Created
May 26, 2020 10:16
-
-
Save ncarboni/a1457b34b84b7472d170a1f238362578 to your computer and use it in GitHub Desktop.
Convert geonames RDF to usable format
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# script modified from https://github.com/rhasan/sw/blob/master/genames/convert2ntriples.py | |
# This script will take genames rdf dump available here http://download.geonames.org/all-geonames-rdf.zip | |
# and convert each triples to N-Triple seralization. | |
# The dump has one rdf document per toponym on every line of the file. | |
# The produced N-Triples will be written in geonames.nt file. The final geonames.nt file is approximately 13.21GB | |
#!/usr/bin/python | |
import rdflib | |
fo = open("geonames.nt", "wb") | |
totalStmt = 0 | |
with open("all-geonames-rdf.txt") as fileobject: | |
count = 0 | |
for line in fileobject: | |
# print ("Line number: ", count+1, ":", line) | |
if count/10000 == int(count/10000): | |
print(count) | |
if count%2 != 0: | |
g = rdflib.Graph() | |
result = g.parse(data=line,format='xml') | |
#print("graph has %s statements." % len(g)) | |
totalStmt += len(g) | |
s = g.serialize(format='nt') | |
fo.write(s) | |
#print s | |
#g.serialize(format='nt', destination='out.nt') | |
#else: | |
# print "Feature: ", line | |
count = count + 1 | |
# if count == 3000: | |
# break | |
print ("Total statements: ", totalStmt) | |
fo.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment