added conopy script proxy

README.md

@@ -96,9 +96,12 @@ If direct download is blocked, use a SOCKS5 proxy (`pip install PySocks`):
 python scripts/bootstrap_canopy.py \
   --bbox 27.3,58.4,35.8,61.4 \
   --output-dir data/canopy \
-  --proxy socks5://user:pass@host:port
+  --proxy socks5h://user:pass@host:port
 ```
 
+Use `socks5h://` (DNS via proxy), same as `curl --proxy socks5h://`. Plain `socks5://`
+resolves hostnames locally and may hang if local DNS is blocked.
+
 The same URL can be passed via `CANOPY_PROXY` env var instead of `--proxy`.
 
 The `/api/v1/landcover/path` endpoint samples all `.tif`/`.tiff` files under

api/tests/test_viewshed_and_canopy.py

@@ -67,13 +67,14 @@ def test_canopy_selects_intersecting_tiles_from_geojson_index() -> None:
 
 def test_canopy_parse_socks5_proxy_url() -> None:
     proxy = bootstrap_canopy.parse_socks5_proxy(
-        "socks5://proxy_user:secret@194.33.35.46:38599"
+        "socks5h://proxy_user:secret@194.33.35.46:38599"
     )
+    assert proxy.scheme == "socks5h"
     assert proxy.host == "194.33.35.46"
     assert proxy.port == 38599
     assert proxy.username == "proxy_user"
     assert proxy.password == "secret"
-    assert proxy.endpoint == "socks5://194.33.35.46:38599"
+    assert proxy.endpoint == "socks5h://194.33.35.46:38599"
 
 
 def test_canopy_urls_file_ignores_comments(tmp_path: Path) -> None:

scripts/bootstrap_canopy.py

@@ -63,10 +63,13 @@ def configure_socks5_proxy(proxy_url: str) -> Socks5Proxy:
         ) from exc
 
     proxy = parse_socks5_proxy(proxy_url)
+    # socks5h resolves hostnames on the proxy (like curl --proxy socks5h://).
+    rdns = proxy.scheme == "socks5h"
     socks.set_default_proxy(
         socks.SOCKS5,
         proxy.host,
         proxy.port,
+        rdns=rdns,
         username=proxy.username,
         password=proxy.password,
     )
@@ -140,11 +143,12 @@ def _asset_url(feature: dict[str, Any], base_url: str = META_CHM_V2_BASE_URL) ->
     return None
 
 
-def validate_urls(urls: list[str], sample_size: int = 2) -> None:
+def validate_urls(urls: list[str], sample_size: int = 2, *, timeout_s: int = 60) -> None:
+    print(f"validating {min(sample_size, len(urls))} sample URL(s)")
     for url in urls[:sample_size]:
         request = Request(url, headers={"Range": "bytes=0-0", "User-Agent": USER_AGENT})
         try:
-            with urlopen(request) as response:
+            with urlopen(request, timeout=timeout_s) as response:
                 if response.status >= 400:
                     raise SystemExit(f"Canopy URL is not reachable: {url} ({response.status})")
         except HTTPError as exc:
@@ -156,13 +160,17 @@ def validate_urls(urls: list[str], sample_size: int = 2) -> None:
             raise SystemExit(f"Canopy URL validation failed: {url}: {exc}") from exc
 
 
-def load_index(index_url: str) -> dict[str, Any]:
+def load_index(index_url: str, *, timeout_s: int = 120) -> dict[str, Any]:
     path = Path(index_url)
     if path.exists():
+        print(f"loading index from {path}")
         return json.loads(path.read_text(encoding="utf-8"))
+    print(f"loading index from {index_url}")
     request = Request(index_url, headers={"User-Agent": USER_AGENT})
-    with urlopen(request) as response:
-        return json.loads(response.read().decode("utf-8"))
+    with urlopen(request, timeout=timeout_s) as response:
+        payload = response.read()
+    print(f"index loaded ({_format_mb(len(payload))})")
+    return json.loads(payload.decode("utf-8"))
 
 
 def select_tile_urls(
@@ -294,14 +302,14 @@ def main() -> None:
     if args.urls_file is not None:
         urls = urls_from_file(args.urls_file)
     else:
-        index = load_index(args.index_url)
+        index = load_index(args.index_url, timeout_s=max(args.timeout_s, 120))
         urls = select_tile_urls(index, args.bbox)
 
     if not urls:
         raise SystemExit("No canopy tiles intersect requested AOI")
 
     if not args.skip_url_check:
-        validate_urls(urls)
+        validate_urls(urls, timeout_s=args.timeout_s)
 
     print(f"selected_tiles={len(urls)}")
     downloaded, skipped, failed = download_urls(