def scrape(self):
sessions = reversed(self.jurisdiction.legislative_sessions)
committee_term_instances = committees_from_sessions(self, sessions)
committees_by_code = build_lookup_dict(self, data_list=committee_term_instances, index_key='code')
for code, instances in committees_by_code.items():
# TODO: Figure out how to edit city council org.
if code == 'CC':
continue
extras = {'tmmis_decision_body_ids': []}
for i, inst in enumerate(instances):
# TODO: Ensure this survives addition of new term (2017)
# so specific year always creates
canonical_i = 0
if i == canonical_i:
o = Organization(name=inst['name'], classification='committee')
extras.update({'description': inst['info']})
o.add_identifier(inst['code'], scheme=TWO_LETTER_ORG_CODE_SCHEME)
extras['tmmis_decision_body_ids'].append({inst['term']: inst['decision_body_id']})
o.extras = extras
o.add_source(inst['source_url'])
if instances[canonical_i]['name'] != inst['name']:
# TODO: Add start_date and end_date
o.add_name(inst['name'])
yield o
def scrape(self):
sessions = reversed(self.jurisdiction.legislative_sessions)
committee_term_instances = committees_from_sessions(self, sessions)
committees_by_code = build_lookup_dict(
self, data_list=committee_term_instances, index_key='code')
for code, instances in committees_by_code.items():
# TODO: Figure out how to edit city council org.
if code == 'CC':
continue
extras = {'tmmis_decision_body_ids': []}
for i, inst in enumerate(instances):
# TODO: Ensure this survives addition of new term (2017)
# so specific year always creates
canonical_i = 0
if i == canonical_i:
o = Organization(name=inst['name'],
classification='committee')
extras.update({'description': inst['info']})
o.add_identifier(inst['code'],
scheme=TWO_LETTER_ORG_CODE_SCHEME)
extras['tmmis_decision_body_ids'].append(
{inst['term']: inst['decision_body_id']})
o.extras = extras
o.add_source(inst['source_url'])
if instances[canonical_i]['name'] != inst['name']:
# TODO: Add start_date and end_date
o.add_name(inst['name'])
yield o
def test_extras_organization():
org = ScrapeOrganization('United Nations', classification='international')
org.extras = {"hello": "world", "foo": {"bar": "baz"}}
od = org.as_dict()
OrganizationImporter('jurisdiction-id').import_data([od])
o = Organization.objects.get()
assert o.extras['foo']['bar'] == 'baz'
def test_extras_organization():
org = ScrapeOrganization('United Nations', classification='international')
org.extras = {"hello": "world",
"foo": {"bar": "baz"}}
od = org.as_dict()
OrganizationImporter('jurisdiction-id').import_data([od])
o = Organization.objects.get()
assert o.extras['foo']['bar'] == 'baz'
def scrape(self):
sessions = reversed(self.jurisdiction.legislative_sessions)
committee_term_instances = committees_from_sessions(self, sessions)
committees_by_code = build_lookup_dict(
self, data_list=committee_term_instances, index_key='code')
for code, instances in committees_by_code.items():
# TODO: Figure out how to edit city council org.
if code == 'CC':
continue
# When there are no meetings scheduled and was no way to deduce committee code.
if not code:
continue
extras = {'tmmis_decision_body_ids': []}
for i, inst in enumerate(instances):
# TODO: Ensure this survives addition of new term (2017)
# so specific year always creates
canonical_i = 0
if i == canonical_i:
o = Organization(name=inst['name'],
classification='committee')
extras.update({'description': inst['info']})
o.add_identifier(inst['code'],
scheme=TWO_LETTER_ORG_CODE_SCHEME)
# TODO: Scrape non-councillor members
meeting_id = self.referenceMeetingId(
inst['code'], inst['term'])
if meeting_id:
seen_posts = []
membership_url = MEMBERSHIP_URL_TEMPLATE.format(
meeting_id)
for councillor in self.councillorMembers(
membership_url):
o.add_member(councillor['name'],
councillor['role'])
if councillor['role'] not in seen_posts:
