Pulling structured data off a webpage usually means writing a one-off scraper that breaks the moment the site changes. This extractor takes a URL and a schema instead.
sonnet4 daysFirecrawlPlaywrightOpenAIPostgres
Claude
65ROI
72Scale
$2.2k93Saved
ROI for
README.md
Why this subagent
Pulling structured data off a webpage usually means writing a one-off scraper that breaks the moment the site changes. This extractor takes a URL and a schema instead.
You describe the fields you want, and it renders the page, maps the elements, and returns clean validated records. Switch sites by switching the schema; no new scraper to write, and any field the page lacks is flagged rather than faked.
How it runs
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.
Take your defined schema and map page elements to its fields.
pending
Extract the data, coerce types, and validate each row against the schema.
pending
Return clean structured records and flag fields the page didn't provide.
pending
Sample output
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.