""" Advanced WFS probing - BBOX with correct CRS, cross-workspace layers, and deep property inspection of the richest layers. """ import json import os import sys import time from datetime import datetime import requests import urllib3 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning) sys.stdout.reconfigure(encoding="utf-8") BASE_URL = "https://ymspace.ga.nycu.edu.tw:8080/geoserver/wfs" OUTPUT_DIR = r"C:\Users\thc1006\Desktop\NQSD\新增資料夾\data\ymmap_archive\wfs_cql_queries" def wfs_get(params, timeout=30): default = {"service": "WFS", "version": "1.1.0"} default.update(params) try: r = requests.get(BASE_URL, params=default, verify=False, timeout=timeout) return r except Exception as e: print(f" [ERROR] {e}") return None def get_json(type_name, extra_params=None, timeout=60): params = { "request": "GetFeature", "typeName": type_name, "outputFormat": "application/json", } if extra_params: params.update(extra_params) r = wfs_get(params, timeout=timeout) if r and r.status_code == 200: try: return r.json() except: return {"error": "non-json", "text": r.text[:500]} elif r: return {"error": f"HTTP {r.status_code}", "text": r.text[:500]} return None def save_json(data, filename): fpath = os.path.join(OUTPUT_DIR, filename) with open(fpath, "w", encoding="utf-8") as f: json.dump(data, f, ensure_ascii=False, indent=2) return fpath print("=" * 70) print("Advanced WFS Probing") print(f"Started: {datetime.now().isoformat()}") print("=" * 70) # ============================================================ # Part 1: Look at actual coordinate extents from building_geom # ============================================================ print("\n--- Part 1: Determine actual coordinate system from building data ---") # Get a sample building to see coordinate values data = get_json("gis:gis_building_geom", {"maxFeatures": "3"}) if data and "features" in data: for feat in data["features"]: name = feat["properties"].get("BuildName", "?") geom = feat.get("geometry", {}) gtype = geom.get("type", "?") # Get a sample coordinate coords = geom.get("coordinates", []) if gtype == "MultiPolygon" and coords: sample = coords[0][0][0] if coords[0] and coords[0][0] else None print(f" {name}: type={gtype}, sample_coord={sample}") elif gtype == "Polygon" and coords: sample = coords[0][0] if coords[0] else None print(f" {name}: type={gtype}, sample_coord={sample}") # Get CRS info crs = data.get("crs", {}) print(f" CRS info: {crs}") # Also check campus boundaries for coordinate extent data_campus = get_json("gis:gis_campus") if data_campus and "features" in data_campus: print("\n Campus boundaries:") for feat in data_campus["features"]: props = feat["properties"] name = props.get("NAME_CH", "?") area = props.get("area", "?") geom = feat.get("geometry", {}) if geom.get("coordinates"): coords_flat = [] def flatten_coords(c): if isinstance(c[0], (int, float)): coords_flat.append(c) else: for sub in c: flatten_coords(sub) flatten_coords(geom["coordinates"]) if coords_flat: xs = [c[0] for c in coords_flat] ys = [c[1] for c in coords_flat] print(f" {name}: area={area}") print(f" X range: {min(xs):.6f} - {max(xs):.6f}") print(f" Y range: {min(ys):.6f} - {max(ys):.6f}") # ============================================================ # Part 2: Deep inspection of gis_building (richest layer: 41 columns) # ============================================================ print("\n--- Part 2: Deep inspection of gis:gis_building (41 properties) ---") data_bldg = get_json("gis:gis_building") if data_bldg and "features" in data_bldg: save_json(data_bldg, "gis_gis_building_FULL_PROPERTIES.json") print(f" Saved full building data with all 41 properties") print(f" Total buildings: {len(data_bldg['features'])}") # Analyze which fields are populated vs empty all_keys = set() populated_counts = {} for feat in data_bldg["features"]: props = feat.get("properties", {}) for k, v in props.items(): all_keys.add(k) if v and str(v).strip(): populated_counts[k] = populated_counts.get(k, 0) + 1 print(f"\n Property population analysis ({len(data_bldg['features'])} buildings):") for key in sorted(all_keys): count = populated_counts.get(key, 0) pct = (count / len(data_bldg["features"])) * 100 if data_bldg["features"] else 0 print(f" {key:20s}: {count:3d}/{len(data_bldg['features'])} ({pct:.0f}%)") # Show interesting populated fields for first 5 buildings interesting_fields = [ "BuildID", "BuildName", "BuildNameEn", "Campus", "CampusID", "Floors", "UnFloors", "FArea", "Unit", "address", "BuildCategory", "BuildType", "BuildTypeName", "view360", "DescCh", "DescEn", "PropertyID", "PropertyName", "Lifetime", "Date_Accept", "Perimeter", "add_area", "Monument" ] print("\n