# TODO: More specific divisions for some committee?
o.add_post(
role=councillor['role'],
label=councillor['role'],
division_id=self.jurisdiction.division_id)
seen_posts.append(councillor['role'])
extras['tmmis_decision_body_ids'].append(
{inst['term']: inst['decision_body_id']})
o.extras = extras
o.add_source(inst['source_url'])
if instances[canonical_i]['name'] != inst['name']:
# TODO: Add start_date and end_date
o.add_name(inst['name'])
yield o
def scrape(self):
sessions = reversed(self.jurisdiction.legislative_sessions)
committee_term_instances = committees_from_sessions(self, sessions)
committees_by_code = build_lookup_dict(self, data_list=committee_term_instances, index_key='code')
for code, instances in committees_by_code.items():
# TODO: Figure out how to edit city council org.
if code == 'CC':
continue
# When there are no meetings scheduled and was no way to deduce committee code.
if not code:
continue
extras = {'tmmis_decision_body_ids': []}
for i, inst in enumerate(instances):
# TODO: Ensure this survives addition of new term (2017)
# so specific year always creates
canonical_i = 0
if i == canonical_i:
o = Organization(name=inst['name'], classification='committee')
extras.update({'description': inst['info']})
o.add_identifier(inst['code'], scheme=TWO_LETTER_ORG_CODE_SCHEME)
# TODO: Scrape non-councillor members
meeting_id = self.referenceMeetingId(inst['code'], inst['term'])
if meeting_id:
seen_posts = []
membership_url = MEMBERSHIP_URL_TEMPLATE.format(meeting_id)
for councillor in self.councillorMembers(membership_url):
o.add_member(councillor['name'], councillor['role'])
if councillor['role'] not in seen_posts:
o.add_post(
role=councillor['role'],
label=councillor['role'],
# TODO: More specific divisions for some committee?
division_id=self.jurisdiction.division_id,
)
seen_posts.append(councillor['role'])
extras['tmmis_decision_body_ids'].append({inst['term']: inst['decision_body_id']})
o.extras = extras
o.add_source(inst['source_url'])
if instances[canonical_i]['name'] != inst['name']:
# TODO: Add start_date and end_date
o.add_name(inst['name'])
yield o
def scrape_committee(self, comm_num):
url = self.committee_url(comm_num)
page = self.lxmlize(url)
# get title
comm_name = page.xpath("//h1/text()")[0]
# create object
comm = Organization(name=comm_name,
classification="committee",
chamber="legislature")
comm.add_source(url=url)
# add posts
comm.add_post(label="chair", role="chair")
# FIXME do we need a separate post for each member?
# FIXME is member an appropriate name?
comm.add_post(label="member", role="member")
# helper for finding other nodes
landmark_node = page.xpath("//h2[text()='Committee Members']")[0]
# add memberships
member_names = landmark_node.xpath(
"following-sibling::div/ul/li/a/text()")
fl_names = [HumanName.name_firstandlast(name) for name in member_names]
print("My attempt to scrub people's names:",
list(zip(member_names, fl_names)))
chair_name, *other_names = fl_names
if chair_name not in {'Lewis Reed'}:
comm.add_member(chair_name, role="chair")
for name in other_names:
if name not in {'Lewis Reed'}:
comm.add_member(name, role="member")
# add description
about_node = page.xpath("//h2[text()='About']")[0]
(description, ) = about_node.xpath(
"parent::div//div[@class='content-block']/p[2]/text()")
description = description.strip()
comm.extras = {"description": description}
yield comm
def scrape_committee(self, comm_num):
url = self.committee_url(comm_num)
page = self.lxmlize(url)
# get title
comm_name = page.xpath("//h1/text()")[0]
# create object
comm = Organization(name=comm_name,
classification="committee",
chamber="legislature")
comm.add_source(url=url)
# add posts
comm.add_post(label="chair", role="chair")
