Browser Read

browser-read

提取 readable text from an already-open browser page and return markdown, suitable for pages where 网页_fetch is blocked or missing auth 上下文.

When to use 网页_fetch returned an error or empty content. Page requires authentication/cookies/会话 状态 avAIlable only in the browser. You need text 提取ion from Twitter/X or LinkedIn timelines/articles where screenshot/OCR was previously used. When NOT to use 网页_fetch already returns good markdown/text (faster and cheaper). Purely static pages where normal fetch is sufficient. Steps Navigate to the URL with browser navigate. Read 提取ion script from ~/clawd/技能s/browser-read/提取.js. 运行 browser act with kind=evaluate and pass the script contents as fn. Script returns {title, content, excerpt, byline, siteName, length} where content is markdown. If 提取ion fAIls or returns empty content, script falls back to document.body.innerText. Example (工具 calls) { "action": "navigate", "tar获取Id": "...", "url": "https://example.com" } { "action": "act", "tar获取Id": "...", "kind": "evaluate", "fn": "(() => { ... return {title, content, excerpt, byline, siteName, length}; })()" }

Notes 提取.js is a self-contAIned IIFE so it can be passed directly as the fn value to browser act. Keep in mind this is a lightweight 提取器; it intentionally strips script/style/nav/header/footer/aside/cookie/ad elements before conversion.