bycoffe · July 10, 2017 13:31
diff --git a/birth_dates.csv b/birth_dates.csv
diff --git a/get_birth_dates.py b/get_birth_dates.py
 #!/usr/bin/python

 import csv
 import datetime
 import re
 from urllib.parse import unquote
 from utils import load_data, save_data
 from SPARQLWrapper import SPARQLWrapper, JSON

 def run():
    sparql_endpoint = 'https://query.wikidata.org/bigdata/namespace/wdq/sparql'
    s = SPARQLWrapper(sparql_endpoint)

    output = csv.writer(open("birth_dates.csv", "w"))
    output.writerow(['bioguide', 'name', 'birth'])

    # sparql query to fetch the wikidata url, wikipedia url, freebase id, knowledge graph id
    query = """
      PREFIX wd: <http://www.wikidata.org/entity/>
      PREFIX wdt: <http://www.wikidata.org/prop/direct/>
      PREFIX schema: <http://schema.org/>

      SELECT ?bio ?birth ?death ?subject
      WHERE {
        ?subject wdt:P1157 ?bio .
        ?subject wdt:P569 ?birth .
        ?subject wdt:P570 ?death .
        OPTIONAL {
            ?article schema:about ?subject .
            ?article schema:inLanguage "en" .
            ?article schema:isPartOf <https://en.wikipedia.org/> .
        }
      }

    """

    # run the query and stick everything in a big hash keyed by bioguide id
    s.setQuery(query)
    s.setReturnFormat(JSON)
    results = s.query().convert()
    ret = {}

    y = load_data("legislators-historical.yaml")

    births_by_bioguide = {}
    for row in results['results']['bindings']:
        births_by_bioguide[row['bio']['value']] = row['birth']['value']

    for m in y:
        try:
            ddate = births_by_bioguide[m['id']['bioguide']]
        except KeyError:
            continue

        try:
            ddate = datetime.datetime.strptime(ddate, "%Y-%m-%dT%H:%M:%SZ").date()
        except ValueError:
            continue

        last_term_end = datetime.datetime.strptime(m['terms'][-1]['end'], '%Y-%m-%d').date()

        if last_term_end > ddate:
            output.writerow([m['id']['bioguide'], m['id']['wikipedia'], str(ddate)])


 if __name__ == '__main__':
  run()
	#!/usr/bin/python

	import csv
	import datetime
	import re
	from urllib.parse import unquote
	from utils import load_data, save_data
	from SPARQLWrapper import SPARQLWrapper, JSON

	def run():
	sparql_endpoint = 'https://query.wikidata.org/bigdata/namespace/wdq/sparql'
	s = SPARQLWrapper(sparql_endpoint)

	output = csv.writer(open("birth_dates.csv", "w"))
	output.writerow(['bioguide', 'name', 'birth'])

	# sparql query to fetch the wikidata url, wikipedia url, freebase id, knowledge graph id
	query = """
	PREFIX wd: <http://www.wikidata.org/entity/>
	PREFIX wdt: <http://www.wikidata.org/prop/direct/>
	PREFIX schema: <http://schema.org/>

	SELECT ?bio ?birth ?death ?subject
	WHERE {
	?subject wdt:P1157 ?bio .
	?subject wdt:P569 ?birth .
	?subject wdt:P570 ?death .
	OPTIONAL {
	?article schema:about ?subject .
	?article schema:inLanguage "en" .
	?article schema:isPartOf <https://en.wikipedia.org/> .
	}
	}

	"""

	# run the query and stick everything in a big hash keyed by bioguide id
	s.setQuery(query)
	s.setReturnFormat(JSON)
	results = s.query().convert()
	ret = {}

	y = load_data("legislators-historical.yaml")

	births_by_bioguide = {}
	for row in results['results']['bindings']:
	births_by_bioguide[row['bio']['value']] = row['birth']['value']

	for m in y:
	try:
	ddate = births_by_bioguide[m['id']['bioguide']]
	except KeyError:
	continue

	try:
	ddate = datetime.datetime.strptime(ddate, "%Y-%m-%dT%H:%M:%SZ").date()
	except ValueError:
	continue

	last_term_end = datetime.datetime.strptime(m['terms'][-1]['end'], '%Y-%m-%d').date()

	if last_term_end > ddate:
	output.writerow([m['id']['bioguide'], m['id']['wikipedia'], str(ddate)])


	if __name__ == '__main__':
	run()