Skip to content

Instantly share code, notes, and snippets.

View LvanWissen's full-sized avatar

Leon van Wissen LvanWissen

11 followers · 3 following
View GitHub Profile
@LvanWissen
LvanWissen / vele-handen@1.csv
Last active September 13, 2023 15:24
Get Metadata from SAA Beeldbank OpenSearch for VeleHanden data
We can't make this file beautiful and searchable because it's too large.
"velehanden_scan_id","memorix_id","beeldbank_id","gcps"
"7","ANWD00674000001","b8d437e8-b31b-7d7b-8629-99b635efd30f","{""id"":""marker_1"",""title"":"""",""imageLat"":""85.03914893626745"",""imageLng"":""-179.66371536254883"",""imageGeoLat"":""808.0000000005821"",""imageGeoLng"":""1958.9999999998836"",""geoLat"":""52.38581563110102"",""geoLng"":""4.882950782775879""}"
"7","ANWD00674000001","e0145944-3ee2-f6ad-73f9-20b5f8b8fd92","{""id"":""marker_3"",""title"":"""",""imageLat"":""85.0357484008423"",""imageLng"":""-179.64242935180664"",""imageGeoLat"":""1037.0000000003492"",""imageGeoLng"":""2083"",""geoLat"":""52.36034868684877"",""geoLng"":""4.904108047485351""}"
"7","ANWD00674000001","2cbe704f-fac4-6dd0-5303-e0aa847f056a","{""id"":""marker_4"",""title"":"""",""imageLat"":""85.03793154442138"",""imageLng"":""-179.62783813476562"",""imageGeoLat"":""890.0000000001164"",""imageGeoLng"":""2168"",""geoLat"":""52.37570397280555"",""geoLng"":""4.92161750793457""}"
"11","ANWG00507000001","a93dd690-6ee7-96aa-5ca9-f623
@LvanWissen
LvanWissen / sparql2rdfs.rq
Created December 10, 2021 10:22
SPARQL query to construct a RDFS vocabulary from a dataset.
PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
CONSTRUCT {
?classType a rdfs:Class ;
rdfs:label ?classLabel .
?property a rdf:Property ;
rdfs:domain ?classType ;
@LvanWissen
LvanWissen / CT_2021_02_01.json
Last active February 1, 2021 22:07
Get a list of all CERL Thesaurus identifiers (cnc, cni, cnp, cnl)
["cnc00000001", "cnc00000008", "cnc00000009", "cnc00000013", "cnc00000014", "cnc00000015", "cnc00000016", "cnc00000017", "cnc00000018", "cnc00000019", "cnc00000020", "cnc00000021", "cnc00000023", "cnc00000024", "cnc00000025", "cnc00000029", "cnc00000030", "cnc00000031", "cnc00000032", "cnc00000033", "cnc00000034", "cnc00000035", "cnc00000036", "cnc00000037", "cnc00000041", "cnc00000049", "cnc00000050", "cnc00000052", "cnc00000054", "cnc00000055", "cnc00000058", "cnc00000059", "cnc00000062", "cnc00000064", "cnc00000065", "cnc00000066", "cnc00000068", "cnc00000069", "cnc00000070", "cnc00000071", "cnc00000072", "cnc00000073", "cnc00000076", "cnc00000079", "cnc00000081", "cnc00000084", "cnc00000086", "cnc00000087", "cnc00000088", "cnc00000089", "cnc00000090", "cnc00000091", "cnc00000092", "cnc00000093", "cnc00000095", "cnc00000096", "cnc00000097", "cnc00000098", "cnc00000099", "cnc00000100", "cnc00000101", "cnc00000102", "cnc00000103", "cnc00000106", "cnc00000108", "cnc00000109", "cnc00000110", "cnc00000111", "cn
@LvanWissen
LvanWissen / a2a_saa.py
Created November 19, 2020 12:17
Download alle A2A-records van 8 indexen voor Golden Agents
import os
from sickle import Sickle
from sickle.iterator import OAIResponseIterator
def main(url: str):
for (setSpec,
name) in [("08953f2f-309c-baf9-e5b1-0cefe3891b37",
"SAA-ID-001_SAA_Index_op_notarieel_archief"),
("f6e5401f-c486-5f3d-6a5c-6e277e12628e",
@LvanWissen
LvanWissen / eye_afficheproject.py
Last active November 12, 2020 17:52
Download van metadata (csv + json) van alle affiches uit het Afficheproject van het Geheugen van Nederland (Delpher)
import json
import requests
import pandas as pd
from bs4 import BeautifulSoup
URL = "https://geheugen.delpher.nl/nl/geheugen/results?query=Eye+AND+afficheproject&maxperpage=1000&coll=ngvn&page="
def main(destination, pages, URL=URL):
@LvanWissen
LvanWissen / main.py
Created June 28, 2020 10:29
Repertorium van ambtsdragers
import requests
from bs4 import BeautifulSoup
from time import sleep
import json
import datetime
import calendar
from dateutil import relativedelta
@LvanWissen
LvanWissen / alto2text.py
Last active December 3, 2019 18:14
Convert Alto to text
"""
Usage for one file:
$ python alto2text.py filename.xml > filename.txt
Usage for multiple files:
$ for f in *.xml; do python alto2text.py $f > $f.txt; done
"""
import sys
from lxml import etree
@LvanWissen
LvanWissen / convertWeddingPoems.py
Last active December 12, 2019 10:38
from collections import defaultdict
from itertools import count
from rdflib import Graph, URIRef, Literal, XSD, Namespace, RDFS, BNode
from rdfalchemy import rdfSubject, rdfMultiple, rdfSingle
import pandas as pd
DATA = pd.read_csv('gedichtenGGD_STCN_Steur_stripped.csv', sep=';')
@LvanWissen
LvanWissen / getAddressAmsterdam.py
Created November 7, 2019 11:41
Fetch a centroid of a 'nummeraanduidingobject' from the Amsterdam BAG API
"""
Using the Amsterdam address BAG data, fetch a 'centroid' by address (street + number).
See: https://api.data.amsterdam.nl/atlas/search/adres/
"""
import re
import requests
def get_centroid(q):
@LvanWissen
LvanWissen / OpenRotatingFiles.py
Created October 22, 2018 11:40
Use one of the file handlers of the python logging module to automatically split an output file into multiple files, based on a maximum size.
import logging
from logging.handlers import BaseRotatingHandler, RotatingFileHandler
class OpenRotatingFiles(RotatingFileHandler):
def __init__(self, filename, mode='a', maxBytes=0, backupCount=0, encoding=None, delay=False, prefix="", suffix=""):
"""
Addition to RotatingFileHandler to use this as a file handler that
creates a new file on maxBytes. Uses an optional prefix and suffix that
is printed after and before each rotation. The backupCount setting should