Class: BibCard::Crawler

Inherits:
Object
  • Object
show all
Defined in:
lib/bib_card/crawler.rb

Constant Summary collapse

SPARQL_ENDPOINTS =
{
  getty: "http://vocab.getty.edu/sparql?query=",
  wikidata: "http://query.wikidata.org/sparql?query=",
  dbpedia: "http://dbpedia.org/sparql?query="
}

Instance Method Summary collapse

Constructor Details

#initialize(uri, repository) ⇒ Crawler

Returns a new instance of Crawler.



4
5
6
7
# File 'lib/bib_card/crawler.rb', line 4

def initialize(uri, repository)
  @subject = RDF::URI(uri)
  @repository = repository
end

Instance Method Details

#alma_matersObject



328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
# File 'lib/bib_card/crawler.rb', line 328

def alma_maters
  sparql = "
  #{self.wikidata_sparql_prefixes}

  SELECT DISTINCT ?inst ?instLabel ?statement ?reference ?source ?sourceLabel
  WHERE
  {
    <#{self.wikidata_uri.to_s}> p:P69 ?statement .
    ?statement ps:P69 ?inst .
    ?inst rdfs:label ?instLabel .
    FILTER(langMatches(lang(?instLabel), \"en\"))
    OPTIONAL {
      ?statement prov:wasDerivedFrom ?reference .
      ?reference pref:P248 ?source .
      ?source rdfs:label ?sourceLabel .
      FILTER(langMatches(lang(?sourceLabel), \"en\"))
    }
  }
  "
  get_data(sparql, :wikidata)
end

#birth_dateObject



15
16
17
18
# File 'lib/bib_card/crawler.rb', line 15

def birth_date
  stmt = @repository.query({subject: @subject, predicate: SCHEMA_BIRTHDATE}).first
  stmt.nil? ? nil : stmt.object
end

#brief_bioObject



350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
# File 'lib/bib_card/crawler.rb', line 350

def brief_bio
  sparql = "
  #{self.wikidata_sparql_prefixes}

  SELECT DISTINCT ?description ?workLocation ?workLocationLabel
  WHERE
  {
    <#{self.wikidata_uri.to_s}> schema:description ?description .
    OPTIONAL {
      <#{self.wikidata_uri.to_s}> wdt:P937 ?workLocation .
    }
    SERVICE wikibase:label {
      bd:serviceParam wikibase:language \"en\" .
    }
    FILTER(langMatches(lang(?description), \"en\"))
  }
  "
  get_data(sparql, :wikidata).first
end

#creator_graphObject



45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
# File 'lib/bib_card/crawler.rb', line 45

def creator_graph
  graph = RDF::Graph.new
  if @repository.size > 0
    @repository.query({subject: @subject, predicate: RDF.type}).each {|stmt| graph << stmt}
    @repository.query({subject: @subject, predicate: SCHEMA_NAME}).each {|stmt| graph << stmt}
    graph << [@subject, SCHEMA_BIRTHDATE, self.birth_date] if self.birth_date
    graph << [@subject, SCHEMA_DEATHDATE, self.death_date] if self.death_date
    graph << [@subject, SCHEMA_SAME_AS, self.loc_uri] if self.loc_uri
    graph << [@subject, SCHEMA_SAME_AS, self.dbpedia_uri] if self.dbpedia_uri
    graph << [@subject, SCHEMA_SAME_AS, self.getty_uri] if self.getty_uri
    graph << [@subject, SCHEMA_SAME_AS, self.wikidata_uri] if self.wikidata_uri
    graph << dbpedia_graph if self.dbpedia_uri
    graph << getty_note_graph if self.getty_uri
    graph << wikidata_graph if self.wikidata_uri
  end
  graph
end

#dbpedia_graphObject



63
64
65
66
67
68
69
70
71
72
73
74
75
# File 'lib/bib_card/crawler.rb', line 63

def dbpedia_graph
  graph = RDF::Graph.new
  begin
    graph << profile_graph
    graph << influence_graph
    graph << film_graph
  rescue RestClient::RequestTimeout
    BibCard.logger.warn "DBPedia failed to respond. SPARQL query request timed out after 5 seconds for #{@current_query}."
  rescue Exception => e
    BibCard.logger.warn "DBPedia failed to respond. Processing data for SPARQL request: #{@current_query}. Error: #{e.message}"
  end
  graph
end