Detailed building info (all 47):") for feat in data_bldg["features"]: props = feat.get("properties", {}) bid = props.get("BuildID", "?") bname = props.get("BuildName", "?") bname_en = props.get("BuildNameEn", "?") campus = props.get("Campus", "?") floors = props.get("Floors", "?") unfloors = props.get("UnFloors", "?") unit = props.get("Unit", "?") addr = props.get("address", "?") bcat = props.get("BuildCategory", "?") btype = props.get("BuildTypeName", "?") view = props.get("view360", "?") desc = str(props.get("DescCh", ""))[:80] print(f" [{bid}] {bname} / {bname_en}") print(f" Campus={campus}, Floors={floors}/{unfloors}, Unit={unit}") print(f" Category={bcat}, Type={btype}, Addr={addr}") if view and str(view).strip(): print(f" 360View={view}") if desc.strip(): print(f" Desc={desc}") # ============================================================ # Part 3: Deep inspection of gis_campus (rich metadata) # ============================================================ print("\n--- Part 3: Deep inspection of gis:gis_campus ---") if data_campus and "features" in data_campus: for feat in data_campus["features"]: props = feat.get("properties", {}) print(f" Campus: {props.get('NAME_CH')} / {props.get('NAME_EN')}") for k, v in sorted(props.items()): if k != "the_geom": print(f" {k}: {v}") # ============================================================ # Part 4: Try BBOX with correct coordinates (EPSG:4326) # ============================================================ print("\n--- Part 4: BBOX queries with correct coordinates ---") # Based on campus data, derive correct BBOX # Let's read the actual coordinates from the campus feature first if data_campus and "features" in data_campus: for feat in data_campus["features"]: name = feat["properties"].get("NAME_CH", "?") geom = feat["geometry"] coords_flat = [] def flatten_coords2(c): if isinstance(c[0], (int, float)): coords_flat.append(c) else: for sub in c: flatten_coords2(sub) flatten_coords2(geom["coordinates"]) if coords_flat: xs = [c[0] for c in coords_flat] ys = [c[1] for c in coords_flat] bbox = f"{min(xs)},{min(ys)},{max(xs)},{max(ys)}" print(f"\n Campus '{name}' BBOX: {bbox}") # Now try BBOX filter on buildings for layer in ["gis:gis_building_geom", "gis:gis_restaurant", "gis:gis_parking", "gis:gis_aed"]: data_bbox = get_json(layer, {"CQL_FILTER": f"BBOX(the_geom,{bbox})"}) if data_bbox and "features" in data_bbox: n = len(data_bbox["features"]) if n > 0: print(f" {layer}: {n} features") names = [f["properties"].get("name_ch") or f["properties"].get("BuildName") or "?" for f in data_bbox["features"][:5]] print(f" Sample: {names}") time.sleep(0.2) # ============================================================ # Part 5: Try different output formats # ============================================================ print("\n--- Part 5: Alternative output formats ---") formats_to_try = [ "application/json", "text/xml; subtype=gml/3.1.1", "csv", "application/vnd.google-earth.kml+xml", "SHAPE-ZIP", ] for fmt in formats_to_try: r = wfs_get({ "request": "GetFeature", "typeName": "gis:gis_building", "maxFeatures": "2", "outputFormat": fmt, }) if r: ct = r.headers.get("content-type", "?") print(f" Format '{fmt}': status={r.status_code}, content-type={ct}, size={len(r.content)} bytes") time.sleep(0.3) # ============================================================ # Part 6: Try GetPropertyValue (WFS 2.0 operation) # ============================================================ print("\n--- Part 6: GetPropertyValue attempts ---") for prop in ["BuildName", "BuildNameEn", "Campus", "Floors"]: r = wfs_get({ "request": "GetPropertyValue", "typeNames": "gis:gis_building", "valueReference": prop, "version": "2.0.0", }) if r: if r.status_code == 200: # Try to extract values import re values = re.findall(r"<[^>]*>([^<]+)([^<]+)", r.text) non_gis = [l for l in all_layers if not l.startswith("gis:")] if non_gis: print(f" Non-gis layers: {non_gis}") else: print(f" All {len(all_layers)} layers are in 'gis' namespace") # ============================================================ # Part 8: Check for stored queries (WFS 2.0) # ============================================================ print("\n--- Part 8: Stored queries ---") r = wfs_get({ "request": "ListStoredQueries", "version": "2.0.0", }) if r and r.status_code == 200: import re queries = re.findall(r'id="([^"]+)"', r.text) print(f" Stored queries: {queries}") else: print(f" ListStoredQueries: {'HTTP ' + str(r.status_code) if r else 'failed'}") # ============================================================ # Part 9: Try specific CQL