# FIXME do we need a separate post for each member?
# FIXME is member an appropriate name?
comm.add_post(label="member", role="member")
# helper for finding other nodes
landmark_node = page.xpath("//h2[text()='Committee Members']")[0]
# add memberships
member_names = landmark_node.xpath("following-sibling::div/ul/li/a/text()")
fl_names = [HumanName.name_firstandlast(name) for name in member_names]
print("My attempt to scrub people's names:",
list(zip(member_names, fl_names)))
chair_name, *other_names = fl_names
if chair_name not in {'Lewis Reed'} :
comm.add_member(chair_name, role="chair")
for name in other_names:
if name not in {'Lewis Reed'} :
comm.add_member(name, role="member")
# add description
about_node = page.xpath("//h2[text()='About']")[0]
(description, ) = about_node.xpath("parent::div//div[@class='content-block']/p[2]/text()")
description = description.strip()
comm.extras = {"description": description}
yield comm
def scrape_session(self, session, chambers):
sid = SESSION_SITE_IDS[session]
committees = backoff(self.cservice.GetCommitteesBySession, sid)
# if committees.strip() == "":
# return # If we get here, it's a problem.
# Commenting this out for future debugging. - PRT
if str(committees).strip() == "":
raise ValueError("Error: No committee data for sid: %s" % (sid))
committees = committees['CommitteeListing']
for committee in committees:
cid = committee['Id']
committee = backoff(self.cservice.GetCommittee, cid)
subctty_cache = {}
comname, typ, guid, code, description = [committee[x] for x in [
'Name', 'Type', 'Id', 'Code', 'Description'
]]
comchamber = {
"House": "lower",
"Senate": "upper",
"Joint": "joint"
}[typ]
ctty_key = '{}-{}'.format(typ, code)
if ctty_key not in self.ctty_cache:
ctty = Organization(chamber=comchamber, name=comname, classification='committee')
ctty.extras = {
'code': code,
'guid': guid,
'description': description,
}
self.ctty_cache[ctty_key] = ctty
members = committee['Members']['CommitteeMember']
for member in members:
name = "{First} {Last}".format(**dict(member['Member']['Name']))
role = member['Role']
membership = ctty.add_member(name, role)
membership.extras = {'guid': member['Member']['Id']}
subcoms = member['SubCommittees'] or []
for subcom in subcoms:
subcom = subcom[1][0]
subguid = subcom['Id']
subcommittee = subcom['Name']
if subcommittee in subctty_cache:
# Add member to existing subcommittee.
subctty = subctty_cache[subcommittee]
else:
# Create subcommittee.
subctty = Organization(
name=subcommittee, classification='committee',
parent_id={'classification': comchamber, 'name': comname})
subctty.extras = {
'guid': subguid,
}
subctty.add_source(self.csource)
subctty.add_source(CTTIE_URL.format(**{
"sid": sid,
"cttie": guid,
}))
subctty_cache[subcommittee] = subctty
membership = subctty.add_member(name, role)
membership.extras = {'guid': member['Member']['Id']}
for subctty in subctty_cache.values():
yield subctty
ctty.add_source(self.csource)
ctty.add_source(CTTIE_URL.format(**{
"sid": sid,
"cttie": guid,
}))
yield ctty
def _scrape_lower_chamber(self, session):
self.info('Scraping lower chamber for committees.')
chamber = 'lower'
url = '{base}ActiveCommittees.aspx'.format(base=self._reps_url_base)
page_string = self.get(url).text
page = lxml.html.fromstring(page_string)
table = page.xpath('//div[@class="lightened"]/table[1]')[0]
# Last tr has the date
trs = table.xpath('tr')[:-1]
for tr in trs:
committee_parts = [part.strip()
for part in tr.text_content().split(',')]
committee_name = committee_parts[0].title().strip()
if len(committee_parts) > 0:
status = committee_parts[1].strip()
committee_url = tr.xpath('td/a')[0].attrib.get('href')
committee_url = '{base}{url}'.format(base=self._reps_url_base,
url=committee_url)
actual_chamber = chamber
if 'joint' in committee_name.lower():
actual_chamber = 'joint'
committee_name = committee_name.replace('Committee On ', '')
committee_name = committee_name.replace('Special', '')
committee_name = committee_name.replace('Select', '')
committee_name = committee_name.replace('Special', '')
committee_name = committee_name.replace('Joint', '')
committee_name = committee_name.replace(' Committee', '')
committee_name = committee_name.strip()
committee = Organization(
committee_name,
chamber=actual_chamber,
classification='committee',
)
committee.extras = {'status': status}
committee_page_string = self.get(committee_url).text
committee_page = lxml.html.fromstring(committee_page_string)
# First tr has the title (sigh)
mem_trs = committee_page.xpath('id("memGroup")/tr')[1:]
for mem_tr in mem_trs:
mem_code = None
mem_links = mem_tr.xpath('td/a[1]')
if len(mem_links):
mem_code = mem_links[0].attrib.get('href')
# Output is "Rubble, Barney, Neighbor"
mem_parts = mem_tr.text_content().strip().split(',')
if self._no_members_text in mem_parts:
continue
mem_name = (mem_parts[1].strip() + ' ' +
mem_parts[0].strip())
# Sometimes Senator abbreviation is in the name
mem_name = mem_name.replace('Sen. ', '')
mem_role = 'member'
if len(mem_parts) > 2:
# Handle the case where there is a comma in the
# role name
mem_role = ', '.join(
[p.strip() for p in mem_parts[2:]]).lower()
membership = committee.add_member(mem_name, role=mem_role)
membership.extras = {'code': mem_code}
committee.add_source(url)
committee.add_source(committee_url)
yield committee
def scrape_session(self, session, chambers):
sid = SESSION_SITE_IDS[session]
committees = backoff(self.cservice.GetCommitteesBySession, sid)