#dbpedia_profileObject



189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
# File 'lib/bib_card/crawler.rb', line 189

def dbpedia_profile
  sparql = "
  #{self.dbpedia_sparql_prefixes}

  SELECT ?abstract ?foundedDate ?location ?thumbnail ?depiction
  WHERE {
    OPTIONAL { <#{self.dbpedia_uri}> dbo:abstract ?abstract . }
    OPTIONAL {<#{self.dbpedia_uri}> dbp:location ?location . }
    OPTIONAL { <#{self.dbpedia_uri}> dbp:foundedDate ?foundedDate . }
    OPTIONAL { <#{self.dbpedia_uri}> dbo:thumbnail ?thumbnail . }
    OPTIONAL { <#{self.dbpedia_uri}> foaf:depiction ?depiction . }
    FILTER(langMatches(lang(?abstract), \"en\"))
  }
  "
  get_data(sparql, :dbpedia).first
end

#dbpedia_uriObject



30
31
32
33
# File 'lib/bib_card/crawler.rb', line 30

def dbpedia_uri
  stmt = @repository.query({subject: @subject, predicate: SCHEMA_SAME_AS}).select {|s| s.object.to_s.match('http://dbpedia.org/resource')}.first
  stmt.nil? ? nil : stmt.object
end

#death_dateObject



20
21
22
23
# File 'lib/bib_card/crawler.rb', line 20

def death_date
  stmt = @repository.query({subject: @subject, predicate: SCHEMA_DEATHDATE}).first
  stmt.nil? ? nil : stmt.object
end

#film_appearancesObject



206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
# File 'lib/bib_card/crawler.rb', line 206

def film_appearances
  sparql = "
  #{self.dbpedia_sparql_prefixes}

  SELECT ?film ?filmName ?filmAbstract
  WHERE {
    ?film dbo:starring <#{self.dbpedia_uri}> .
    ?film rdfs:label ?filmName .
    ?film dbo:abstract ?filmAbstract .
    FILTER(langMatches(lang(?filmName), \"en\"))
    FILTER(langMatches(lang(?filmAbstract), \"en\"))
  }
  "
  get_data(sparql, :dbpedia)
end

#film_graphObject



104
105
106
107
108
109
110
111
112
113
114
# File 'lib/bib_card/crawler.rb', line 104

def film_graph
  @current_query = "film graph"
  graph = RDF::Graph.new
  self.film_appearances.each do |appearance|
    film = RDF::URI.new(appearance["film"]["value"])
    graph << [film, DBO_STARRING, self.dbpedia_uri]
    graph << [film, RDF::RDFS.label, appearance["filmName"]["value"]]
    graph << [film, DBO_ABSTRACT, appearance["filmAbstract"]["value"]]
  end
  graph
end

#getty_note_graphObject



222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
# File 'lib/bib_card/crawler.rb', line 222

def getty_note_graph
  @current_query = "getty note graph"
  graph = RDF::Graph.new
  begin
    getty_subject = self.getty_uri
    self.getty_scope_notes.each do |scope_note|
      # Add the scope note itself
      scope_note_uri = RDF::URI.new(scope_note["scopeNote"]["value"])
      graph << [getty_subject, SKOS_SCOPE_NOTE, scope_note_uri]
      graph << [scope_note_uri, RDF.value, scope_note["scopeNoteValue"]["value"]]

      # Add the sources/citations for the scope note
      source_uri = RDF::URI.new(scope_note["source"]["value"])
      graph << [scope_note_uri, DC_SOURCE, source_uri]
      if scope_note["sourceShortTitle"]
        graph << [source_uri, BIBO_SHORT_TITLE, scope_note["sourceShortTitle"]["value"]]
      else
        parent_uri = RDF::URI.new(scope_note["parent"]["value"])
        graph << [source_uri, DC_IS_PART_OF, parent_uri]
        graph << [source_uri, RDF.type, BIBO_DOCUMENT_PART]
        graph << [parent_uri, BIBO_SHORT_TITLE, scope_note["parentShortTitle"]["value"]]
      end
    end
  rescue RestClient::RequestTimeout
    BibCard.logger.warn "Getty failed to respond. SPARQL query request timed out after 5 seconds for #{@current_query}."
  rescue Exception => e
    BibCard.logger.warn "Getty failed to respond. Processing data for SPARQL request: #{@current_query}. Error: #{e.message}"
  end
  graph
end

#getty_scope_notesObject



253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
# File 'lib/bib_card/crawler.rb', line 253

def getty_scope_notes
  sparql = "
  PREFIX ulan: <http://vocab.getty.edu/ulan/>
  PREFIX skos: <http://www.w3.org/2004/02/skos/core#>
  PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
  PREFIX dct: <http://purl.org/dc/terms/>
  PREFIX bibo: <http://purl.org/ontology/bibo/>

