mirror of https://github.com/gsi-upm/sitc
Add Beatles introduction
parent
9937490213
commit
1f5318a357
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@ -1,49 +0,0 @@
|
|||||||
|
|
||||||
import sys
|
|
||||||
from future.standard_library import install_aliases
|
|
||||||
install_aliases()
|
|
||||||
|
|
||||||
from urllib import request, parse
|
|
||||||
from rdflib import Graph, term
|
|
||||||
from lxml import etree
|
|
||||||
|
|
||||||
if len(sys.argv) < 2:
|
|
||||||
print('Usage: python {} <URL>'.format(sys.argv[0]))
|
|
||||||
print('')
|
|
||||||
print('Extract rdfa, microdata and json-ld annotations from a website')
|
|
||||||
exit(1)
|
|
||||||
|
|
||||||
url = sys.argv[1]
|
|
||||||
|
|
||||||
g = Graph()
|
|
||||||
g.parse(url, format='rdfa')
|
|
||||||
g.parse(url, format='microdata')
|
|
||||||
|
|
||||||
|
|
||||||
def sanitize_triple(t):
|
|
||||||
"""Function to remove bad URIs from the graph that would otherwise
|
|
||||||
make the serialization fail."""
|
|
||||||
def sanitize_triple_item(item):
|
|
||||||
if isinstance(item, term.URIRef) and '/' not in item:
|
|
||||||
return term.URIRef(parse.quote(str(item)))
|
|
||||||
return item
|
|
||||||
|
|
||||||
return (sanitize_triple_item(t[0]),
|
|
||||||
sanitize_triple_item(t[1]),
|
|
||||||
sanitize_triple_item(t[2]))
|
|
||||||
|
|
||||||
|
|
||||||
with request.urlopen(url) as response:
|
|
||||||
# Get all json-ld objects embedded in the html file
|
|
||||||
html = response.read().decode('utf-8', errors='ignore')
|
|
||||||
parser = etree.XMLParser(recover=True)
|
|
||||||
root = etree.fromstring(html, parser=parser)
|
|
||||||
if root:
|
|
||||||
for jsonld in root.findall(".//script[@type='application/ld+json']"):
|
|
||||||
g.parse(data=jsonld.text, publicID=url, format='json-ld')
|
|
||||||
|
|
||||||
|
|
||||||
fixedgraph = Graph()
|
|
||||||
fixedgraph += [sanitize_triple(s) for s in g]
|
|
||||||
|
|
||||||
print(g.serialize(format='turtle').decode('utf-8', errors='ignore'))
|
|
@ -1,29 +0,0 @@
|
|||||||
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
|
|
||||||
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
|
|
||||||
@prefix schema: <http://schema.org/> .
|
|
||||||
|
|
||||||
|
|
||||||
_:Hotel1 a schema:Hotel ;
|
|
||||||
schema:description "A fictitious hotel" .
|
|
||||||
|
|
||||||
|
|
||||||
_:Review1 a schema:Review ;
|
|
||||||
schema:reviewBody "This is a great review" ;
|
|
||||||
schema:reviewRating [
|
|
||||||
a schema:Rating ;
|
|
||||||
schema:author <http://jfernando.es/me> ;
|
|
||||||
schema:ratingValue "0.7"
|
|
||||||
|
|
||||||
] ;
|
|
||||||
schema:itemReviewed _:Hotel1 .
|
|
||||||
|
|
||||||
|
|
||||||
_:Review2 a schema:Review ;
|
|
||||||
schema:reviewBody "This is a not so great review" ;
|
|
||||||
schema:reviewRating [
|
|
||||||
a schema:Rating ;
|
|
||||||
schema:author [ a schema:Person ;
|
|
||||||
schema:givenName "anonymous" ] ;
|
|
||||||
schema:ratingValue "0.3"
|
|
||||||
] ;
|
|
||||||
schema:itemReviewed _:Hotel1 .
|
|
@ -1,23 +0,0 @@
|
|||||||
# !/bin/env python #
|
|
||||||
# Ejemplo de consultas SPARQL sobre turtle #
|
|
||||||
# python consultas.py #
|
|
||||||
import rdflib
|
|
||||||
import sys
|
|
||||||
|
|
||||||
dataset = sys.argv[1] if len(sys.argv) > 1 else 'reviews.ttl'
|
|
||||||
g = rdflib.Graph()
|
|
||||||
|
|
||||||
schema = rdflib.Namespace("http://schema.org/")
|
|
||||||
|
|
||||||
# Read Turtle file #
|
|
||||||
g.parse(dataset, format='turtle')
|
|
||||||
|
|
||||||
results = g.query(
|
|
||||||
"""SELECT DISTINCT ?review ?p ?o
|
|
||||||
WHERE {
|
|
||||||
?review a schema:Review.
|
|
||||||
?review ?p ?o.
|
|
||||||
}""", initNs={'schema': schema})
|
|
||||||
|
|
||||||
for row in results:
|
|
||||||
print("%s %s %s" % row)
|
|
@ -1,6 +0,0 @@
|
|||||||
import rdflib
|
|
||||||
import sys
|
|
||||||
g = rdflib.Graph()
|
|
||||||
dataset = sys.argv[1] if len(sys.argv) > 1 else 'reviews.ttl'
|
|
||||||
g.parse(dataset, format="n3")
|
|
||||||
print(g.serialize(format="n3").decode('utf-8'))
|
|
Loading…
Reference in New Issue