Add ProHarvest Seeds: 119 varieties + 161 cross-vendor plot reports
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.
This commit is contained in:
@@ -0,0 +1,193 @@
|
||||
{
|
||||
"source": "proharvest_plots",
|
||||
"source_key": "phpr-soybeans-2024-9637",
|
||||
"data_type": "trial",
|
||||
"vendor": "ProHarvest Seeds",
|
||||
"brand": "ProHarvest Seeds",
|
||||
"crop": "soybeans",
|
||||
"state": "NE",
|
||||
"state_abbrev": "ne",
|
||||
"city": "Nebraska City",
|
||||
"county": "Otoe",
|
||||
"year": 2024,
|
||||
"plot_id": 9637,
|
||||
"cooperator": "Garrett Schomerus",
|
||||
"latitude": 40.676526,
|
||||
"longitude": -95.858694,
|
||||
"company_representative": "Trent Geistlinger",
|
||||
"planted_date": "5/29/2024",
|
||||
"harvested_date": "10/25/2024",
|
||||
"previous_crop": "Corn",
|
||||
"row_width": "36",
|
||||
"population_seeds_per_acre": 150000,
|
||||
"fungicide": null,
|
||||
"herbicide": null,
|
||||
"insecticide": null,
|
||||
"tillage": "Conventional",
|
||||
"irrigation": "Non-Irrigated",
|
||||
"results": [
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 1,
|
||||
"product": "AE2750",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"Seed Trtmt.": "67000 POPULATION",
|
||||
"% H2O": 8.5,
|
||||
"Test Wt.": 54.7,
|
||||
"Yield": 54.71,
|
||||
"+/- Ave": 8.8
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 2,
|
||||
"product": "AE2750",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"Seed Trtmt.": "75000 POPULATION",
|
||||
"% H2O": 8.5,
|
||||
"Test Wt.": 55,
|
||||
"Yield": 52.1,
|
||||
"+/- Ave": 6.2
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 3,
|
||||
"product": "AE3950S",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"Seed Trtmt.": "proTect Ultra",
|
||||
"% H2O": 8.1,
|
||||
"Test Wt.": 56,
|
||||
"Yield": 48.4,
|
||||
"+/- Ave": 2.5
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "ProHarvest",
|
||||
"rank": 4,
|
||||
"product": "35E52",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"Seed Trtmt.": "proTect Ultra",
|
||||
"% H2O": 7.6,
|
||||
"Test Wt.": 54.8,
|
||||
"Yield": 48.01,
|
||||
"+/- Ave": 2.1
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 5,
|
||||
"product": "AE2750",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"Seed Trtmt.": "120000 POPULATION",
|
||||
"% H2O": 8.6,
|
||||
"Test Wt.": 54.4,
|
||||
"Yield": 47.49,
|
||||
"+/- Ave": 1.6
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 6,
|
||||
"product": "AE2750",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"Seed Trtmt.": "proTect Ultra",
|
||||
"% H2O": 8.6,
|
||||
"Test Wt.": 54.9,
|
||||
"Yield": 46.19,
|
||||
"+/- Ave": 0.3
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 7,
|
||||
"product": "AE3340",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"Seed Trtmt.": "proTect Ultra",
|
||||
"% H2O": 7.9,
|
||||
"Test Wt.": 55.4,
|
||||
"Yield": 44.58,
|
||||
"+/- Ave": -1.3
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 8,
|
||||
"product": "AE3850",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"Seed Trtmt.": "proTect Ultra",
|
||||
"% H2O": 8.2,
|
||||
"Test Wt.": 55.5,
|
||||
"Yield": 43.78,
|
||||
"+/- Ave": -2.1
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 9,
|
||||
"product": "AE2750",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"Seed Trtmt.": "proTect Ultra",
|
||||
"% H2O": 8.2,
|
||||
"Test Wt.": 54.7,
|
||||
"Yield": 43.12,
|
||||
"+/- Ave": -2.8
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 10,
|
||||
"product": "AE3550S",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"Seed Trtmt.": "proTect Ultra",
|
||||
"% H2O": 7.8,
|
||||
"Test Wt.": 56.6,
|
||||
"Yield": 42.66,
|
||||
"+/- Ave": -3.2
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 11,
|
||||
"product": "AE2950",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"Seed Trtmt.": "proTect Ultra",
|
||||
"% H2O": 8.5,
|
||||
"Test Wt.": 56,
|
||||
"Yield": 41.03,
|
||||
"+/- Ave": -4.8
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 12,
|
||||
"product": "AE3150",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"Seed Trtmt.": "proTect Ultra",
|
||||
"% H2O": 8.4,
|
||||
"Test Wt.": 55,
|
||||
"Yield": 38.47,
|
||||
"+/- Ave": -7.4
|
||||
}
|
||||
}
|
||||
],
|
||||
"n_results": 12,
|
||||
"raw_text": false,
|
||||
"source_urls": [
|
||||
"https://proharvestseeds.com/wp-content/uploads/2024/11/Soy-Garrett-Schomerus-Nebraska-City-NE-68410.pdf"
|
||||
],
|
||||
"fetched_at": "2026-06-05T00:56:47.451710+00:00",
|
||||
"scraper_version": "0.1.0"
|
||||
}
|
||||
Reference in New Issue
Block a user