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:
2026-06-04 21:04:33 -04:00
parent e356633d4f
commit 89eea0f2b4
567 changed files with 80023 additions and 8 deletions
@@ -0,0 +1,50 @@
# Soybean yield trial — Ben Bauman (Goodfield, IL, 2025)
- **Publisher:** ProHarvest Seeds (cross-vendor plot report)
- **Crop:** Soybean
- **Year:** 2025
- **Location:** Goodfield, IL · Woodford County
- **Source PDF:** https://proharvestseeds.com/wp-content/uploads/2025/10/Soy-Bauman-PLACE-Organic-min.pdf
---
## Trial data (verbatim from PDF)
```
Dealer/Sales Rep Parable Agronomics Irrigation: none
Cooperator: PBenr Baaumianrie HyPlabntedr Poipdulatsion: Plot Results
Year: 2025 Row Width: 30
Planting Date: 5/16/2025 Chemicals: none
Harvest Date: 9/30/2025 Previous Crop:
Tillage: organic Previous Chemical: none
Soil Type: Check Variety:
Fertilizer Used: Check Variance:
Other: 40.661261, -89.287869
Comments: organic. South to north planted order.
Row No. of Plant Harvest Test Harvest % #2
Company Variety RM Length Rows Pop. Pop. Wt. Weight Moist. Yield comments: from the combine
1Beck's 341ZZ 3.4 843 8 1563 8.8 70.6
2American Organic 27C34 2.7 843 8 1610 8.3 73.1
3Lakeview Farms LVF2849 2.8 843 8 1688 9.0 76.0
4Lakeview Farms LVF2872 2.8 843 8 1690 8.2 76.8
5LG Seeds LGS2801 2.8 843 8 1672 8.7 75.6
6Merschman Seeds Sioux 2228 2.8 843 8 1640 8.3 74.4
7Beck's 281ZZ 2.8 843 8 1690 8.8 76.3
8Merschman Seeds Shawnee 2629 2.9 843 8 1640 8.6 74.2
9ProHarvest 29C57 2.9 843 8 1648 9.1 74.1
10American Organic 3034 3 843 8 1570 8.8 70.9
11Lakeview Farms LVF3073 3 843 8 1662 9.1 74.8
12Beck's 310ZZ 3.1 843 8 1700 8.5 77.0
13Lakeview Farms LVF3134 3.1 843 8 1684 9.2 75.7
14ProHarvest 31C30 3.1 843 8 1770 8.8 79.9
15American Organic 33C44 3.3 843 8 1476 9.0 66.5
16Lakeview Farms LVF3432 3.4 843 8 1650 8.7 74.6
17Beck's 341ZZ 3.4 843 8 1676 9.1 75.4
18Lakeview Farms LVF3472 3.4 843 8 1700 9.0 76.6
19Merschman Seeds Wilson 2635 3.5 843 8 1718 8.7 77.6
20ProHarvest 35C56S 3.5 843 8 1710 8.7 77.3
21Lakeview Farms LVF3674 3.6 843 8 1726 8.7 78.0
22Beck's 341ZZ 3.4 843 8 1660 9.1 74.7
23 #DIV/0!
24 #N/A #DIV/0!
```