  SELECT ?scopeNote ?scopeNoteValue ?source ?sourceShortTitle ?parent ?parentShortTitle
  WHERE {
    <#{self.getty_uri.to_s}> skos:scopeNote ?scopeNote .
    ?scopeNote rdf:value ?scopeNoteValue .
    ?scopeNote dct:source ?source .
    OPTIONAL { ?source bibo:shortTitle ?sourceShortTitle . }
    OPTIONAL {
      ?source dct:isPartOf ?parent .
      ?parent bibo:shortTitle ?parentShortTitle .
    }
  }
  "
  get_data(sparql, :getty)
end

#getty_uriObject



35
36
37
38
# File 'lib/bib_card/crawler.rb', line 35

def getty_uri
  stmt = @repository.query({subject: @subject, predicate: SCHEMA_SAME_AS}).select {|s| s.object.to_s.match('vocab.getty.edu')}.first
  stmt.nil? ? nil : RDF::URI.new( stmt.object.to_s.gsub('-agent', '') )
end

#influence_graphObject



77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
# File 'lib/bib_card/crawler.rb', line 77

def influence_graph
  graph = RDF::Graph.new
  [:influences, :influenced].each do |relationship|
    m = self.method(relationship)
    m.call.each do |influence|
      if relationship == :influences
        field = "influence"
        predicate = DBO_INFLUENCED_BY
      else
        field = "influenced"
        predicate = DBO_INFLUENCED
      end
      influence_entity = RDF::URI.new(influence[field]["value"])
      graph << [self.dbpedia_uri, predicate, influence_entity]
      graph << [influence_entity, RDFS_LABEL, influence["#{field}Label"]["value"]]
      if influence["#{field}GivenName"] and influence["#{field}Surname"]
        graph << [influence_entity, FOAF_GIVEN_NAME, influence["#{field}GivenName"]["value"]]
        graph << [influence_entity, FOAF_SURNAME, influence["#{field}Surname"]["value"]]
      end
      if influence["influenceSameAs"]
        graph << [influence_entity, RDF::OWL.sameAs, influence["#{field}SameAs"]["value"]]
      end
    end
  end
  graph
end

#influencedObject



160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
# File 'lib/bib_card/crawler.rb', line 160

def influenced
  @current_query = "influence upon graph"
  sparql = "
  #{self.dbpedia_sparql_prefixes}

  SELECT ?influenced ?influencedGivenName ?influencedSurname ?influencedSameAs ?influencedLabel
  WHERE {
    {
      <#{self.dbpedia_uri}> dbo:influenced ?influenced .
    }
    UNION
    {
      ?influenced dbo:influencedBy <#{self.dbpedia_uri}> .
    }
    ?influenced rdfs:label ?influencedLabel .
    OPTIONAL {
      ?influenced foaf:givenName ?influencedGivenName .
      ?influenced foaf:surname ?influencedSurname .
    }
    OPTIONAL {
      ?influenced owl:sameAs ?influencedSameAs .
      FILTER regex(STR(?influencedSameAs), \"viaf.org\").
    }
    FILTER (lang(?influencedLabel) = 'en')
  }
  "
  get_data(sparql, :dbpedia)
end

#influencesObject



131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
# File 'lib/bib_card/crawler.rb', line 131

def influences
  @current_query = "influences graph"
  sparql = "
  #{self.dbpedia_sparql_prefixes}

  SELECT DISTINCT ?influence ?influenceGivenName ?influenceSurname ?influenceSameAs ?influenceLabel
  WHERE {
    {
      ?influence dbo:influenced <#{self.dbpedia_uri}> .
    }
    UNION
    {
      <#{self.dbpedia_uri}> dbo:influencedBy ?influence .
    }
    ?influence rdfs:label ?influenceLabel .
    OPTIONAL {
      ?influence foaf:givenName ?influenceGivenName .
      ?influence foaf:surname ?influenceSurname .
    }
    OPTIONAL {
      ?influence owl:sameAs ?influenceSameAs .
      FILTER regex(STR(?influenceSameAs), \"viaf.org\").
    }
    FILTER (lang(?influenceLabel) = 'en')
  }
  "
  get_data(sparql, :dbpedia)
end

#loc_uriObject



25
26
27
28
# File 'lib/bib_card/crawler.rb', line 25

def loc_uri
  stmt = @repository.query({subject: @subject, predicate: SCHEMA_SAME_AS}).select {|s| s.object.to_s.match('http://id.loc.gov/authorities/names/')}.first
  stmt.nil? ? nil : stmt.object
end

