-
Notifications
You must be signed in to change notification settings - Fork 0
/
database_lagen_updaten
317 lines (257 loc) · 12.3 KB
/
database_lagen_updaten
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
import requests
import xml.etree.ElementTree as ET
from datetime import datetime, timedelta
import time
import pandas as pd
import geopandas as gpd
from shapely.geometry import Point, LineString, MultiLineString, Polygon, MultiPolygon
from shapely import wkt
from sqlalchemy import create_engine, text
from geoalchemy2 import Geometry, WKTElement
import configparser
import os
# Read configuration from config.ini
config = configparser.ConfigParser()
config.read('config.ini')
username = config['database']['username']
password = config['database']['password']
host = config['database']['host']
port = config['database']['port']
database_name = config['database']['database_name']
schema = config['database']['schema']
layer_point = config['database']['layer_point']
layer_line = config['database']['layer_line']
layer_polygon = config['database']['layer_polygon']
db_url = f'postgresql://{username}:{password}@{host}:{port}/{database_name}'
geometry_bounds_wkt = config['api']['geometry_bounds']
geometry_bounds = wkt.loads(geometry_bounds_wkt)
# Constants
API_ENDPOINT = "https://repository.overheid.nl/sru"
NAMESPACES = {
'sru': "http://docs.oasis-open.org/ns/search-ws/sruResponse",
'gzd': "http://standaarden.overheid.nl/sru",
'dcterms': "http://purl.org/dc/terms/",
'c': "http://standaarden.overheid.nl/collectie/",
'overheidwetgeving': "http://standaarden.overheid.nl/wetgeving/",
'overheid': "http://standaarden.overheid.nl/owms/terms/"
}
FIELDS_TO_EXTRACT = [
'dcterms:identifier', 'dcterms:title', 'dcterms:type', 'dcterms:creator',
'dcterms:modified', 'overheid:authority', 'dcterms:available',
'dcterms:hasVersion', 'dcterms:subject', 'dcterms:abstract',
'dcterms:publisher', 'c:product-area', 'c:content-area',
'overheidwetgeving:activiteit', 'overheidwetgeving:jaargang',
'overheidwetgeving:organisatietype', 'overheidwetgeving:publicatienummer',
'overheidwetgeving:publicatienaam'
]
def timer_decorator(func):
def wrapper(*args, **kwargs):
start_time = time.time()
result = func(*args, **kwargs)
elapsed_time = time.time() - start_time
print(f"Elapsed time for {func.__name__}: {elapsed_time:.2f} seconds")
return result
return wrapper
def validate_geometries(gdf):
"""Validate geometries in a GeoDataFrame and remove invalid ones."""
valid_gdf = gdf[gdf.is_valid]
invalid_gdf = gdf[~gdf.is_valid]
print(f"Found {len(invalid_gdf)} invalid geometries out of {len(gdf)}. Removing invalid geometries.")
