[
  {
    "id": "bayer",
    "title": "Bayer Crop Science US — Product Labels",
    "type": "manufacturer",
    "homepage": "https://www.cropscience.bayer.us",
    "scraper": "scrape.sources.bayer",
    "scraper_version": "0.1.0",
    "license_note": "robots.txt explicitly permits scraping for AI retrieval-augmented generation (verified 2026-05)"
  },
  {
    "id": "epa_ppls",
    "title": "EPA Pesticide Product Label System",
    "type": "regulator",
    "homepage": "https://ordspub.epa.gov/ords/pesticides/f?p=PPLS:1",
    "scraper": "scrape.sources.epa_ppls",
    "scraper_version": "0.1.0",
    "license_note": "US federal government — public domain (no ToS restriction)",
    "scope_filter": "corn / soybean / wheat only — products with at least one site matching CORN, MAIZE, POPCORN, SOYBEAN(S), or WHEAT (word-boundary match). Hits ~16% of the PPLS universe in sampling. Pass --no-row-crop-filter to scrape the full PPLS universe.",
    "registrant_filter": "Pre-API filter at PPIS enumeration: only products from registrants on scrape/sources/epa_registrant_allowlist.json (34 major US ag-chem companies — Syngenta, Bayer, BASF, Corteva, FMC, Nufarm, ADAMA, UPL, Albaugh, Loveland, AMVAC, Helena, Drexel, Atticus, etc.) hit the API. Cuts the 102K-row PPIS universe to ~11.5K — full backfill drops from ~28h to ~5-6h. --no-registrant-filter to skip."
  }
]