Patent Number → Full-Text Markdown (Claims & Spec)
Pricing
from $4.00 / 1,000 patent markdowns
Patent Number → Full-Text Markdown (Claims & Spec)
Publication numbers → full-text Markdown (title, abstract, claims, description) + RAG chunks + CPC/citations. Only robots-allowed patents.google.com /patent/ pages — no search/SERP. 512 MB. Failures free.
Pricing
from $4.00 / 1,000 patent markdowns
Rating
0.0
(0)
Developer
新世紀書僮
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
12 hours ago
Last modified
Categories
Share
Turn patent publication numbers (e.g. US9876543B2, EP3411969B1, WO2017120318A1) into clean full-text Markdown for RAG and due-diligence pipelines:
- Title, abstract
- Claims (itemized)
- Description / specification as Markdown
- Paragraph RAG chunks (~500–1000 chars with headings)
- Metadata: applicants / assignees, inventors, priority / filing / publication dates, CPC, backward & forward citations, PDF link
Compliance (robots.txt)
patents.google.com/robots.txt:
This Actor only fetches https://patents.google.com/patent/{NUMBER}/{lang} pages.
It does not search, does not crawl SERPs, and does not hit listing/disallowed paths.
No API key, account, or KYC is required.
Input
| Field | Notes |
|---|---|
publicationNumbers | List of publication numbers (primary) |
patentNumbers | Alias of the above |
datasetId / keyValueStoreId | Optional batch sources |
includeClaims / includeDescription / includeRagChunks | Defaults true |
maxConcurrency | Default 2 (keep low) |
useApifyProxy | Default false — prefer direct; enable only if you measure sustained 429/blocks |
Output
- Dataset: one row per number (
status=ok|failed, title, abstract, claims[], descriptionMarkdown, cpc[], citations*, markdown, chunks[]) - KV
REPORT.md— summary + abstract previews - KV
PATENTS.md— full Markdown documents - KV
CHUNKS.jsonl— RAG chunks (optional) - KV
SUMMARY/OUTPUT
Failed / not-found / invalid rows are not charged.
Pricing (pay-per-event)
| Event | Price |
|---|---|
| Actor start | $0.001 |
patent-markdown (primary) | $0.004 per successful patent |
vs typical patent scrapers
Most Store Actors focus on search + citation graphs and default to 4 GB browsers. This one is built for RAG Markdown + chunks, stays on robots-allowed /patent/ pages only, and targets 512 MB.
Memory & limits
Default 512 MB, timeout 3600 s. Concurrency 1–5 (default 2). Retries on 429/5xx/timeouts.
Example
