Fix: Remove build-time download script
Browse files
backend/scripts/download_hdx_panama.py
DELETED
|
@@ -1,105 +0,0 @@
|
|
| 1 |
-
#!/usr/bin/env python3
|
| 2 |
-
"""
|
| 3 |
-
Download Panama-specific datasets from HDX
|
| 4 |
-
"""
|
| 5 |
-
|
| 6 |
-
import requests
|
| 7 |
-
import geopandas as gpd
|
| 8 |
-
from pathlib import Path
|
| 9 |
-
import logging
|
| 10 |
-
import zipfile
|
| 11 |
-
import io
|
| 12 |
-
|
| 13 |
-
logging.basicConfig(level=logging.INFO)
|
| 14 |
-
logger = logging.getLogger(__name__)
|
| 15 |
-
|
| 16 |
-
DATA_DIR = Path(__file__).parent.parent / "data" / "hdx"
|
| 17 |
-
|
| 18 |
-
# HDX Dataset URLs (Panama-specific)
|
| 19 |
-
HDX_DATASETS = {
|
| 20 |
-
"waterways": {
|
| 21 |
-
"url": "https://data.humdata.org/dataset/9b925ead-6034-4ce8-92d9-45d3a1ece1fc/resource/e0dd9e95-5b04-4a5c-b7ef-31a2ea046e1c/download/hotosm_pan_waterways_lines_geojson.zip",
|
| 22 |
-
"description": "Panama Waterways from OpenStreetMap"
|
| 23 |
-
},
|
| 24 |
-
"road_surface": {
|
| 25 |
-
"url": "https://data.humdata.org/dataset/c55bf26a-eba6-402d-b004-8c4af8c24b39/resource/c03fa6cc-e698-4c10-8b05-77de91e13e86/download/panama_roads.geojson",
|
| 26 |
-
"description": "Panama Road Surface Data (AI-predicted paved/unpaved)"
|
| 27 |
-
},
|
| 28 |
-
"admin_3": {
|
| 29 |
-
"url": "https://data.humdata.org/dataset/d188544c-352b-419b-a489-0ae6b763bf21/resource/119d6756-749e-4e4f-bf3a-9694ce22df0a/download/pan_admin3_2021.geojson",
|
| 30 |
-
"description": "Panama Admin 3 (Corregimientos) Boundaries"
|
| 31 |
-
},
|
| 32 |
-
"admin_lines": {
|
| 33 |
-
"url": "https://data.humdata.org/dataset/d188544c-352b-419b-a489-0ae6b763bf21/resource/d7981358-867c-4034-aa1e-07d0f419c968/download/pan_admin_lines_2021.geojson",
|
| 34 |
-
"description": "Panama Admin Lines"
|
| 35 |
-
}
|
| 36 |
-
}
|
| 37 |
-
|
| 38 |
-
def download_and_extract_hdx(dataset_name, url, description):
|
| 39 |
-
"""Download and extract HDX dataset"""
|
| 40 |
-
logger.info(f"Downloading {description}...")
|
| 41 |
-
|
| 42 |
-
output_dir = DATA_DIR / dataset_name
|
| 43 |
-
output_dir.mkdir(parents=True, exist_ok=True)
|
| 44 |
-
|
| 45 |
-
try:
|
| 46 |
-
response = requests.get(url, timeout=60)
|
| 47 |
-
response.raise_for_status()
|
| 48 |
-
|
| 49 |
-
# Check if ZIP or direct GeoJSON
|
| 50 |
-
if url.endswith('.zip'):
|
| 51 |
-
# Extract ZIP
|
| 52 |
-
with zipfile.ZipFile(io.BytesIO(response.content)) as z:
|
| 53 |
-
z.extractall(output_dir)
|
| 54 |
-
logger.info(f"Extracted ZIP to {output_dir}")
|
| 55 |
-
|
| 56 |
-
# Find GeoJSON file
|
| 57 |
-
geojson_files = list(output_dir.glob("*.geojson"))
|
| 58 |
-
if geojson_files:
|
| 59 |
-
geojson_path = geojson_files[0]
|
| 60 |
-
gdf = gpd.read_file(geojson_path)
|
| 61 |
-
logger.info(f"Loaded {len(gdf)} features from {geojson_path.name}")
|
| 62 |
-
return geojson_path, len(gdf)
|
| 63 |
-
else:
|
| 64 |
-
# Direct GeoJSON
|
| 65 |
-
if dataset_name == "admin_3":
|
| 66 |
-
output_dir = DATA_DIR.parent / "base"
|
| 67 |
-
geojson_path = output_dir / "pan_admin3.geojson"
|
| 68 |
-
elif dataset_name == "admin_lines":
|
| 69 |
-
output_dir = DATA_DIR.parent / "base"
|
| 70 |
-
geojson_path = output_dir / "pan_adminlines.geojson"
|
| 71 |
-
else:
|
| 72 |
-
# Default behavior
|
| 73 |
-
geojson_path = output_dir / f"{dataset_name}.geojson"
|
| 74 |
-
|
| 75 |
-
# Ensure directory exists (critical for Docker build)
|
| 76 |
-
output_dir.mkdir(parents=True, exist_ok=True)
|
| 77 |
-
|
| 78 |
-
with open(geojson_path, 'wb') as f:
|
| 79 |
-
f.write(response.content)
|
| 80 |
-
|
| 81 |
-
gdf = gpd.read_file(geojson_path)
|
| 82 |
-
logger.info(f"Loaded {len(gdf)} features")
|
| 83 |
-
return geojson_path, len(gdf)
|
| 84 |
-
|
| 85 |
-
except Exception as e:
|
| 86 |
-
logger.error(f"Failed to download {dataset_name}: {e}")
|
| 87 |
-
return None, 0
|
| 88 |
-
|
| 89 |
-
def main():
|
| 90 |
-
logger.info("=== Downloading HDX Panama Datasets ===")
|
| 91 |
-
|
| 92 |
-
results = []
|
| 93 |
-
for name, info in HDX_DATASETS.items():
|
| 94 |
-
path, count = download_and_extract_hdx(name, info["url"], info["description"])
|
| 95 |
-
if path:
|
| 96 |
-
results.append({"dataset": name, "count": count, "path": path})
|
| 97 |
-
|
| 98 |
-
logger.info("\n=== Download Summary ===")
|
| 99 |
-
for result in results:
|
| 100 |
-
logger.info(f" {result['dataset']}: {result['count']} features")
|
| 101 |
-
|
| 102 |
-
return results
|
| 103 |
-
|
| 104 |
-
if __name__ == "__main__":
|
| 105 |
-
main()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|