Python Person.add_identifier方法代码示例

# 需要导入模块: from pupa.scrape import Person [as 别名]
# 或者: from pupa.scrape.Person import add_identifier [as 别名]
def test_full_person():
    person = ScrapePerson('Tom Sawyer')
    person.add_identifier('1')
    person.add_name('Tommy', start_date='1880')
    person.add_contact_detail(type='phone', value='555-555-1234', note='this is fake')
    person.add_link('http://example.com/link')
    person.add_source('http://example.com/source')

    # import person
    pd = person.as_dict()
    PersonImporter('jurisdiction-id').import_data([pd])

    # get person from db and assert it imported correctly
    p = Person.objects.get()
    assert 'ocd-person' in p.id
    assert p.name == person.name

    assert p.identifiers.all()[0].identifier == '1'
    assert p.identifiers.all()[0].scheme == ''

    assert p.other_names.all()[0].name == 'Tommy'
    assert p.other_names.all()[0].start_date == '1880'

    assert p.contact_details.all()[0].type == 'phone'
    assert p.contact_details.all()[0].value == '555-555-1234'
    assert p.contact_details.all()[0].note == 'this is fake'

    assert p.links.all()[0].url == 'http://example.com/link'
    assert p.sources.all()[0].url == 'http://example.com/source'

# 需要导入模块: from pupa.scrape import Person [as 别名]
# 或者: from pupa.scrape.Person import add_identifier [as 别名]
def test_bill_sponsor_by_identifier():
    create_jurisdiction()
    org = create_org()

    bill = ScrapeBill('HB 1', '1900', 'Axe & Tack Tax Act',
                      classification='tax bill', chamber='lower')
    bill.add_sponsorship_by_identifier(name="SNODGRASS",
                                       classification='sponsor',
                                       entity_type='person',
                                       primary=True,
                                       identifier="TOTALLY_REAL_ID",
                                       scheme="TOTALLY_REAL_SCHEME")

    oi = OrganizationImporter('jid')
    pi = PersonImporter('jid')

    zs = ScrapePerson(name='Zadock Snodgrass')
    zs.add_identifier(identifier='TOTALLY_REAL_ID',
                      scheme='TOTALLY_REAL_SCHEME')
    pi.import_data([zs.as_dict()])
    za_db = Person.objects.get()
    Membership.objects.create(person_id=za_db.id,
                              organization_id=org.id)

    BillImporter('jid', oi, pi).import_data([bill.as_dict()])

    obj = Bill.objects.get()
    (entry,) = obj.sponsorships.all()
    assert entry.person.name == "Zadock Snodgrass"

# 需要导入模块: from pupa.scrape import Person [as 别名]
# 或者: from pupa.scrape.Person import add_identifier [as 别名]
def test_bill_sponsor_limit_lookup():
    create_jurisdiction()
    org = create_org()

    bill = ScrapeBill('HB 1', '1900', 'Axe & Tack Tax Act',
                      classification='tax bill', chamber='lower')
    bill.add_sponsorship_by_identifier(name="SNODGRASS",
                                       classification='sponsor',
                                       entity_type='person',
                                       primary=True,
                                       identifier="TOTALLY_REAL_ID",
                                       scheme="TOTALLY_REAL_SCHEME")

    oi = OrganizationImporter('jid')
    pi = PersonImporter('jid')

    zs = ScrapePerson(name='Zadock Snodgrass', birth_date="1800-01-01")
    zs.add_identifier(identifier='TOTALLY_REAL_ID',
                      scheme='TOTALLY_REAL_SCHEME')
    pi.import_data([zs.as_dict()])

    za_db = Person.objects.get()
    Membership.objects.create(person_id=za_db.id,
                              organization_id=org.id)

    zs2 = ScrapePerson(name='Zadock Snodgrass', birth_date="1900-01-01")
    zs2.add_identifier(identifier='TOTALLY_REAL_ID',
                       scheme='TOTALLY_REAL_SCHEME')

    # This is contrived and perhaps broken, but we're going to check this.
    # We *really* don't want to *ever* cross jurisdiction bounds.
    PersonImporter('another-jurisdiction').import_data([zs.as_dict()])

    BillImporter('jid', oi, pi).import_data([bill.as_dict()])

    obj = Bill.objects.get()
    (entry,) = obj.sponsorships.all()
    assert entry.person.name == "Zadock Snodgrass"
    assert entry.person.birth_date == "1800-01-01"