return valid_gdf
@timer_decorator
def get_most_recent_date(db_url):
engine = create_engine(db_url)
most_recent_dates = []
table_names = [layer_line, layer_point, layer_polygon]
with engine.connect() as connection:
for table_name in table_names:
result = connection.execute(text(f"SELECT to_regclass('{schema}.{table_name}')"))
if result.scalar() is not None:
result = connection.execute(text(f"SELECT MAX(modified) FROM {schema}.{table_name}"))
most_recent_date = result.scalar()
if most_recent_date:
most_recent_dates.append(most_recent_date)
else:
print(f"Table {schema}.{table_name} does not exist")
if most_recent_dates:
most_recent_date = max(most_recent_dates)
else:
most_recent_date = None
print(f"Most recent date in PostGIS: {most_recent_date}")
return most_recent_date
@timer_decorator
def fetch_records(start_date):
all_records = []
start_record = 1
end_date = datetime.now()
start_date_str = start_date.strftime('%Y-%m-%d')
end_date_str = end_date.strftime('%Y-%m-%d')
while True:
params = {
'query': f"(c.product-area==officielepublicaties AND dt.modified>={start_date_str} AND dt.modified<={end_date_str})",
'startRecord': start_record,
'maximumRecords': 1000
}
response = requests.get(API_ENDPOINT, params=params)
if response.status_code != 200:
break
root = ET.fromstring(response.content)
records = root.findall('.//sru:record', NAMESPACES)
if not records:
break
for record in records:
extracted_data = extract_data(record)
all_records.extend(extracted_data)
start_record += 1000
if len(records) < 1000:
break
print(f'Records fetched: {len(all_records)}')
return all_records
def extract_data(record):
base_data = {field.split(':')[-1]: None for field in FIELDS_TO_EXTRACT}
for field in FIELDS_TO_EXTRACT:
found_element = record.find(f'.//{field}', NAMESPACES)
if found_element is not None:
base_data[field.split(':')[-1]] = found_element.text
has_version_element = record.find('.//dcterms:hasVersion', NAMESPACES)
identifier = base_data.get('identifier')
source = None
if has_version_element is not None and 'resourceIdentifier' in has_version_element.attrib:
source = has_version_element.attrib['resourceIdentifier'].replace('.html', '')
source_xml = f"https://repository.overheid.nl/sru?&query=(dt.identifier={identifier})" if identifier else None
record_data = []
for gebiedsmarkering in record.findall('.//overheidwetgeving:gebiedsmarkering', NAMESPACES):
geom_type = gebiedsmarkering.tag.split('}')[1]
geometries = gebiedsmarkering.findall('.//overheidwetgeving:geometrie', NAMESPACES)
labels = gebiedsmarkering.findall('.//overheidwetgeving:geometrielabel', NAMESPACES)
for geometry, label in zip(geometries, labels):
geo_data = base_data.copy()
geo_data['geometry'] = geometry.text
geo_data['source'] = source + '.html' if source else None
geo_data['source_xml'] = source_xml
geo_data['gebiedsmarkering_type'] = geom_type
geo_data['geometrieLabel'] = label.text if label is not None else None
record_data.append(geo_data)
return record_data
def fetch_metadata_url(source_xml_url, retries=3, backoff_factor=0.3):
attempt = 0
while attempt < retries:
try:
response = requests.get(source_xml_url)
if response.status_code == 200:
root = ET.fromstring(response.content)
metadata_url_element = root.find('.//gzd:itemUrl[@manifestation="metadata"]', NAMESPACES)
if metadata_url_element is not None:
return metadata_url_element.text
else:
print(f"No metadata URL found in source XML for URL: {source_xml_url}")
else:
print(f"Failed to fetch source XML from {source_xml_url}, status code: {response.status_code}")
except Exception as e:
print(f"Error fetching metadata URL from {source_xml_url}: {e}")
time.sleep(backoff_factor * (2 ** attempt)) # Exponential backoff
attempt += 1
return None
def fetch_referentienummer(metadata_url, retries=3, backoff_factor=0.3):
attempt = 0
while attempt < retries:
try:
response = requests.get(metadata_url)
if response.status_code == 200:
root = ET.fromstring(response.content)
referentienummer_element = root.find('.//metadata[@name="OVERHEIDop.referentienummer"]')
if referentienummer_element is not None:
return referentienummer_element.attrib.get('content')
else:
print(f"Failed to fetch metadata from {metadata_url}, status code: {response.status_code}")
