Library/@admin/read-url

Read Url

Fetch any URL and extract its main content as clean markdown. Strips navigation, ads, cookie banners, and boilerplate — ideal as a "reader" step before summarization, translation, or RAG ingestion. No JS rendering (server-side only, no headless browser), no platform inference credits are spent.

jobwebv0.1.0Featured
Updated 30d ago · 6 total runs

Inputs

urlstringrequiredAbsolute URL to fetch. Must return HTML or XML.
include_linksbooleanKeep inline links ([text](url)) in the markdown output.
include_tablesbooleanKeep tables as GFM-style markdown tables.
favor_recallbooleanWhen true, trafilatura errs on the side of keeping more content (useful for non-article pages). Set false for strict article extraction.

Outputs

textstring
titlestring
authorstring
publishedstring
source_urlstring
char_countinteger
content_pathstring

Resources

CPU
1
Memory
512 MB
Timeout
120s