claude
2425a79f0c
Independent regional brand (Elkhorn, NE; rolled up Federal Hybrids / Big Cob / Kiser / Rupp's grain-forage). No structured web catalog — the lineup lives in the 2026 Seed Guide PDF — so this is a PDF-extraction identity source. - robseeco (130: 87 corn + 43 soy; Rob-See-Co 105 + Innotech 25). Downloads the guide (cached under var/, gitignored), dedups the duplicated pages, parses the corn (p5-8) + soy (p19-26) ratings tables. Rotated/vertical column headers reconstructed by clustering rotated words; cells mapped by x-center alignment; descriptive 2-col cards joined by code for trait_stack + strengths. Masters Choice silage + sorghum scoped out (row-crop core only). - SCALE 1-9, 9=Best (higher=better, like Bayer/Stine-corn); column map verified against the card bullets (e.g. RC2500 "rapid drydown"->Drydown 8, "short plant"->Plant Height 5; RC4779 "industry-leading tar spot"->Tar Spot 7). Validation: all 130 chunk via rag.chunk.chunks_from_variety (0 errors), 0 duplicate keys, 0 out-of-range ratings (misalignment check), RM/MG all sane. robseeco.com robots permissive (Squarespace AI-block toggle off; no ToS scrape clause; PDF on a public CDN). docs: sources.json + README/CLAUDE inventory (2,398 variety records) + rating-scales lesson (added RobSeeCo to the higher=better group + the cross-vendor direction warning).
scrape/
Per-vendor seed catalog scrapers + the runner that dispatches to
them. Each source lives in scrape/sources/<name>.py with a main()
entrypoint. The runner is a thin shim:
python -m scrape.runner --source bayer_seeds --force
python -m scrape.runner --source golden_harvest --limit 20
python -m scrape.runner --all # only GREEN sources
Output layout
Each scraper writes:
corpus/<source>/<source_key>.md— LLM-visible body (chunk_0 preamble + the variety's marketing + agronomic narrative)corpus/<source>/<source_key>.json— sidecar metadata (per CLAUDE.md's canonical schema)
source_key is a stable per-vendor slug — typically <brand>-<sku>
lowercased, e.g. dekalb-dkc62-08rib. Stability matters: it's the
join key the MCP uses for get_page(source, source_key).
Sources
| Source | Module | Verdict | Notes |
|---|---|---|---|
bayer_seeds |
bayer_seeds.py |
🟢 | DEKALB + Asgrow + WestBred, ~475 varieties |
golden_harvest |
golden_harvest.py |
🟢 | ~175 varieties, 9-to-1 disease scale (reverse) |
nk |
nk.py |
🟢 | 29 varieties, ratings in CDN PDFs |
agripro |
agripro.py |
🟢 | 24 wheat varieties |
becks_pfr |
becks_pfr.py |
🟡 | 2,089 research docs via public Sanity GROQ |
becks_products |
becks_products.py |
🟡 | 860 products, identity-only (SeedIQ-gated) |
Pioneer is intentionally absent — see CLAUDE.md and the curated
Pioneer fallback in docs_mcp/lessons.md.
Tips
- Sniff before you scrape. Most catalogs are SPAs that call a
backend API. The recon docs in
~/.claude/projects/-home-justin/ memory/reference_seed_vendor_recon.mdalready capture the endpoints; if you find new ones, update that file. - Idempotent re-scrapes. Without
--force, skip pages already on disk. With--force, re-fetch everything — that's the monthly cron mode. - Respect the portals. Backoff on 429s. Set a recognizable
user-agent (
seed-mcp-scraper/<version>). - Normalize at chunk time, not at scrape time. The chunker
(Phase 2) handles the 9-to-1 → 1-9 disease-scale flip for Golden
Harvest, NOT this scraper. Sidecar JSON should preserve the
vendor's raw values + a
_scale_directionfield; the chunker reads that and normalizes the markdown body.
changelog.py
Reusable as-is from the template. Walks git diff --name-status
output for the commit summary, and git log for the digest history
(Phase 13).