PDF → Markdown/JSON, handles complex tables in 10-K/SAP filings
| type | extraction_library |
| url | github · mineru |
| auth | none |
| cost | free |
| consumers | statsight, productscope |
| classification | vendor_restricted |
Open-source, self-hostable. Replaces stubbed PDF parsing in StatSight and enables N-4 prospectus extraction in ProductScope.