For analysts and researchers
The data exists. It is just in fourteen places.
The numbers are public but sit in PDFs, regional sites, and registries. Nobody writes a collector for a one-off study. Now an agent does.
Planned
Jobs
What you would ask for.
Assemble from scattered sources
PDFs, government pages, registries, one table.
Reconcile formats
Units, dates, and names normalized.
Refresh when they publish
Rerun yearly or quarterly.
Example
Say it like this. Get this back.
“Collect the annual rainfall tables published by these 14 regional water authorities into one table, with the source and year for every row.”
Your table · 3 rows shownIllustrative
| regiontext · collected | yearnumber · collected | rainfall_mmnumber · collected | source_urlurl · collected |
|---|---|---|---|
| North Basin | 2,024 | 1,120 | northbasin.example/annual-2024.pdf |
| Coastal | 2,024 | 1,580 | coastalwater.example/stats |
| Highlands | 2,024 | — | highlands.example/report24.pdf |
Good to know
Where the answer can be no, before you pay.
- Scanned PDFs can be misread. We flag low confidence.
- Empty means the source did not say.
Request types
What this audience asks for most.
Research and obscure data
Scattered public data from PDFs and registries, in one table.
PlannedSee the task →
Website to spreadsheet
Any pages into rows and the columns you choose.
First releaseSee the task →
Financial and market data
Rates, filings, and listings from many sites, refreshed on schedule.
PlannedSee the task →
Early access
Tell us what you want from the internet.
Describe your ask. A person replies with possible or not, and roughly what it costs.