# if committees.strip() == "":
# return # If we get here, it's a problem.
# Commenting this out for future debugging. - PRT
if str(committees).strip() == "":
raise ValueError("Error: No committee data for sid: %s" % (sid))
committees = committees['CommitteeListing']
for committee in committees:
cid = committee['Id']
committee = backoff(self.cservice.GetCommittee, cid)
subctty_cache = {}
comname, typ, guid, code, description = [
committee[x]
for x in ['Name', 'Type', 'Id', 'Code', 'Description']
]
comchamber = {
"House": "lower",
"Senate": "upper",
"Joint": "joint"
}[typ]
ctty_key = '{}-{}'.format(typ, code)
if ctty_key not in self.ctty_cache:
ctty = Organization(chamber=comchamber,
name=comname,
classification='committee')
ctty.extras = {
'code': code,
'guid': guid,
'description': description,
}
self.ctty_cache[ctty_key] = ctty
members = committee['Members']['CommitteeMember']
for member in members:
name = "{First} {Last}".format(
**dict(member['Member']['Name']))
role = member['Role']
membership = ctty.add_member(name, role)
membership.extras = {'guid': member['Member']['Id']}
subcoms = member['SubCommittees'] or []
for subcom in subcoms:
subcom = subcom[1][0]
subguid = subcom['Id']
subcommittee = subcom['Name']
if subcommittee in subctty_cache:
# Add member to existing subcommittee.
subctty = subctty_cache[subcommittee]
else:
# Create subcommittee.
subctty = Organization(name=subcommittee,
classification='committee',
parent_id={
'classification':
comchamber,
'name': comname
})
subctty.extras = {
'guid': subguid,
}
subctty.add_source(self.csource)
subctty.add_source(
CTTIE_URL.format(**{
"sid": sid,
"cttie": guid,
}))
subctty_cache[subcommittee] = subctty
membership = subctty.add_member(name, role)
membership.extras = {'guid': member['Member']['Id']}
for subctty in subctty_cache.values():
yield subctty
ctty.add_source(self.csource)
ctty.add_source(CTTIE_URL.format(**{
"sid": sid,
"cttie": guid,
}))
yield ctty
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'],
scheme='urn:sopr:registrant'
)
registrant_contact_details = [
{
"type": "address",
"note": "contact address",
"value": '; '.join([
p for p in [
parsed_form['registrant']['registrant_address_one'],
parsed_form['registrant']['registrant_address_two'],
parsed_form['registrant']['registrant_city'],
parsed_form['registrant']['registrant_state'],
parsed_form['registrant']['registrant_zip'],
parsed_form['registrant']['registrant_country']]
if len(p) > 0]).strip(),
},
{
"type": "voice",
"note": "contact phone",
"value": parsed_form['registrant']['registrant_contact_phone'],
},
{
"type": "email",
"note": "contact email",
"value": parsed_form['registrant']['registrant_contact_email'],
},
]
registrant_contact_ppb = {
"type": "address",
"note": "principal place of business",
"value": '; '.join([
p for p in [
parsed_form['registrant']['registrant_ppb_city'],
parsed_form['registrant']['registrant_ppb_state'],
parsed_form['registrant']['registrant_ppb_zip'],
parsed_form['registrant']['registrant_ppb_country']]
if len(p) > 0]).strip(),
}
if registrant_contact_ppb["value"]:
registrant_contact_details.append(registrant_contact_ppb)
for cd in registrant_contact_details:
_registrant.add_contact_detail(**cd)
_registrant.extras = {
"contact_details_structured": [
{
"type": "address",
"note": "contact address",
"parts": [
{
"note": "address_one",
"value": parsed_form['registrant'][
'registrant_address_one'],
},
{
"note": "address_two",
"value": parsed_form['registrant'][
'registrant_address_two'],
},
{
"note": "city",
"value": parsed_form['registrant'][
'registrant_city'],
},
{
"note": "state",
"value": parsed_form['registrant'][
'registrant_state'],
},
{
"note": "zip",
"value": parsed_form['registrant'][
'registrant_zip'],
},
{
"note": "country",
"value": parsed_form['registrant'][
'registrant_country'],
}
],
},
{
"type": "address",
"note": "principal place of business",
"parts": [
{
"note": "city",
"value": parsed_form['registrant'][
'registrant_ppb_city'],
},
{
"note": "state",
"value": parsed_form['registrant'][
'registrant_ppb_state'],
},
{
"note": "zip",
"value": parsed_form['registrant'][
'registrant_ppb_zip'],
},
{
"note": "country",
"value": parsed_form['registrant'][
'registrant_ppb_country'],
}
],
},
]
}
# # People
# build contact
_main_contact = Person(
name=parsed_form['registrant']['registrant_contact_name'],
source_identified=True
)
main_contact_contact_details = [
{
"type": "voice",
"note": "contact phone",
"value": parsed_form['registrant']['registrant_contact_phone'],
},
{
"type": "email",
"note": "contact email",
"value": parsed_form['registrant']['registrant_contact_email'],
}
]
for cd in main_contact_contact_details:
_main_contact.add_contact_detail(**cd)
if _registrant._type == 'organization':
_registrant.add_member(
name_or_person=_main_contact,
role='main_contact',
label='main contact for {n}'.format(n=_registrant.name),
start_date=_disclosure.effective_date.strftime('%Y-%m-%d')
)
else:
_registrant_self_employment.add_member(
name_or_person=_main_contact,
role='main_contact',
label='main contact for {n}'.format(n=_registrant.name),
start_date=_disclosure.effective_date.strftime('%Y-%m-%d')
)
# # Client
# build client
_client = Organization(
name=parsed_form['client']['client_name'],
classification='company',
source_identified=True
)
client_contact_details = [
{
"type": "address",
"note": "contact address",
"value": '; '.join([
p for p in [
parsed_form['client']['client_address'],
parsed_form['client']['client_city'],
parsed_form['client']['client_state'],
parsed_form['client']['client_zip'],
parsed_form['client']['client_country']]
if len(p) > 0]).strip(),
},
]
client_contact_ppb = {
"type": "address",
"note": "principal place of business",
"value": '; '.join([
p for p in [
parsed_form['client']['client_ppb_city'],
parsed_form['client']['client_ppb_state'],
parsed_form['client']['client_ppb_zip'],
parsed_form['client']['client_ppb_country']]
if len(p) > 0]).strip(),
}
if client_contact_ppb["value"]:
client_contact_details.append(client_contact_ppb)
for cd in client_contact_details:
_client.add_contact_detail(**cd)
_client.extras = {
"contact_details_structured": [
{
"type": "address",
"note": "contact address",
"parts": [
{
"note": "address",
"value": parsed_form['client']['client_address'],
},
{
"note": "city",
"value": parsed_form['client']['client_city'],
},
{
"note": "state",
"value": parsed_form['client']['client_state'],
},
{
"note": "zip",
"value": parsed_form['client']['client_zip'],
},
{
"note": "country",
"value": parsed_form['client']['client_country'],
}
],
},
{
"type": "address",
"note": "principal place of business",
"parts": [
{
"note": "city",
"value": parsed_form['client']['client_ppb_city'],
},
{
"note": "state",
"value": parsed_form['client']['client_ppb_state'],
},
{
"note": "zip",
"value": parsed_form['client']['client_ppb_zip'],
},
{
"note": "country",
"value": parsed_form['client'][
'client_ppb_country'],
}
],
},
],
}
# Collect Foreign Entities
_foreign_entities = []
_foreign_entities_by_name = {}
for fe in parsed_form['foreign_entities']:
fe_extras = {}
fe_name = fe['foreign_entity_name']
# check for name-based duplicates
if fe_name in _foreign_entities_by_name:
_foreign_entity = _foreign_entities_by_name[fe_name]
else:
_foreign_entity = Organization(
name=fe_name,
classification='company',
source_identified=True
)
# collect contact details
foreign_entity_contact_details = [
{
"type": "address",
"note": "contact address",
"value": '; '.join([
p for p in [
fe['foreign_entity_address'],
fe['foreign_entity_city'],
fe['foreign_entity_state'],
fe['foreign_entity_country']]
if len(p) > 0]).strip(),
},
{
"type": "address",
"note": "principal place of business",
"value": '; '.join([
p for p in [
fe['foreign_entity_ppb_state'],
fe['foreign_entity_ppb_country']]
if len(p) > 0]).strip(),
},
]
foreign_entity_contact_ppb = {
"type": "address",
"note": "principal place of business",
"value": '; '.join([
p for p in [
fe['foreign_entity_ppb_city'],
fe['foreign_entity_ppb_state'],
fe['foreign_entity_ppb_country']]
if len(p) > 0]),
}
if foreign_entity_contact_ppb["value"]:
foreign_entity_contact_details.append(
foreign_entity_contact_ppb)
# add contact details
for cd in foreign_entity_contact_details:
if cd['value'] != '':
_foreign_entity.add_contact_detail(**cd)
# add extras
fe_extras["contact_details_structured"] = [
{
"type": "address",
"note": "contact address",
"parts": [
{
"note": "address",
"value": fe['foreign_entity_address'],
},
{
"note": "city",
"value": fe['foreign_entity_city'],
},
{
"note": "state",
"value": fe['foreign_entity_state'],
},
{
"note": "country",
"value": fe['foreign_entity_country'],
}
],
},
{
"type": "address",
"note": "principal place of business",
"parts": [
{
"note": "state",
"value": fe['foreign_entity_ppb_state'],
},
{
"note": "country",
"value": fe['foreign_entity_ppb_country'],
}
],
},
]
_foreign_entity.extras = combine_dicts(_foreign_entity.extras,
fe_extras)
_foreign_entities_by_name[fe_name] = _foreign_entity
for unique_foreign_entity in _foreign_entities_by_name.values():
_foreign_entities.append(unique_foreign_entity)
# TODO: add a variant on memberships to represent inter-org
# relationships (associations, ownership, etc)
#
# _client['memberships'].append({
# "id": _foreign_entity['id'],
# "classification": "organization",
# "name": _foreign_entity['name'],
# "extras": {
# "ownership_percentage":
# fe['foreign_entity_amount']
# }
# })
# Collect Lobbyists
# TODO: deal with wierd non-name line continuation cases (blanks, "continued")
_lobbyists_by_name = {}
for l in parsed_form['lobbyists']:
l_extras = {}
l_name = ' '.join([l['lobbyist_first_name'],
l['lobbyist_last_name'],
l['lobbyist_suffix']
]).strip()
if l_name in _lobbyists_by_name:
_lobbyist = _lobbyists_by_name[l_name]
else:
_lobbyist = Person(
name=l_name,
source_identified=True
)
if l['lobbyist_covered_official_position']:
l_extras['lda_covered_official_positions'] = [
{
'date_reported':
parsed_form['datetimes']['effective_date'],
'covered_official_position':
l['lobbyist_covered_official_position']
},
]
_lobbyist.extras = combine_dicts(_lobbyist.extras, l_extras)
_lobbyists_by_name[l_name] = _lobbyist
_lobbyists = []
for unique_lobbyist in _lobbyists_by_name.values():
_lobbyists.append(unique_lobbyist)
if _registrant._type == 'organization':
for l in _lobbyists:
_registrant.add_member(
l,
role='lobbyist',
label='lobbyist for {n}'.format(n=_registrant.name),
start_date=_disclosure.effective_date.strftime('%Y-%m-%d')
)
else:
for l in _lobbyists:
_registrant_self_employment.add_member(
l,
role='lobbyist',
label='lobbyist for {n}'.format(n=_registrant.name),
start_date=_disclosure.effective_date.strftime('%Y-%m-%d')
)
# # Document
# build document
_disclosure.add_document(
note='submitted filing',
date=parsed_form['datetimes']['effective_date'][:10],
url=response.url
)
# Collect Affiliated orgs
_affiliated_organizations = []
_affiliated_organizations_by_name = {}
