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-2025-9818",
|
||||
"data_type": "trial",
|
||||
"vendor": "ProHarvest Seeds",
|
||||
"brand": "ProHarvest Seeds",
|
||||
"crop": "soybeans",
|
||||
"state": "IN",
|
||||
"state_abbrev": "in",
|
||||
"city": "Montgomery",
|
||||
"county": "Daviess",
|
||||
"year": 2025,
|
||||
"plot_id": 9818,
|
||||
"cooperator": "Wagler Brothers",
|
||||
"latitude": 38.662932933156554,
|
||||
"longitude": -87.04625019838019,
|
||||
"company_representative": "Tom Forrest",
|
||||
"planted_date": "4/26/2025",
|
||||
"harvested_date": "10/3/2025",
|
||||
"previous_crop": "Corn",
|
||||
"row_width": "34",
|
||||
"population_seeds_per_acre": 160000,
|
||||
"fungicide": "No",
|
||||
"herbicide": "Enlist/ Liberty",
|
||||
"insecticide": null,
|
||||
"tillage": "Conventional",
|
||||
"irrigation": "Non-Irrigated",
|
||||
"results": [
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 1,
|
||||
"product": "AE3950S",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 13.1,
|
||||
"Test Wt.": 54.9,
|
||||
"Yield": 88.17,
|
||||
"+/- Ave": 7
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 2,
|
||||
"product": "AE3550S",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 14.2,
|
||||
"Test Wt.": 55,
|
||||
"Yield": 88.01,
|
||||
"+/- Ave": 6.8
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 3,
|
||||
"product": "AE3850",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 13.6,
|
||||
"Test Wt.": 54.9,
|
||||
"Yield": 83.76,
|
||||
"+/- Ave": 2.6
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Seed Consultants",
|
||||
"rank": 4,
|
||||
"product": "SC",
|
||||
"traits": "7385E",
|
||||
"metrics": {
|
||||
"% H2O": 14.1,
|
||||
"Test Wt.": 54.1,
|
||||
"Yield": 83.73,
|
||||
"+/- Ave": 2.6
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 5,
|
||||
"product": "AE3340",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 15.3,
|
||||
"Test Wt.": 53.8,
|
||||
"Yield": 82.79,
|
||||
"+/- Ave": 1.6
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Seed Consultants",
|
||||
"rank": 6,
|
||||
"product": "7416E",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 13.3,
|
||||
"Test Wt.": 54.6,
|
||||
"Yield": 82.27,
|
||||
"+/- Ave": 1.1
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Seed Consultants",
|
||||
"rank": 7,
|
||||
"product": "7364E",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 13.6,
|
||||
"Test Wt.": 53.9,
|
||||
"Yield": 81.09,
|
||||
"+/- Ave": -0.1
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 8,
|
||||
"product": "AE4150S",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 12.6,
|
||||
"Test Wt.": 55.5,
|
||||
"Yield": 80.06,
|
||||
"+/- Ave": -1.1
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 9,
|
||||
"product": "AE3660",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 14.6,
|
||||
"Test Wt.": 53.9,
|
||||
"Yield": 79.41,
|
||||
"+/- Ave": -1.8
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Seed Consultants",
|
||||
"rank": 10,
|
||||
"product": "7375E",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 14.4,
|
||||
"Test Wt.": 53.5,
|
||||
"Yield": 79.37,
|
||||
"+/- Ave": -1.8
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Seed Consultants",
|
||||
"rank": 11,
|
||||
"product": "7355E",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 14.8,
|
||||
"Test Wt.": 52.2,
|
||||
"Yield": 78.69,
|
||||
"+/- Ave": -2.5
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Apex",
|
||||
"rank": 12,
|
||||
"product": "AE4240S",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 12.4,
|
||||
"Test Wt.": 54.9,
|
||||
"Yield": 74.49,
|
||||
"+/- Ave": -6.7
|
||||
}
|
||||
},
|
||||
{
|
||||
"brand": "Seed Consultants",
|
||||
"rank": 13,
|
||||
"product": "7326E",
|
||||
"traits": null,
|
||||
"metrics": {
|
||||
"% H2O": 15.2,
|
||||
"Test Wt.": null,
|
||||
"Yield": 73.29,
|
||||
"+/- Ave": -7.9
|
||||
}
|
||||
}
|
||||
],
|
||||
"n_results": 13,
|
||||
"raw_text": false,
|
||||
"source_urls": [
|
||||
"https://proharvestseeds.com/wp-content/uploads/2025/10/Soy-Wagler-Brothers-Mongomery-IN-min.pdf"
|
||||
],
|
||||
"fetched_at": "2026-06-05T01:00:23.830316+00:00",
|
||||
"scraper_version": "0.1.0"
|
||||
}
|
||||
Reference in New Issue
Block a user