def write(self): triples = [] for proceedings in self.data['proceedings']: if len(proceedings['related']) > 0: resource = create_proceedings_uri(proceedings['volume_number']) for related in proceedings['related']: related_resource = create_proceedings_uri(related) triples.append((resource, RDFS.seeAlso, related_resource)) self.write_triples(triples)
def write(self): triples = [] for proceedings in self.data['proceedings']: if len(proceedings['related']) > 0: resource = create_proceedings_uri(proceedings['volume_number']) for related in proceedings['related']: related_url = "http://ceur-ws.org/Vol-%s/" % related if len(config.input_urls) > 1 and related_url not in config.input_urls: config.input_urls.append(related_url) # # self.spider.add_task(Task('initial', url=related_url)) related_resource = create_proceedings_uri(related) triples.append((resource, RDFS.seeAlso, related_resource)) self.write_triples(triples)
def write(self): triples = [] for proceedings in self.data['proceedings']: if len(proceedings['related']) > 0: resource = create_proceedings_uri(proceedings['volume_number']) for related in proceedings['related']: related_url = "http://ceur-ws.org/Vol-%s/" % related if len(config.input_urls ) > 1 and related_url not in config.input_urls: config.input_urls.append(related_url) # # self.spider.add_task(Task('initial', url=related_url)) related_resource = create_proceedings_uri(related) triples.append((resource, RDFS.seeAlso, related_resource)) self.write_triples(triples)
def begin_template(self): self.data['volume_number'] = WorkshopPageParser.extract_volume_number(self.task.url) self.data['proceedings'] = create_proceedings_uri(self.data['volume_number']) workshops = [w for w in self.graph.objects(self.data['proceedings'], BIBO.presentedAt)] if len(workshops) > 1: self.data['workshops'] = workshops else: raise DataNotFound('Skipping http://ceur-ws.org/Vol-%s/ proceedings, because it\'s not joint' % self.data['volume_number'])
def write(self): triples = [] proceedings = create_proceedings_uri(self.data['volume_number']) conference = URIRef(config.id['conference'] + urllib.quote(self.data['acronym'] + "-" + self.data['year'])) triples.append((conference, RDF.type, SWC.OrganizedEvent)) triples.append((conference, RDFS.label, Literal(self.data['acronym'], datatype=XSD.string))) triples.append((conference, TIMELINE.atDate, Literal(self.data['year'], datatype=XSD.gYear))) for workshop in self.graph.objects(proceedings, BIBO.presentedAt): triples.append((workshop, SWC.isSubEventOf, conference)) self.write_triples(triples)
def write(self): triples = [] proceedings = create_proceedings_uri(self.data['volume_number']) conference = URIRef(config.id['conference'] + urllib.quote(self.data['acronym'] + "-" + self.data['year'])) triples.append((conference, RDF.type, SWRC.Conference)) triples.append((conference, BIBO.shortTitle, Literal(self.data['acronym'], datatype=XSD.string))) triples.append((conference, TIMELINE.atDate, Literal(self.data['year'], datatype=XSD.gYear))) for workshop in self.graph.objects(proceedings, BIBO.presentedAt): triples.append((workshop, SWC.isSubEventOf, conference)) self.write_triples(triples)
def begin_template(self): self.data['volume_number'] = WorkshopPageParser.extract_volume_number(self.task.url) self.data['proceedings'] = create_proceedings_uri(self.data['volume_number']) self.editors = [] for editor in self.graph.objects(self.data['proceedings'], FOAF.maker): editor_name = self.graph.value(editor, FOAF.name) if(editor_name.split(' ', 1)[0].find('.') > 0): self.editors.append((editor, editor_name)) if len(self.editors) == 0: raise DataNotFound('Skipping http://ceur-ws.org/Vol-%s/, because the name are okay' % self.data['volume_number'])
def begin_template(self): self.data['workshop'] = self.task.url self.data['volume_number'] = self.extract_volume_number(self.task.url) proceedings = create_proceedings_uri(self.data['volume_number']) self.data['workshops'] = [] for workshop in self.graph.objects(proceedings, BIBO.presentedAt): try: label = self.graph.objects(workshop, BIBO.shortTitle).next() self.data['workshops'].append((workshop, label.toPython())) except StopIteration: pass except: traceback.print_exc()
def begin_template(self): self.data['volume_number'] = WorkshopPageParser.extract_volume_number(self.task.url) self.data['proceedings'] = create_proceedings_uri(self.data['volume_number']) self.editors = [] for editor in self.graph.objects(self.data['proceedings'], FOAF.maker): editor_name = self.graph.value(editor, FOAF.name) if editor_name.split(' ', 1)[0].find('.') > 0: self.editors.append((editor, editor_name)) if len(self.editors) == 0: raise DataNotFound('Skipping http://ceur-ws.org/Vol-%s/, because the name are okay' % self.data['volume_number'])
def write(self): triples = [] proceedings = create_proceedings_uri(self.data['volume_number']) workshops = self.graph.objects(proceedings, BIBO.presentedAt) proceedings_related = self.graph.objects(proceedings, RDFS.seeAlso) workshops_related = [] for p_related in proceedings_related: map(workshops_related.append, self.graph.objects(p_related, BIBO.presentedAt)) for workshop in workshops: for workshop_related in workshops_related: if self.is_related(workshop, workshop_related): triples.append((workshop, RDFS.seeAlso, workshop_related)) self.write_triples(triples)
def begin_template(self): self.data['volume_number'] = WorkshopPageParser.extract_volume_number(self.task.url) self.data['proceedings'] = create_proceedings_uri(self.data['volume_number'])