for ao in parsed_form['affiliated_organizations']:
ao_extras = {}
ao_name = ao['affiliated_organization_name']
if ao_name in _affiliated_organizations_by_name:
# There's already one by this name
_affiliated_organization = _affiliated_organizations_by_name[ao_name]
else:
# New affiliated org
_affiliated_organization = Organization(
name=ao_name,
classification='company',
source_identified=True
)
# collect contact details
affiliated_organization_contact_details = [
{
"type": "address",
"note": "contact address",
"value": '; '.join([
p for p in [
ao['affiliated_organization_address'],
ao['affiliated_organization_city'],
ao['affiliated_organization_state'],
ao['affiliated_organization_zip'],
ao['affiliated_organization_country']]
if len(p) > 0]).strip(),
},
]
affiliated_organization_contact_ppb = {
"type": "address",
"note": "principal place of business",
"value": '; '.join([
p for p in [
ao['affiliated_organization_ppb_city'],
ao['affiliated_organization_ppb_state'],
ao['affiliated_organization_ppb_country']]
if len(p) > 0]).strip(),
}
if affiliated_organization_contact_ppb["value"]:
affiliated_organization_contact_details.append(
affiliated_organization_contact_ppb)
# add contact details
for cd in affiliated_organization_contact_details:
_affiliated_organization.add_contact_detail(**cd)
ao_extras["contact_details_structured"] = [
{
"type": "address",
"note": "contact address",
"parts": [
{
"note": "address",
"value": ao['affiliated_organization_address'],
},
{
"note": "city",
"value": ao['affiliated_organization_city'],
},
{
"note": "state",
"value": ao['affiliated_organization_state'],
},
{
"note": "zip",
"value": ao['affiliated_organization_zip'],
},
{
"note": "country",
"value": ao['affiliated_organization_country'],
}
],
},
{
"type": "address",
"note": "principal place of business",
"parts": [
{
"note": "city",
"value":
ao['affiliated_organization_ppb_city'],
},
{
"note": "state",
"value":
ao['affiliated_organization_ppb_state'],
},
{
"note": "country",
"value":
ao['affiliated_organization_ppb_country'],
}
],
},
],
_affiliated_organization.extras = combine_dicts(
_affiliated_organization.extras, ao_extras)
for unique_affiliated_organization in _affiliated_organizations_by_name.values():
_affiliated_organizations.append(unique_affiliated_organization)
# # Events & Agendas
# name
if parsed_form['registration_type']['new_registrant']:
registration_type = 'New Client, New Registrant'
elif parsed_form['registration_type']['is_amendment']:
registration_type = 'Amended Registration'
else:
registration_type = 'New Client for Existing Registrant'
# Create registration event
_event = Event(
name="{rn} - {rt}, {cn}".format(rn=_registrant.name,
rt=registration_type,
cn=_client.name),
timezone='America/New_York',
location='United States',
start_time=datetime.strptime(
parsed_form['datetimes']['effective_date'],
'%Y-%m-%d %H:%M:%S').replace(tzinfo=UTC),
classification='registration'
)
# add participants
_event.add_participant(type=_registrant._type,
id=_registrant._id,
name=_registrant.name,
note="registrant")
if _registrant._type == 'person':
_event.add_participant(type=_registrant._type,
id=_registrant._id,
name=_registrant.name,
note="registrant")
_event.add_participant(type=_client._type,
id=_client._id,
name=_client.name,
note="client")
for l in _lobbyists:
_event.add_participant(type=l._type,
id=l._id,
name=l.name,
note='lobbyist')
for fe in _foreign_entities:
_event.add_participant(type=fe._type,
id=fe._id,
name=fe.name,
note='foreign_entity')
for ao in _affiliated_organizations:
_event.add_participant(type=ao._type,
id=ao._id,
name=ao.name,
note='affiliated_organization')
