nText\t-f text\tPlain text (default)\nJSON\t-f json\tStructured JSON array\nCSV\t-f csv\tComma-separated values\nMarkdown\t-f md\tMarkdown-formatted\nExamples\nExtract product listings\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py extract \"https://shop.example.com\" -s \".product\" -f json\n\n\nOutput:\n\n[\n {\"text\": \"Widget Pro - $29.99\", \"tag\": \"div\", \"class\": \"product\"},\n {\"text\": \"Widget Max - $49.99\", \"tag\": \"div\", \"class\": \"product\"}\n]\n\nExtract pricing table\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py tables \"https://example.com/pricing\" -f csv\n\nGet all external links\nuv run --with beautifulsoup4 --with lxml python scripts/scraper.py links \"https://example.com\" --external\n\nRate Limiting\nDefault: 1 request per second (respectful crawling)\nOverride with --delay 0.5 (seconds between requests)\nRespects robots.txt by default (override with --ignore-robots)\nNotes\nRequires beautifulsoup4 and lxml (auto-installed by uv run --with)\nUses a standard browser User-Agent to avoid blocks\nHandles redirects, encoding detection, and error pages gracefully\nNo JavaScript rendering (use for static HTML pages)" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/mariusfit/smart-web-scraper", "publisherUrl": "https://clawhub.ai/mariusfit/smart-web-scraper", "owner": "mariusfit", "version": "1.0.0", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/smart-web-scraper", "downloadUrl": "https://openagent3.xyz/downloads/smart-web-scraper", "agentUrl": "https://openagent3.xyz/skills/smart-web-scraper/agent", "manifestUrl": "https://openagent3.xyz/skills/smart-web-scraper/agent.json", "briefUrl": "https://openagent3.xyz/skills/smart-web-scraper/agent.md" } }