Convert public PDF URLs to Markdown page text. One row per nonempty page: text, page number, extraction method, dimensions and download URL. PDF转Markdown、扫描PDF识别。 Optional English/Chinese OCR on pages without text. Free blank pages and ID/hash exclusions; bounded page ranges.
The run now finishes before its own timeout: no document or page is started in the last 10% of the run time (20 s to 2 min), what was read is delivered and charged, and the run ends SUCCEEDED with time_hit in SUMMARY and "run time limit reached" on the run card instead of TIMED-OUT. Runs that finish in time are unchanged: no prices, input fields, defaults or output fields changed.
1.3 — 2026-11-16
maxItems (sent by AI agents) now also lifts default caps: leave maxPagesPerDocument and maxResults at their defaults and the run delivers up to maxItems rows in total; explicit caps still win. Add-ons follow the delivered rows; no prices, defaults or output fields changed.
1.2 — 2026-11-16
Extra input fields from agents are accepted and ignored; maxItems caps total rows. The input schema no longer refuses unknown top-level fields, and the README input notes say so. No prices, output fields, defaults or input fields changed.
1.1 — 2026-11-16
Unknown input fields are ignored instead of failing the run (agents often add maxItems or proxyConfiguration); maxItems caps the rows delivered and charged; input problems end with an explanation and no charge instead of a failed run. No prices, output fields, defaults or input fields changed.
2026-11-13 — Restore previous listing keywords
Restore title, description and SEO text to the November 5 baseline at the owner’s request. Preserve current runtime fixes, input/output contracts, billing, prices and defaults.
2026-11-07 — First-call contract corrections
Clarify that the page limit counts inspected pages and that nonempty prose pages are billed even without tables. Runtime, input names/types/defaults/prefills, output fields, metadata and pricing are unchanged.
2026-11-06 — MCP discovery metadata
Clarify supported search intents and output nouns in the Store listing. Runtime, input contract, output and prices are unchanged.
Changelog
1.1.0 — 2026-10-17
Add opt-in OCR for PDF pages without extractable text, with English and simplified Chinese language selection. Preserve digital extraction by default and on text-bearing pages. Bound rendering to 20 million pixels at 150 DPI. OCR output identifies its extraction method and language, with the same per-page price and downloadable Markdown. Empty recognition results remain free.
1.0.1 — 2026-10-17
Stop source work immediately at the result cap. Add source request, byte and DNS cache counters to SUMMARY. Reuse positive DNS answers within their TTL for batch email verification. Resolve website Markdown links and image paths against the page base URL. Private launch hardening; publication held.
1.0.0 — 2026-10-17
Private initial release selected from global keyword evidence. Bounded extraction, explicit limitations, result billing, source evidence and English/Chinese discovery metadata. Publication held.