filters for interesting data # ============================================================ print("\n--- Part 9: Targeted CQL filters ---") # Buildings with 360 views data_360 = get_json("gis:gis_building", {"CQL_FILTER": "view360 IS NOT NULL"}) if data_360 and "features" in data_360: buildings_360 = [(f["properties"].get("BuildName"), f["properties"].get("view360")) for f in data_360["features"] if f["properties"].get("view360") and str(f["properties"].get("view360")).strip()] print(f" Buildings with 360 views: {len(buildings_360)}") for name, url in buildings_360: print(f" {name}: {url}") # Buildings with descriptions data_desc = get_json("gis:gis_building", {"CQL_FILTER": "DescCh IS NOT NULL"}) if data_desc and "features" in data_desc: buildings_desc = [(f["properties"].get("BuildName"), f["properties"].get("DescCh"), f["properties"].get("DescEn")) for f in data_desc["features"] if f["properties"].get("DescCh") and str(f["properties"].get("DescCh")).strip()] print(f"\n Buildings with Chinese descriptions: {len(buildings_desc)}") for name, desc_ch, desc_en in buildings_desc[:10]: print(f" {name}:") print(f" CH: {str(desc_ch)[:100]}") print(f" EN: {str(desc_en)[:100]}" if desc_en else " EN: (none)") # Buildings by campus for campus_val in ["1", "2", "3", "YM", "GF", "陽明", "光復"]: data_c = get_json("gis:gis_building", { "CQL_FILTER": f"Campus = '{campus_val}'", "maxFeatures": "2", }) if data_c and "features" in data_c and len(data_c["features"]) > 0: print(f"\n Buildings with Campus='{campus_val}': {len(data_c['features'])} features") for f in data_c["features"][:2]: print(f" {f['properties'].get('BuildName')}") # Buildings by CampusID for cid in ["1", "2", "3"]: data_cid = get_json("gis:gis_building", { "CQL_FILTER": f"CampusID = '{cid}'", "maxFeatures": "2", }) if data_cid and "features" in data_cid and len(data_cid["features"]) > 0: print(f"\n Buildings with CampusID='{cid}': {len(data_cid['features'])} features") for f in data_cid["features"][:2]: print(f" {f['properties'].get('BuildName')} / {f['properties'].get('BuildNameEn')}") # Buildings by BuildCategory data_cats = get_json("gis:gis_building") if data_cats and "features" in data_cats: categories = set() types = set() for f in data_cats["features"]: cat = f["properties"].get("BuildCategory") bt = f["properties"].get("BuildType") btn = f["properties"].get("BuildTypeName") if cat: categories.add(cat) if bt: types.add((bt, btn)) print(f"\n BuildCategory values: {sorted(categories)}") print(f" BuildType/Name pairs: {sorted(types)}") # ============================================================ # Part 10: Explore busstop details with route info # ============================================================ print("\n--- Part 10: Bus stop details ---") data_bus = get_json("gis:gis_busstop") if data_bus and "features" in data_bus: for feat in data_bus["features"]: props = feat["properties"] coords = feat["geometry"]["coordinates"] if feat.get("geometry") else "?" print(f" {props.get('name_ch')} / {props.get('name_en')}") print(f" Routes: {props.get('desc_ch')}") print(f" Coords: {coords}") # ============================================================ # Part 11: Explore sport facilities # ============================================================ print("\n--- Part 11: Sport facilities ---") data_sport = get_json("gis:gis_sport") if data_sport and "features" in data_sport: for feat in data_sport["features"]: props = feat["properties"] print(f" {props.get('name_ch')} / {props.get('name_en')}") if props.get("url"): print(f" URL: {props['url']}") if props.get("photo"): print(f" Photo: {props['photo']}") # ============================================================ # Part 12: Explore campus photos with URLs # ============================================================ print("\n--- Part 12: Campus photos ---") data_photos = get_json("gis:gis_campusphotos") if data_photos and "features" in data_photos: for feat in data_photos["features"]: props = feat["properties"] print(f" {props.get('name_ch')} / {props.get('name_en')}") if props.get("url"): print(f" URL: {props['url']}") if props.get("keyword"): print(f" Keywords: {props['keyword']}") # Save combined deep analysis print("\n--- Saving combined results ---") combined = { "timestamp": datetime.now().isoformat(), "building_full": data_bldg if data_bldg and "features" in data_bldg else None, "campus_full": data_campus if data_campus and "features" in data_campus else None, "busstop_full": data_bus if (data_bus and "features" in data_bus) else None, } save_json(combined, "DEEP_PROPERTY_ANALYSIS.json") print(f"\nCompleted: {datetime.now().isoformat()}")