# 需要导入模块: from pupa.scrape import Person [as 别名]
# 或者: from pupa.scrape.Person import add_identifier [as 别名]
    def scrape_legislator(self, legislator_id):
        old = self.api('legislators/' + legislator_id + '?')
        # just not needed
        id = old.pop('id')

        old.pop('created_at')
        old.pop('updated_at')
        old.pop('country', None)
        old.pop('level', None)
        old.pop('state')
        old.pop('leg_id')
        old.pop('active')
        # junk keys
        old.pop('suffix', None)
        old.pop('notice', None)
        old.pop('csrfmiddlewaretoken', None)
        old.pop('office_address', None)
        old.pop('office_phone', None)

        # translated
        district = old.pop('district', None)
        chamber = old.pop('chamber', None)
        image = old.pop('photo_url', '')
        name = old.pop('full_name')
        party = old.pop('party', None)

        if party in ('Nonpartisan', 'unknown', 'Unknown', 'Unaffiliated', "Non Affiliated", " "):
            party = None
        elif party == 'Democrat':
            party = 'Democratic'

        if self.state in('ne', 'dc'):
            chamber = 'legislature'

        if chamber == 'upper' and self.state == 'pr':
            pr_district = {
                '1': 'I',
                '2': 'II',
                '3': 'III',
                '4': 'IV',
                '5': 'V',
                '6': 'VI',
                '7': 'VII',
                '8': 'VIII',
            }
            if district in pr_district:
                district = pr_district[district]

        if '2008-2011' in old:
            old['old_roles']['2008-2011'] = old.pop('2008-2011')

        old_roles = old.pop('old_roles', {})

        if old['roles'] and 'Lt. Governor' in [x['type'] for x in old['roles']]:
            new = Person(name=name, district=district, party=party, image=image)
            self.jurisdiction._executive.add_post(
                'Lt. Governor',
                'lt-gov'
            )
            membership = Membership(
                person_id=new._id,
                role="Lt. Governor",
                organization_id=self.jurisdiction._executive._id
            )
            new._related.append(membership)
        else:
            new = Person(name=name, party=party, image=image)

        if id in birthdays:
            new.birth_date = birthdays[id]

        # various ids
        id_types = {'votesmart_id': 'votesmart',
                    'transparencydata_id': 'influence-explorer',
                    'nimsp_id': 'nimsp',
                    'nimsp_candidate_id': 'nimsp-candidate',
                   }
        for idname, scheme in id_types.items():
            val = old.pop(idname, None)
            if val:
                new.add_identifier(val, scheme=scheme)
        for id in old.pop('all_ids'):
            new.add_identifier(id, scheme='openstates')
            self._people[id] = new

        # contact details
        email = old.pop('email', None)
        if email:
            new.add_contact_detail(type='email', value=email, note='')
        office_keys = {'fax': 'fax',
                       'phone': 'voice',
                       'email': 'email',
                       'address': 'address'}
        for office in old.pop('offices'):
            for key, type in office_keys.items():
                if office.get(key):
                    if 'Office Hours' in office[key] and self.state == 'pa':
                        for x in office[key].split('Office Hours: '):
                            if x:
                                new.add_contact_detail(type=type, value=x, note=office['name'])
#.........这里部分代码省略.........

# 需要导入模块: from pupa.scrape import Person [as 别名]
# 或者: from pupa.scrape.Person import add_identifier [as 别名]
    def scrape_current_legislators(self, repos):
        for repo in repos:
            CURRENT_LEGISLATORS = self.get_url(repo)

            people = self.yamlize(CURRENT_LEGISLATORS)
            parties = set()
            posts = {}
            person_cache = defaultdict(lambda: defaultdict(lambda: None))

            for person in people:
                name = person['name'].get('official_full')
                if name is None:
                    name = "{name[first]} {name[last]}".format(**person)

                if 'birthday' in person['bio']:
                    birth_date = person['bio']['birthday']

                who = person_cache[name][birth_date]
                has_term = False

                if who is None:
                    who = Person(name=name, birth_date=birth_date)
                    who.add_source(url=CURRENT_LEGISLATORS, note="unitedstates project on GitHub")

                for term in person.get('terms', []):
                    has_term = True
                    start_date = term['start']
                    end_date = term['end']
                    state = term['state']
                    type_ = term['type']
                    district = term.get('district', None)
                    party = term.get('party', None)

                    chamber = {'rep': self.house,
                               'sen': self.senate}[type_]

                    role = {'rep': 'Representative',
                            'sen': 'Senator'}[type_]

                    if type_ == "rep" and district is not None:
                        label = "%s for District %s in %s" % (role, district, state)

                        division_id = ("ocd-division/country:us/state:{state}".format(state=state.lower()))