#notable_worksObject



370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
# File 'lib/bib_card/crawler.rb', line 370

def notable_works
  sparql = "
  #{self.wikidata_sparql_prefixes}

  SELECT DISTINCT ?notableWork ?notableWorkLabel ?isbn ?oclcNumber
  WHERE
  {
  	<#{self.wikidata_uri.to_s}> wdt:P800 ?notableWork .
    	OPTIONAL {
        ?notableWork wdt:P212 ?isbn .
        ?notableWork wdt:P243 ?oclcNumber .
      }
  	SERVICE wikibase:label {
  		bd:serviceParam wikibase:language \"en\" .
  	}
  }
  "
  notable_works = get_data(sparql, :wikidata)
  notable_works.select {|work| work["notableWorkLabel"] != nil and !work["notableWorkLabel"]["value"].match(/^Q\d+$/)}
end

#profile_graphObject



116
117
118
119
120
121
122
123
124
125
126
127
128
129
# File 'lib/bib_card/crawler.rb', line 116

def profile_graph
  @current_query = "profile graph"
  graph = RDF::Graph.new
  dbpedia_subject = self.dbpedia_uri
  profile = self.dbpedia_profile
  if profile
    graph << [dbpedia_subject, DBO_ABSTRACT, profile["abstract"]["value"]] if profile["abstract"]
    graph << [dbpedia_subject, DBP_FOUNDED, profile["foundedDate"]["value"]] if profile["foundedDate"]
    graph << [dbpedia_subject, DBP_LOCATION, profile["location"]["value"]] if profile["location"]
    graph << [dbpedia_subject, DBO_THUMBNAIL, profile["thumbnail"]["value"]] if profile["thumbnail"]
    graph << [dbpedia_subject, FOAF_DEPICTION, profile["depiction"]["value"]] if profile["depiction"]
  end
  graph
end

#wikidata_graphObject



276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
# File 'lib/bib_card/crawler.rb', line 276

def wikidata_graph
  graph = RDF::Graph.new
  begin
    wikidata_subject = self.wikidata_uri
    self.alma_maters.each do |alma_mater|
      @current_query = "alma maters graph"
      am_inst_uri   = RDF::URI.new(alma_mater["inst"]["value"])
      am_edu_stmt   = RDF::URI.new(alma_mater["statement"]["value"])

      graph << [wikidata_subject, WDT_EDUCATED_AT, am_inst_uri]
      graph << [am_inst_uri, RDF::RDFS.label, alma_mater["instLabel"]["value"]]
      graph << [wikidata_subject, WDP_EDUCATED_AT, am_edu_stmt]
      graph << [am_edu_stmt, WDPS_STMT_EDU_AT, am_inst_uri]

      # Not all assertions have references/citations
      if alma_mater["reference"]
        am_stmt_ref   = RDF::URI.new(alma_mater["reference"]["value"])
        am_ref_source = RDF::URI.new(alma_mater["source"]["value"])

        graph << [am_edu_stmt, PROV_DERIVED_FROM, am_stmt_ref]
        graph << [am_stmt_ref, WDR_STATED_IN, am_ref_source]
        graph << [am_ref_source, RDF::RDFS.label, alma_mater["sourceLabel"]["value"]]
      end
    end

    bio = self.brief_bio
    if bio
      @current_query = "brief bio graph"
      graph << [wikidata_subject, SCHEMA_DESCRIPTION, bio["description"]["value"]] if bio["description"]
      if bio["workLocation"]
        work_loc_uri = RDF::URI.new(bio["workLocation"]["value"])
        graph << [wikidata_subject, WDT_WORK_LOCATION, work_loc_uri]
        graph << [work_loc_uri, RDF::RDFS.label, bio["workLocationLabel"]["value"]]
      end
    end

    self.notable_works.each do |work|
      @current_query = "notable works graph"
      work_uri = RDF::URI.new(work["notableWork"]["value"])
      graph << [wikidata_subject, WDT_NOTABLE_WORKS, work_uri]
      graph << [work_uri, RDF::RDFS.label, work["notableWorkLabel"]["value"]]
      graph << [work_uri, WDT_ISBN, work["isbn"]["value"]] if work["isbn"]
      graph << [work_uri, WDT_OCLC_NUMBER, work["oclcNumber"]["value"]] if work["oclcNumber"]
    end
  rescue RestClient::RequestTimeout
    BibCard.logger.warn "WikiData failed to respond. SPARQL query request timed out after 5 seconds for #{@current_query}."
  rescue Exception => e
    BibCard.logger.warn "WikiData failed to respond. Processing data for SPARQL request: #{@current_query}. Error: #{e.message}"
  end
  graph
end

#wikidata_uriObject



40
41
42
43
# File 'lib/bib_card/crawler.rb', line 40

def wikidata_uri
  stmt = @repository.query({subject: @subject, predicate: SCHEMA_SAME_AS}).select {|s| s.object.to_s.match('http://www.wikidata.org/entity')}.first
  stmt.nil? ? nil : stmt.object
end