Add 4 independent seed brands: Latham, Stine, 1st Choice, Burrus (+623 varieties)
Four independent regional brands across IA/IN/IL (variety-identity sources,
each parsed into structured characteristics_groups so ratings embed):
- latham (264: 155 corn + 109 soy) — Latham Hi-Tech Seeds, Alexander IA.
WordPress REST enum (/wp-json/wp/v2/varieties) + /products/<slug>/ detail
HTML. Scale 1-9 LOWER=better (reversed, like NK/AgriPro).
- stine (217: 58 corn + 159 soy) — Stine Seed, Adel IA (largest US
independent). sitemap enum + /{crop}/traits/<slug>/<code>/ detail HTML.
Corn 1-9 (9=best); soy qualitative.
- first_choice (78: 52 corn + 22 soy + 4 wheat) — 1st Choice Seeds,
Rushville IN (employee-owned). Per-crop sitemap -> detail HTML. Scale
0-10 higher=better. ~40 older corn pages thin at source; wheat
identity-only.
- burrus (64: 38 corn + 26 soy) — Burrus Seed, Arenzville IL. Seedware
JSON API. Scale 1-10 (10=best). Brands Burrus/Power Plus/DONMARIO.
robots ai-train=no + named-bot blocks; operator opted in, scraper uses a
non-blacklisted UA + honors Crawl-delay 10.
All 623 validated through rag.chunk.chunks_from_variety (0 errors; 6
identity-only pages from source gaps). No chunk.py change needed (identity
sources auto-route to chunks_from_variety).
Docs:
- sources.json: 4 entries + Hoegemeyer added to _excluded_sources. The
Corteva ToU (shared across pioneer.com / hoegemeyer.com / therightseed.com
/ corteva.com + the Vylor spinoff) bans scrapers + competitive use, so the
whole Corteva family is one excluded ToU domain.
- docs_mcp/lessons.md: rating-scales updated with all 4 directions +
an explicit cross-vendor warning (Latham 1=best vs Stine/Burrus higher=best
— never compare raw numbers without _scale_direction).
- README + CLAUDE corpus inventory: now 2,268 variety + 6,787 trial records.
CI rebuilds the index from the committed corpus.
This commit is contained in:
@@ -0,0 +1,107 @@
|
||||
{
|
||||
"source": "latham",
|
||||
"source_key": "latham-lh-3746-pce-ra",
|
||||
"vendor": "Latham Hi-Tech Seeds",
|
||||
"brand": "Latham Hi-Tech Seeds",
|
||||
"product_name": "LH 3746 PCE RA",
|
||||
"product_id": "LH 3746 PCE RA",
|
||||
"crop": "corn",
|
||||
"release_year": "2025",
|
||||
"relative_maturity": 87,
|
||||
"maturity_group": null,
|
||||
"wheat_class": null,
|
||||
"trait_stack": [
|
||||
"Powercore Enlist Corn"
|
||||
],
|
||||
"trait_descriptions": [],
|
||||
"positioning_statement": "Outstanding early PowerCore Enlist hybrid with top yield across years. Low green snap risk with very good Goss’ wilt tolerance allows for strong east to West in zone and north of zone performance. A flexing ear style with blocky kernels works across varying populations. LH3746 PCE RA is a Grain First / Silage Capable hybrid.",
|
||||
"strengths": [],
|
||||
"characteristics_groups": [
|
||||
{
|
||||
"label": "AGRONOMIC CHARACTERISTICS",
|
||||
"items": [
|
||||
{
|
||||
"characteristic": "Early Vigor",
|
||||
"value": "2.0"
|
||||
},
|
||||
{
|
||||
"characteristic": "Stalk Strength",
|
||||
"value": "2.0"
|
||||
},
|
||||
{
|
||||
"characteristic": "Root Strength",
|
||||
"value": "3.0"
|
||||
},
|
||||
{
|
||||
"characteristic": "Stay Green",
|
||||
"value": "2.0"
|
||||
},
|
||||
{
|
||||
"characteristic": "Drydown",
|
||||
"value": "2.0"
|
||||
},
|
||||
{
|
||||
"characteristic": "Test Weight",
|
||||
"value": "3.0"
|
||||
},
|
||||
{
|
||||
"characteristic": "Drought Tolerance",
|
||||
"value": "3.0"
|
||||
},
|
||||
{
|
||||
"characteristic": "Foliar Fungicide",
|
||||
"value": "2.0"
|
||||
},
|
||||
{
|
||||
"characteristic": "Corn-on-Corn",
|
||||
"value": "3.0"
|
||||
},
|
||||
{
|
||||
"characteristic": "Ear Height",
|
||||
"value": "Medium HIgh"
|
||||
},
|
||||
{
|
||||
"characteristic": "Ear Type",
|
||||
"value": "Flex"
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"label": "DISEASE RATINGS",
|
||||
"items": [
|
||||
{
|
||||
"characteristic": "Goss’s Wilt",
|
||||
"value": "2.0"
|
||||
},
|
||||
{
|
||||
"characteristic": "Northern Leaf Blight",
|
||||
"value": "2.0"
|
||||
},
|
||||
{
|
||||
"characteristic": "Anthracnose Stalk Rot",
|
||||
"value": "2.0"
|
||||
},
|
||||
{
|
||||
"characteristic": "Gray Leaf Spot",
|
||||
"value": "3.0"
|
||||
}
|
||||
]
|
||||
}
|
||||
],
|
||||
"_scale_direction": "numeric ratings ~1-9 where LOWER = BETTER (1 = best / most tolerant / most resistant); confirmed by cross-referencing Product Overview prose vs values (top-rated stalks/roots cluster 1.0-1.5, weak traits 3.0-3.5, none approach 9). Categorical values pass through verbatim (SCN source 'PI 88788', Phytophthora 'Rps 1k', Anthracnose 'ASR', 'Medium Tall', 'Flex'). NA/blank = not rated.",
|
||||
"regional_recommendations": [
|
||||
{
|
||||
"product_list_name": "Latham dealer network (Upper Midwest — IA/MN/WI/IL/ND/SD/NE)",
|
||||
"agronomist": null,
|
||||
"agronomist_email": null,
|
||||
"variant_id": null
|
||||
}
|
||||
],
|
||||
"image_url": null,
|
||||
"source_urls": [
|
||||
"https://www.lathamseeds.com/products/lh-3746-pce-ra/"
|
||||
],
|
||||
"sitemap_last_modified": null,
|
||||
"fetched_at": "2026-06-05T01:45:33.964886+00:00",
|
||||
"scraper_version": "0.1.0"
|
||||
}
|
||||
Reference in New Issue
Block a user