claude
89eea0f2b4
ProHarvest Seeds (independent Corn Belt brand, proharvestseeds.com) exposes a public, no-auth WordPress REST API — cleaner ingestion than the HTML-only independents. Two new sources: - `proharvest` (variety identity, 119 row-crop varieties: 70 corn / 47 soy / 2 wheat). Enumerated via /wp/v2/seed (seed-type taxonomy), agronomics parsed from each /seed/<slug>/ detail page into structured characteristics_groups so the ratings actually embed. Mixed scale: disease 1-9 numeric (9=best, no flip), agronomic/general qualitative, soil HR/R. - `proharvest_plots` (trials, data_type=trial, 161 plots, 2024+2025). Per- cooperator harvest reports via the custom /wp-json/proharvest/v1/plots?y= endpoint + PDF table extraction. Many are cross-vendor head-to-head (ProHarvest/Apex vs Pioneer/DEKALB/Becks/Channel/Wyffels). Handles ruled tables, unruled tables (text fallback; soy drops the Test-Wt column → 4 vs 5 numerics), and off-template third-party reports (sanity-gated to verbatim so junk rows never ship). Image-only PDFs skipped + counted. - rag/chunk.py: route proharvest_plots through the shared cross-vendor plot renderer (structured) / verbatim body (raw_text fallback). - sources.json + lessons.md (rating-scales, trial-data). - README/CLAUDE.md corpus inventory brought current (it had drifted: bayer 931 not 475; ebberts/lg/agrigold were unlisted). New totals: 1,645 variety + 6,787 trial records. robots.txt permissive (only search + /dealer-* disallowed); no ToS automation clause. CI rebuilds the index from the committed corpus.
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).