ettorerizza

from SPARQLWrapper import SPARQLWrapper, JSON

sparql = SPARQLWrapper("http://linkeddata.uriburner.com/sparql")
sparql.setQuery("""
    PREFIX xsd: <http://www.w3.org/2001/XMLSchema#> 
PREFIX foaf: <http://xmlns.com/foaf/0.1/> 
PREFIX owl: <http://www.w3.org/2002/07/owl#> 
 
 PREFIX wd: <http://www.wikidata.org/entity/>
 PREFIX wdt: <http://www.wikidata.org/prop/direct/>

ettorerizza

# -*- coding: utf-8 -*-
""" 
Test du Stanford NER tagger avec les modèles CRF d'Europeana
entrainés sur des journaux :
http://lab.kbresearch.nl/static/html/eunews.html
La fonction est lente --> songer au multiprocessing
"""
import warnings
with warnings.catch_warnings():
    warnings.filterwarnings("ignore",category=DeprecationWarning)

ettorerizza

library(rvest)
library(dplyr)

#création des urls de départ
main_url <- "https://fr.wikipedia.org/wiki/Décès_en_"
annee <- 2010:2018

urls <- paste0(main_url, annee)
#vecteur vide qui contiendra les urls des pages
liens <- vector()

ettorerizza

import requests
import functools
from ngram import NGram

def get_similar(data, target):
    G = NGram(target)
    return G.find(data)


class cache(object):

ettorerizza

import subprocess

console = subprocess.run('openrefine_cli.exe --help', shell=True, stdout=subprocess.PIPE).stdout.decode('utf8')

print(console)

ettorerizza

import requests
import requests_cache
from time import sleep

# Nominatim bloque les requêtes répétées
requests_cache.install_cache('nominatim_cache')


def get_nominatim(value, countrycodes=['BE',''], limit=5, lang="fr"):
    # doc : https://wiki.openstreetmap.org/wiki/Nominatim

ettorerizza

# -*- coding: utf-8 -*-
"""
Created on Fri Jan  5 12:35:54 2018

@author: ettor
"""

import pandas as pd
import requests
import requests_cache

ettorerizza

import  itertools 

def glance(d):
    """aperçu d'un échantillon non ordonné d'un dictionnaire"""
    return dict(itertools.islice(d.items(), 3))

glance(json_file)

ettorerizza

<qualifieddc xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:dc="http://purl.org/dc/elements/1.1" xmlns:dcterms="http://purl.org/dc/terms" xmlns:marcrel="http://www.loc.gov/marc.relators" xsi:schemaLocation="http://www.loc.gov/marc.relators http://imlsdcc2.grainger.illinois.edu/registry/marcrel.xsd" xsi:noNamespaceSchemaLocation="http://dublincore.org/schemas/xmls/qdc/2008/02/11/qualifieddc.xsd">
{{forNonBlank(cells["id"], v, "<dc:identifier>"+v.value+"</dc:identifier>", "")}}
{{forNonBlank(cells["Title"], v, "<dc:title>"+v.value+"</dc:title>", "")}}
{{forNonBlank(cells["Creator"], v, "<dc:creator>"+v.value+"</dc:creator>", "")}}
{{forNonBlank(cells["Date"], v, "<dc:date>"+v.value+"</dc:date>", "")}}
{{forNonBlank(cells["Description"], v, "<dc:description>"+v.value+"</dc:description>", "")}}
{{forNonBlank(cells["Description2"], v, "<dc:description>"+v.value+"</dc:description>", "")}}
{{forNonBlank(cells["Rights"], v, "<dc:rights>"+v.value+"</dc:rights>", "")}}
{{forNonBlank(cells["Type"], v, "<dc:

ettorerizza

import json
from pprint import pprint



with open(r'C:\Users\ettor\Desktop\lod-data.json') as f:
    data = json.load(f)

myfile = open('test.txt', 'a')
for key in data.keys():