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.
203 lines
3.9 KiB
JSON
203 lines
3.9 KiB
JSON
{
|
|
"source": "proharvest_plots",
|
|
"source_key": "phpr-soybeans-2024-9671",
|
|
"data_type": "trial",
|
|
"vendor": "ProHarvest Seeds",
|
|
"brand": "ProHarvest Seeds",
|
|
"crop": "soybeans",
|
|
"state": "KS",
|
|
"state_abbrev": "ks",
|
|
"city": "Esbon",
|
|
"county": "Jewell",
|
|
"year": 2024,
|
|
"plot_id": 9671,
|
|
"cooperator": "Todd Davis",
|
|
"latitude": 39.8221094,
|
|
"longitude": -98.435713,
|
|
"company_representative": "Derald Watson",
|
|
"planted_date": "5/29/2024",
|
|
"harvested_date": "10/8/2024",
|
|
"previous_crop": "Corn",
|
|
"row_width": "30\"",
|
|
"population_seeds_per_acre": 30000,
|
|
"fungicide": "Yes",
|
|
"herbicide": null,
|
|
"insecticide": null,
|
|
"tillage": null,
|
|
"irrigation": "Non-Irrigated",
|
|
"results": [
|
|
{
|
|
"rank": 1,
|
|
"metrics": {
|
|
"Yield": 36.89,
|
|
"% H2O": 7.0,
|
|
"+/- Ave": 5.0
|
|
},
|
|
"brand": "Channel",
|
|
"product": "3025R",
|
|
"traits": "XF"
|
|
},
|
|
{
|
|
"rank": 2,
|
|
"metrics": {
|
|
"Yield": 35.91,
|
|
"% H2O": 7.0,
|
|
"+/- Ave": 4.0
|
|
},
|
|
"brand": "AgriGold",
|
|
"product": "3724XF",
|
|
"traits": "XF"
|
|
},
|
|
{
|
|
"rank": 3,
|
|
"metrics": {
|
|
"Yield": 35.15,
|
|
"% H2O": 7.2,
|
|
"+/- Ave": 3.2
|
|
},
|
|
"brand": "AgriGold",
|
|
"product": "4184",
|
|
"traits": "XF"
|
|
},
|
|
{
|
|
"rank": 4,
|
|
"metrics": {
|
|
"Yield": 34.39,
|
|
"% H2O": 6.8,
|
|
"+/- Ave": 2.5
|
|
},
|
|
"brand": "Channel",
|
|
"product": "3624RXF",
|
|
"traits": "XF"
|
|
},
|
|
{
|
|
"rank": 5,
|
|
"metrics": {
|
|
"Yield": 32.46,
|
|
"% H2O": 7.1,
|
|
"+/- Ave": 0.6
|
|
},
|
|
"brand": "Asgrow",
|
|
"product": "AG36F4",
|
|
"traits": "XF"
|
|
},
|
|
{
|
|
"rank": 6,
|
|
"metrics": {
|
|
"Yield": 32.02,
|
|
"% H2O": 7.5,
|
|
"+/- Ave": 0.1
|
|
},
|
|
"brand": "AgriGold",
|
|
"product": "4094",
|
|
"traits": "XF"
|
|
},
|
|
{
|
|
"rank": 7,
|
|
"metrics": {
|
|
"Yield": 32.0,
|
|
"% H2O": 6.9,
|
|
"+/- Ave": 0.1
|
|
},
|
|
"brand": "AgriGold",
|
|
"product": "3552XF",
|
|
"traits": "XF"
|
|
},
|
|
{
|
|
"rank": 8,
|
|
"metrics": {
|
|
"Yield": 31.92,
|
|
"% H2O": 6.7,
|
|
"+/- Ave": 0.0
|
|
},
|
|
"brand": "Asgrow",
|
|
"product": "AG31F5",
|
|
"traits": "XF"
|
|
},
|
|
{
|
|
"rank": 9,
|
|
"metrics": {
|
|
"Yield": 31.02,
|
|
"% H2O": 6.9,
|
|
"+/- Ave": -0.9
|
|
},
|
|
"brand": "Asgrow",
|
|
"product": "AG30XF4",
|
|
"traits": "XF"
|
|
},
|
|
{
|
|
"rank": 10,
|
|
"metrics": {
|
|
"Yield": 30.98,
|
|
"% H2O": 7.0,
|
|
"+/- Ave": -0.9
|
|
},
|
|
"brand": "ProHarvest",
|
|
"product": "36F58",
|
|
"traits": "XF"
|
|
},
|
|
{
|
|
"rank": 11,
|
|
"metrics": {
|
|
"Yield": 30.26,
|
|
"% H2O": 6.9,
|
|
"+/- Ave": -1.6
|
|
},
|
|
"brand": "AgriGold",
|
|
"product": "3804",
|
|
"traits": "XF"
|
|
},
|
|
{
|
|
"rank": 12,
|
|
"metrics": {
|
|
"Yield": 29.45,
|
|
"% H2O": 6.8,
|
|
"+/- Ave": -2.4
|
|
},
|
|
"brand": "ProHarvest",
|
|
"product": "32F54",
|
|
"traits": "XF"
|
|
},
|
|
{
|
|
"rank": 13,
|
|
"metrics": {
|
|
"Yield": 29.42,
|
|
"% H2O": 6.9,
|
|
"+/- Ave": -2.5
|
|
},
|
|
"brand": "Channel",
|
|
"product": "3124R",
|
|
"traits": "XF"
|
|
},
|
|
{
|
|
"rank": 14,
|
|
"metrics": {
|
|
"Yield": 29.15,
|
|
"% H2O": 6.8,
|
|
"+/- Ave": -2.8
|
|
},
|
|
"brand": "Channel",
|
|
"product": "3424RFX",
|
|
"traits": "XF"
|
|
},
|
|
{
|
|
"rank": 15,
|
|
"metrics": {
|
|
"Yield": 27.54,
|
|
"% H2O": 7.1,
|
|
"+/- Ave": -4.4
|
|
},
|
|
"brand": "ProHarvest",
|
|
"product": "29F42",
|
|
"traits": "XF"
|
|
}
|
|
],
|
|
"n_results": 15,
|
|
"raw_text": false,
|
|
"source_urls": [
|
|
"https://proharvestseeds.com/wp-content/uploads/2024/11/Soy-Todd-Davis-Esbon-KS-66941.pdf"
|
|
],
|
|
"fetched_at": "2026-06-05T00:56:22.172736+00:00",
|
|
"scraper_version": "0.1.0"
|
|
}
|