                        if district != 0:
                            division_id += "/cd:{district}".format(district=district)

                    if type_ == "sen":
                        label = "Senator for %s" % state

                        division_id = ("ocd-division/country:us/state:{state}".format(state=state.lower()))

                    post = posts.get(division_id)
                    if post is None:
                        post = Post(organization_id=chamber._id,
                            division_id=division_id,
                            label=label, role=role)
                        posts[division_id] = post
                        yield post

                    membership = Membership(
                        post_id=post._id,
                        role=role,
                        label=label,
                        start_date=start_date,
                        end_date=end_date,
                        person_id=who._id,
                        organization_id=chamber._id)
                    yield membership

                    if party == "Democrat":
                        party = "Democratic"

                    if party:
                        membership = Membership(
                            role='member',
                            start_date=start_date,
                            end_date=end_date,
                            person_id=who._id,
                            organization_id=make_pseudo_id(
                                classification="party",
                                name=party))
                        yield membership

                for key, value in person.get('id', {}).items():
                    if isinstance(value, list):
                        for v in value:
                            who.add_identifier(str(v), scheme=key)
                    else:
                        who.add_identifier(str(value), scheme=key)
                        if key == 'bioguide':
                            who.image = self.get_image_url(str(value))

                if has_term:
                    yield who

# 需要导入模块: from pupa.scrape import Person [as 别名]
# 或者: from pupa.scrape.Person import add_identifier [as 别名]
    def transform_parse(self, parsed_form, response):

        _source = {
            "url": response.url,
            "note": "LDA Form LD-1"
        }

        # basic disclosure fields
        _disclosure = Disclosure(
            effective_date=datetime.strptime(
                parsed_form['datetimes']['effective_date'],
                '%Y-%m-%d %H:%M:%S').replace(tzinfo=UTC),
            timezone='America/New_York',
            submitted_date=datetime.strptime(
                parsed_form['datetimes']['signature_date'],
                '%Y-%m-%d %H:%M:%S').replace(tzinfo=UTC),
            classification="lobbying"
        )

        _disclosure.add_authority(name=self.authority.name,
                                  type=self.authority._type,
                                  id=self.authority._id)

        _disclosure.add_identifier(
            identifier=parsed_form['_meta']['document_id'],
            scheme="urn:sopr:filing"
        )

        # disclosure extras
        _disclosure.extras = {}
        _disclosure.extras['registrant'] = {
            'self_employed_individual': parsed_form['registrant']['self_employed_individual'],
            'general_description': parsed_form['registrant']['registrant_general_description'],
            'signature': {
                "signature_date": parsed_form['datetimes']['signature_date'],
                "signature": parsed_form['signature']
            }
        }

        _disclosure.extras['client'] = {
            'same_as_registrant':
                parsed_form['client']['client_self'],
            'general_description':
                parsed_form['client']['client_general_description']
        }

        _disclosure.extras['registration_type'] = {
            'is_amendment':
                parsed_form['registration_type']['is_amendment'],
            'new_registrant':
                parsed_form['registration_type']['new_registrant'],
            'new_client_for_existing_registrant':
                parsed_form['registration_type'][
                    'new_client_for_existing_registrant'],
        }

        # # Registrant
        # build registrant
        _registrant_self_employment = None

        if parsed_form['registrant']['self_employed_individual']:
            n = ' '.join([p for p in [
                parsed_form['registrant']['registrant_individual_prefix'],
                parsed_form['registrant']['registrant_individual_firstname'],
                parsed_form['registrant']['registrant_individual_lastname']
            ] if len(p) > 0]).strip()

            _registrant = Person(
                name=n,
                source_identified=True
            )

            _registrant_self_employment = Organization(
                name='SELF-EMPLOYMENT of {n}'.format(n=n),
                classification='company',
                source_identified=True
            )

            _registrant.add_membership(
                organization=_registrant_self_employment,
                role='self_employed',
                label='self-employment of {n}'.format(n=n),
                start_date=_disclosure.effective_date.strftime('%Y-%m-%d')
            )
        else:
            _registrant = Organization(
                name=parsed_form['registrant']['registrant_org_name'],
                classification='company',
                source_identified=True
            )

        if len(parsed_form['registrant']['registrant_house_id']) > 0:
            _registrant.add_identifier(
                identifier=parsed_form['registrant']['registrant_house_id'],
                scheme='urn:house_clerk:registrant'
            )

        if len(parsed_form['registrant']['registrant_senate_id']) > 0:
            _registrant.add_identifier(
                identifier=parsed_form['registrant']['registrant_senate_id'],
#.........这里部分代码省略.........