community-automations/data-forge-url

研究與情報

PublicClaude 子代理

URL 資料萃取器

從網頁抓取結構化資料，通常得寫一支一次性爬蟲，網站一改版就掛掉。這個擷取器不一樣——你給它一個 URL 和一份 schema 就行。

sonnet4 天FirecrawlPlaywrightOpenAIPostgres
ClaudeClaude
ROI for
README.md

為什麼選擇此子代理

從網頁抓取結構化資料，通常得寫一支一次性爬蟲，網站一改版就掛掉。這個擷取器不一樣——你給它一個 URL 和一份 schema 就行。

你只要描述想要的欄位，它就會渲染頁面、對應元素，回傳乾淨且經過驗證的記錄。換網站只需要換 schema，不用重寫爬蟲；頁面上缺少的欄位會被標記出來，而不是憑空捏造。

運作方式

    • Read

      Used at step 01 to kick off the pipeline.

    • Write

      Used at step 01 to kick off the pipeline.

    • WebFetch

      Used at step 01 to kick off the pipeline.

    • WebSearch

      Used at step 01 to kick off the pipeline.

輸出範例

json
// Sample output
// (generated when the pipeline finishes)

Given a URL and a target schema, extract matching records as JSON conforming to the schema; set missing fields null and never invent values.

Unlock the rest

The full agent definition, install snippet, and starter task are gated for community members.

Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.