Created a script to pull sighting data from

INatraulist in just the US based on species list

dev_scripts/map_viewer.py

@@ -0,0 +1,88 @@
+"""
+Visualize species sighting coordinates overlaid on a map.
+Usage:
+  python dev_scripts/map_viewer.py                  # shows all species
+  python dev_scripts/map_viewer.py "Mallard"        # filter by common name (partial match)
+  python dev_scripts/map_viewer.py --list           # list all available species
+
+Requires: pip install folium
+"""
+
+import csv
+import json
+import sys
+import webbrowser
+from pathlib import Path
+
+SIGHTINGS_FILE = Path(__file__).parent.parent / "wildlife" / "portland_wildlife_sightings.csv"
+OUTPUT_HTML    = Path(__file__).parent.parent / "wildlife" / "sightings_map.html"
+PORTLAND_CENTER = [45.5051, -122.6750]
+
+
+def load_sightings(filter_name: str | None = None) -> list[dict]:
+    rows = []
+    with open(SIGHTINGS_FILE, newline="", encoding="utf-8") as f:
+        for row in csv.DictReader(f):
+            coords = json.loads(row["sighting_coordinates"])
+            if not coords:
+                continue
+            if filter_name and filter_name.lower() not in row["common_name"].lower():
+                continue
+            rows.append({
+                "taxon_id":      row["taxon_id"],
+                "common_name":   row["common_name"],
+                "scientific_name": row["scientific_name"],
+                "coords":        coords,
+            })
+    return rows
+
+
+def build_map(species_list: list[dict]) -> str:
+    try:
+        import folium
+    except ImportError:
+        print("folium is not installed. Run: pip install folium")
+        sys.exit(1)
+
+    m = folium.Map(location=PORTLAND_CENTER, zoom_start=11, tiles="OpenStreetMap")
+
+    for sp in species_list:
+        for lat, lng in sp["coords"]:
+            folium.CircleMarker(
+                location=[lat, lng],
+                radius=5,
+                color="red",
+                fill=True,
+                fill_color="red",
+                fill_opacity=0.7,
+                tooltip=f"{sp['common_name']}<br><i>{sp['scientific_name']}</i>",
+            ).add_to(m)
+
+    return m._repr_html_()
+
+
+def main():
+    if "--list" in sys.argv:
+        with open(SIGHTINGS_FILE, newline="", encoding="utf-8") as f:
+            for row in csv.DictReader(f):
+                coords = json.loads(row["sighting_coordinates"])
+                print(f"  {row['common_name']:40s} {len(coords)} sightings")
+        return
+
+    filter_name = next((a for a in sys.argv[1:] if not a.startswith("--")), None)
+    species_list = load_sightings(filter_name)
+
+    if not species_list:
+        print(f"No species found matching '{filter_name}'")
+        return
+
+    print(f"Plotting {len(species_list)} species...")
+    html = build_map(species_list)
+
+    OUTPUT_HTML.write_text(html, encoding="utf-8")
+    print(f"Map saved to {OUTPUT_HTML}")
+    webbrowser.open(OUTPUT_HTML.as_uri())
+
+
+if __name__ == "__main__":
+    main()

dev_scripts/sighting_fetcher.py

@@ -0,0 +1,112 @@
+import csv
+import json
+import time
+import requests
+from pathlib import Path
+
+PLACE_ID    = 2143
+BASE_URL    = "https://api.inaturalist.org/v1/observations"
+INPUT_FILE  = Path(__file__).parent.parent / "wildlife" / "portland_wildlife.csv"
+OUTPUT_FILE = Path(__file__).parent.parent / "wildlife" / "portland_wildlife_sightings.csv"
+OUTPUT_FIELDS = ["taxon_id", "scientific_name", "common_name", "sighting_coordinates"]
+
+
+def load_already_fetched(path: Path) -> set[int]:
+    """Return set of taxon_ids already written to the output CSV."""
+    if not path.exists():
+        return set()
+    done = set()
+    try:
+        with open(path, newline="", encoding="utf-8") as f:
+            for row in csv.DictReader(f):
+                done.add(int(row["taxon_id"]))
+    except Exception:
+        pass
+    return done
+
+
+def fetch_observations(taxon_id: int) -> list[list[float]]:
+    """Fetch up to 600 random research-grade observations (3 pages x 200) and return [lat, lng] pairs."""
+    coords = []
+    for page in range(1, 4):
+        response = requests.get(
+            BASE_URL,
+            headers={"User-Agent": "WildDex (wildlife dex app; contact via colemanswenson@gmail.com)"},
+            params={
+                "taxon_id":      taxon_id,
+                "quality_grade": "research",
+                "per_page":      200,
+                "page":          page,
+                "order_by":      "random",
+                "swlat":         14.5,
+                "swlng":        -168.0,
+                "nelat":         72.0,
+                "nelng":        -52.0,
+            },
+        )
+        response.raise_for_status()
+        results = response.json().get("results", [])
+        if not results:
+            break
+        for obs in results:
+            location = obs.get("location")
+            if not location:
+                continue
+            try:
+                lat, lng = location.split(",")
+                coords.append([float(lat), float(lng)])
+            except (ValueError, AttributeError):
+                continue
+        time.sleep(1)
+    return coords
+
+
+def read_species(path: Path) -> list[dict]:
+    """Read portland_wildlife.csv and return all rows with taxon_id cast to int."""
+    with open(path, newline="", encoding="utf-8") as f:
+        rows = list(csv.DictReader(f))
+    for row in rows:
+        row["taxon_id"] = int(row["taxon_id"])
+    return rows
+
+
+def main() -> None:
+    species   = read_species(INPUT_FILE)
+    done      = load_already_fetched(OUTPUT_FILE)
+    is_new    = not OUTPUT_FILE.exists() or OUTPUT_FILE.stat().st_size == 0
+    total     = len(species)
+
+    with open(OUTPUT_FILE, "a", newline="", encoding="utf-8") as f:
+        writer = csv.DictWriter(f, fieldnames=OUTPUT_FIELDS)
+        if is_new:
+            writer.writeheader()
+
+        for i, sp in enumerate(species, start=1):
+            taxon_id = sp["taxon_id"]
+
+            if taxon_id in done:
+                print(f"[{i}/{total}] Skipping {sp['common_name']} (already done)")
+                continue
+
+            try:
+                coords = fetch_observations(taxon_id)
+            except requests.HTTPError as e:
+                print(f"[{i}/{total}] {sp['common_name']} — HTTP error {e}, skipping")
+                coords = []
+
+            writer.writerow({
+                "taxon_id":            taxon_id,
+                "scientific_name":     sp["scientific_name"],
+                "common_name":         sp["common_name"],
+                "sighting_coordinates": json.dumps(coords),
+            })
+            f.flush()
+
+            print(f"[{i}/{total}] {sp['common_name']} ({taxon_id}) — {len(coords)} coords")
+            time.sleep(1)
+
+    print(f"\nDone. Output: {OUTPUT_FILE}")
+
+
+if __name__ == "__main__":
+    main()