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.
2026-06-04 21:04:33 -04:00
parent e356633d4f
commit 89eea0f2b4
567 changed files with 80023 additions and 8 deletions
@@ -0,0 +1,63 @@
+# Soybean yield trial — Synergy Seeds Herscher (Herscher, IL, 2024)
+
+- **Publisher:** ProHarvest Seeds (cross-vendor plot report)
+- **Crop:** Soybean
+- **Year:** 2024
+- **Location:** Herscher, IL · Kankakee County
+- **Source PDF:** https://proharvestseeds.com/wp-content/uploads/2024/11/Soy-Synergy-Herscher-IL-60941.pdf
+
+---
+
+## Trial data (verbatim from PDF)
+
+```
+2024 Synergy Seeds Soybean Harvest Report
+Cooperator BAUER Prev Crop CORN Prior Year Herb
+Mailing Address Tillage Type N/A PreE Herb
+City, State, Zip HERSCHER % Ground Cover Date Applied
+County KANKAKEE Years in Con Till Rate Applied
+Telephone Irrigated (y/n) NO PostE Herb
+Sales Rep Soil pH Date Applied Assume
+Seed Dealer SYNERGY SEEDS Organic Matter (%) Rate Applied Selling Price:
+Planting Date 5/5/2024 Soil Texture Silty Clay Loam Seed Treatment $10.00
+Planting Pop. 142,000 NPK applied Soil Insecticide per bushel
+Row Width 30.0 P2O5 H, M, L Medium Std Moisture
+Harvest Date 10/5/2024 K2O H, M, L Medium
+Plot Test Type Competitor Plot Describe residue 5=Dead Vegetation, Moderate Residue Corn Stubble 2 years, 25-50%
+Grower Signature YES Experiment Number:
+Use Grower's Name
+Harvest Soybean @13.0% Row Harvest
+Entry Moist. Bushels/Acre Gross Rank by # Length Weight
+No. Brand Variety Trait (%) Yield Rank Income Income Rows (ft.) (lbs.)
+1 Merschman Chippewa 2522 FI + Saltro + Tripidity Enlist 11.3 78.7 2 $ 7 87.48 2 4 360 383
+2 Apex 2440 FI + Saltro Enlist 11.2 63.6 27 $ 6 36.04 27 4 360 309
+3 ProHarvest 25E35 FI + Saltro Enlist 11.3 72.2 14 $ 7 21.68 14 4 360 351
+4 Merschman Osage 2526 FI + Saltro + Tripidity Enlist 11.3 80.6 1 $ 8 05.98 1 4 360 392
+5 Apex 2740 FI + Saltro Enlist 11.2 65.7 26 $ 6 56.81 26 4 352 312
+6 Apex 2750 FI + Saltro Enlist 11.9 76.2 9 $ 7 62.33 9 4 352 365
+7 Burrus 2846 CruiserMaxx APX + Saltro Enlist 11.6 72.1 15 $ 7 21.29 15 4 360 352
+8 Pioneer 28A65 FI + Lumigen Enlist 11.8 71.4 19 $ 7 13.52 19 4 360 349
+9 Alloy 28E34 FI + Ilevo Enlist 11.4 66.7 25 $ 6 67.47 25 4 360 325
+10 Apex 2930 FI + Saltro Enlist 11.7 72.7 13 $ 7 26.61 13 4 360 355
+11 Merschman Cherokee 2429 FI + Saltro + Tripidity Enlist 11.5 76.9 6 $ 7 69.29 6 4 360 375
+12 Apex 2940 FI + Saltro Enlist 11.3 72.0 16 $ 7 19.63 16 4 360 350
+13 Alloy 30E35 FI + Ilevo Enlist 12.0 77.5 4 $ 7 75.14 4 4 360 380
+14 Apex 2950 FI + Saltro Enlist 12.0 73.4 11 $ 7 34.35 11 4 360 360
+15 Merschman Lincoln 2431 FI + Saltro + Tripidity Enlist 11.4 74.8 10 $ 7 47.57 10 4 360 364
+16 Apex 3131S FI + Saltro Enlist 11.8 73.2 12 $ 7 31.93 12 4 360 358
+17 Pioneer 31A73 FI + Lumigen Enlist 11.6 76.8 7 $ 7 68.42 7 4 360 375
+18 Apex 3150 FI + Saltro Enlist 11.6 71.9 17 $ 7 19.24 17 4 360 351
+19 Alloy 33E34 FI + Ilevo Enlist 12.0 77.1 5 $ 7 71.06 5 4 360 378
+20 Apex 3340 FI + Saltro Enlist 11.5 77.5 3 $ 7 75.44 3 4 360 378
+21 Burrus 3415 CruiserMaxx APX + Saltro Enlist 11.4 76.8 8 $ 7 68.10 8 4 360 374
+22 Alloy 34E35 FI + Ilevo Enlist 11.4 68.2 21 $ 6 81.85 21 4 360 332
+23 ProHarvest 35E52 FI + Saltro Enlist 11.9 71.9 18 $ 7 18.84 18 4 360 352
+24 Apex 3541 FI + Saltro Enlist 11.4 71.1 20 $ 7 10.60 20 4 360 346
+25 Don Mario 36E94 CruiserMaxx APX + Saltro Enlist 11.2 68.1 22 $ 6 81.33 22 4 360 331
+26 Apex 3720S FI + Saltro Enlist 11.2 66.9 24 $ 6 68.98 24 4 360 325
+27 Burrus 3767 CruiserMaxx APX + Saltro Enlist 12.2 67.6 23 $ 6 75.69 23 4 360 332
+Plot Average 0.0 72.7
+GPS Coordinates: (41.1065591, -88.0955062)
+Stake is in first row of entry
+planted South to North
+```