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 +1,133 @@
|
||||
{
|
||||
"source": "proharvest_plots",
|
||||
"source_key": "phpr-soybeans-2024-9669",
|
||||
"data_type": "trial",
|
||||
"vendor": "ProHarvest Seeds",
|
||||
"brand": "ProHarvest Seeds",
|
||||
"crop": "soybeans",
|
||||
"state": "MO",
|
||||
"state_abbrev": "mo",
|
||||
"city": "Baring",
|
||||
"county": "Knox",
|
||||
"year": 2024,
|
||||
"plot_id": 9669,
|
||||
"cooperator": "Nolan Good",
|
||||
"latitude": 40.2442046,
|
||||
"longitude": -92.2057395,
|
||||
"company_representative": "Jake Ekstrand",
|
||||
"planted_date": "4/6/2024",
|
||||
"harvested_date": "10/3/2024",
|
||||
"previous_crop": "Corn",
|
||||
"row_width": "30",
|
||||
"population_seeds_per_acre": 160000,
|
||||
"fungicide": null,
|
||||
"herbicide": null,
|
||||
"insecticide": null,
|
||||
"tillage": "No-Till",
|
||||
"irrigation": "Non-Irrigated",
|
||||
"results": [
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 1,
|
||||
"product": "AE3550S",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 10.3,
|
||||
"Test Wt.": 54.7,
|
||||
"Yield": 70.45,
|
||||
"+/- Ave": 10.4
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 2,
|
||||
"product": "AE3950S",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 10.2,
|
||||
"Test Wt.": 54.6,
|
||||
"Yield": 70.04,
|
||||
"+/- Ave": 10
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Partners Brand",
|
||||
"rank": 3,
|
||||
"product": "PB3925",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 10,
|
||||
"Test Wt.": 56.9,
|
||||
"Yield": 69.21,
|
||||
"+/- Ave": 9.2
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 4,
|
||||
"product": "AE4150S",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 10.2,
|
||||
"Test Wt.": 56.2,
|
||||
"Yield": 60.54,
|
||||
"+/- Ave": 0.5
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Partners Brand",
|
||||
"rank": 5,
|
||||
"product": "PB3622S",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 10.7,
|
||||
"Test Wt.": 55.4,
|
||||
"Yield": 59.91,
|
||||
"+/- Ave": -0.1
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Partners Brand",
|
||||
"rank": 6,
|
||||
"product": "PB4124",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 10.7,
|
||||
"Test Wt.": 54.8,
|
||||
"Yield": 53.09,
|
||||
"+/- Ave": -6.9
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Partners Brand",
|
||||
"rank": 7,
|
||||
"product": "PB4424",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 11.8,
|
||||
"Test Wt.": 54.7,
|
||||
"Yield": 48.59,
|
||||
"+/- Ave": -11.4
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Partners Brand",
|
||||
"rank": 8,
|
||||
"product": "PB4624",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 12.4,
|
||||
"Test Wt.": 54.9,
|
||||
"Yield": 48.26,
|
||||
"+/- Ave": -11.8
|
||||
}
|
||||
}
|
||||
],
|
||||
"n_results": 8,
|
||||
"raw_text": false,
|
||||
"source_urls": [
|
||||
"https://proharvestseeds.com/wp-content/uploads/2024/11/Soy-Nolan-Good-Baring-MO-63537.pdf"
|
||||
],
|
||||
"fetched_at": "2026-06-05T00:56:23.431542+00:00",
|
||||
"scraper_version": "0.1.0"
|
||||
}
|
||||
Reference in New Issue
Block a user