except Exception as e:
print(f"Error fetching referentienummer from {metadata_url}: {e}")
time.sleep(backoff_factor * (2 ** attempt)) # Exponential backoff
attempt += 1
return None
@timer_decorator
def parse_geometries(df):
df['geometry'] = df['geometry'].apply(parse_geometry)
return df
def parse_geometry(geo_str):
try:
return wkt.loads(geo_str)
except Exception as e:
print("Failed to parse geometry:", geo_str, "Error:", e)
return None
@timer_decorator
def write_to_postgis(gdf, layer_name, db_url, schema):
engine = create_engine(db_url)
gdf.columns = map(str.lower, gdf.columns)
gdf.to_postgis(name=layer_name, con=engine, schema=schema, if_exists='append', index=False,
dtype={'geometry': Geometry(geometry_type='GEOMETRY', srid=28992)})
print(f'Writing to PostGIS layer: {layer_name}')
@timer_decorator
def delete_records_with_date_and_location(db_url, date, polygon_wkt):
engine = create_engine(db_url)
table_names = [layer_line, layer_point, layer_polygon]
total_deleted_count = 0
with engine.begin() as connection: # Use `begin` to ensure changes are committed
for table_name in table_names:
result = connection.execute(
text(f"""
DELETE FROM {schema}.{table_name}
WHERE modified = :date
RETURNING *
"""),
{'date': date, 'polygon': polygon_wkt}
)
deleted_count = result.rowcount
total_deleted_count += deleted_count
print(f"Deleted {deleted_count} records from {schema}.{table_name} with date {date}")
return total_deleted_count
def main():
most_recent_date_str = get_most_recent_date(db_url)
if most_recent_date_str is None:
most_recent_date = datetime.now() - timedelta(days=1)
else:
most_recent_date = datetime.strptime(most_recent_date_str, '%Y-%m-%d') + timedelta(seconds=1)
# Delete records based on date and location
deleted_count = delete_records_with_date_and_location(db_url, date=most_recent_date.strftime('%Y-%m-%d'),
polygon_wkt=geometry_bounds_wkt)
records = fetch_records(start_date=most_recent_date)
df = pd.DataFrame(records)
df = parse_geometries(df)
gdf_points = gpd.GeoDataFrame(df[df['geometry'].apply(lambda x: isinstance(x, Point))], geometry='geometry',
crs='EPSG:28992')
gdf_lines = gpd.GeoDataFrame(df[df['geometry'].apply(lambda x: isinstance(x, (LineString, MultiLineString)))],
geometry='geometry', crs='EPSG:28992')
gdf_polygons = gpd.GeoDataFrame(df[df['geometry'].apply(lambda x: isinstance(x, (Polygon, MultiPolygon)))],
geometry='geometry', crs='EPSG:28992')
print(f'Filtering geometry by area')
# Filter based on geometry bounds
gdf_points_within = gdf_points[gdf_points.within(geometry_bounds)]
gdf_lines_within = gdf_lines[gdf_lines.within(geometry_bounds)]
gdf_polygons_within = gdf_polygons[gdf_polygons.within(geometry_bounds)]
print(f'Fetching referentienummer from metadata')
# Fetch metadata URL and referentienummer for filtered geometries
unique_source_xmls = gdf_points_within['source_xml'].dropna().unique().tolist() + \
gdf_lines_within['source_xml'].dropna().unique().tolist() + \
gdf_polygons_within['source_xml'].dropna().unique().tolist()
unique_source_xmls = list(set(unique_source_xmls)) # Get unique URLs
metadata_dict = {}
referentienummer_dict = {}
for source_xml in unique_source_xmls:
metadata_url = fetch_metadata_url(source_xml)
if metadata_url:
metadata_dict[source_xml] = metadata_url
referentienummer_dict[source_xml] = fetch_referentienummer(metadata_url)
for gdf in [gdf_points_within, gdf_lines_within, gdf_polygons_within]:
gdf.loc[:, 'metadata_url'] = gdf['source_xml'].map(metadata_dict)
gdf.loc[:, 'referentienummer'] = gdf['metadata_url'].map(referentienummer_dict)
print(f'Writing to PostGIS')
# Write to PostGIS
write_to_postgis(gdf_points_within, layer_point, db_url, schema)
write_to_postgis(gdf_lines_within, layer_line, db_url, schema)
write_to_postgis(gdf_polygons_within, layer_polygon, db_url, schema)
added_count_within = len(gdf_points_within) + len(gdf_lines_within) + len(gdf_polygons_within)
print(f"Records removed with date outside geometry bounds: {deleted_count}")
print(f"Records added within geometry bounds: {added_count_within}")
print("Data fetching, saving, processing, and database writing completed successfully.")
if __name__ == '__main__':
main()