# add agenda item
_agenda = _event.add_agenda_item(
description='issues lobbied on',
)
_agenda['notes'].append(
parsed_form['lobbying_issues_detail']
)
for li in parsed_form['lobbying_issues']:
if li['general_issue_area'] != '':
_agenda.add_subject(li['general_issue_area'])
_disclosure.add_disclosed_event(
name=_event.name,
type=_event._type,
classification=_event.classification,
id=_event._id
)
# add registrant to disclosure's _related and related_entities fields
_disclosure.add_registrant(name=_registrant.name,
type=_registrant._type,
id=_registrant._id)
_registrant.add_source(
url=_source['url'],
note='registrant'
)
yield _registrant
if _registrant_self_employment is not None:
_registrant_self_employment.add_source(
url=_source['url'],
note='registrant_self_employment'
)
yield _registrant_self_employment
_client.add_source(
url=_source['url'],
note='client'
)
yield _client
_main_contact.add_source(
url=_source['url'],
note='main_contact'
)
yield _main_contact
for ao in _affiliated_organizations:
ao.add_source(
url=_source['url'],
note='affiliated_organization'
)
yield ao
for fe in _foreign_entities:
fe.add_source(
url=_source['url'],
note='foreign_entity'
)
yield fe
for l in _lobbyists:
l.add_source(
url=_source['url'],
note='lobbyist'
)
yield l
_event.add_source(**_source)
yield _event
_disclosure.add_source(**_source)
yield _disclosure
def _scrape_lower_chamber(self, session):
self.info('Scraping lower chamber for committees.')
chamber = 'lower'
url = '{base}ActiveCommittees.aspx'.format(base=self._reps_url_base)
page_string = self.get(url).text
page = lxml.html.fromstring(page_string)
table = page.xpath('//div[@class="lightened"]/table[1]')[0]
# Last tr has the date
trs = table.xpath('tr')[:-1]
for tr in trs:
committee_parts = [
part.strip() for part in tr.text_content().split(',')
]
committee_name = committee_parts[0].title().strip()
if len(committee_parts) > 0:
status = committee_parts[1].strip()
committee_url = tr.xpath('td/a')[0].attrib.get('href')
committee_url = '{base}{url}'.format(base=self._reps_url_base,
url=committee_url)
actual_chamber = chamber
if 'joint' in committee_name.lower():
actual_chamber = 'joint'
committee_name = committee_name.replace('Committee On ', '')
committee_name = committee_name.replace('Special', '')
committee_name = committee_name.replace('Select', '')
committee_name = committee_name.replace('Special', '')
committee_name = committee_name.replace('Joint', '')
committee_name = committee_name.replace(' Committee', '')
committee_name = committee_name.strip()
committee = Organization(
committee_name,
chamber=actual_chamber,
classification='committee',
)
committee.extras = {'status': status}
committee_page_string = self.get(committee_url).text
committee_page = lxml.html.fromstring(committee_page_string)
# First tr has the title (sigh)
mem_trs = committee_page.xpath('id("memGroup")/tr')[1:]
for mem_tr in mem_trs:
mem_code = None
mem_links = mem_tr.xpath('td/a[1]')
if len(mem_links):
mem_code = mem_links[0].attrib.get('href')
# Output is "Rubble, Barney, Neighbor"
mem_parts = mem_tr.text_content().strip().split(',')
if self._no_members_text in mem_parts:
continue
mem_name = (mem_parts[1].strip() + ' ' + mem_parts[0].strip())
# Sometimes Senator abbreviation is in the name
mem_name = mem_name.replace('Sen. ', '')
mem_role = 'member'
if len(mem_parts) > 2:
# Handle the case where there is a comma in the
# role name
mem_role = ', '.join([p.strip()
for p in mem_parts[2:]]).lower()
membership = committee.add_member(mem_name, role=mem_role)
membership.extras = {'code': mem_code}
committee.add_source(url)
committee.add_source(committee_url)
yield committee