def do_logic(self, raw_string):
"""
Method performing the logic of parsing raw data into item class
"""
# NOTE: usually the register uses 'Hours' to note time taken - very clunky but works the moment
# TODO: need to be able to parse hours values into mins, hours, days - basically interpret whatever
# was filled in on their form.
# TODO: need to decipher if the amount earned, was donated to party, charity etc
# TODO: if possible find the employer - could also check companies house to investigate further the links
# of the employer, other directors, other MPs, relatives etc
if 'Hours:' in raw_string:
amount = regex_for_amount(raw_string)
if 'monthly salary' in raw_string.lower():
amount = amount * 12
elif 'a month' in raw_string.lower():
amount = amount * 12
next_id = len(self.items) + 1
item_id = '%04d' % next_id
# not much we can really split on
pretty = raw_string.split(' (Registered')[0]
registered = regex_for_registered(raw_string)
self.items.append(
EmploymentItem(item_id, self.category_id, raw_string, pretty,
registered, amount))
def do_logic(self, raw_string):
"""
Method performing the logic of parsing raw data into dictionary
"""
amount = 0
next_id = len(self.items) + 1
item_id = '%04d' % next_id
# not much we can really split on
pretty = raw_string.split(' (Registered')[0]
registered = regex_for_registered(raw_string)
# hold a list of lists with search pair, to then regex out the value between them
regex_pairs = []
regex_pairs.append(['Name of donor: ', 'Address of donor: '])
regex_pairs.append(['Address of donor: ', 'Amount of donation '])
regex_pairs.append(
['Address of donor: ', 'Estimate of the probable value'])
regex_pairs.append(['Destination of visit: ', 'Dates of visit: '])
regex_pairs.append(['Destination of visit: ', 'Date of visit: '])
regex_pairs.append(['Dates of visit: ', 'Purpose of visit: '])
regex_pairs.append(['Date of visit: ', 'Purpose of visit: '])
regex_pairs.append(['Purpose of visit: ', r'\(Registered '])
amount = regex_for_amount(raw_string)
donor = None
address = None
destination = None
dates = None
purpose = None
for pair in regex_pairs:
regex_search = get_regex_pair_search(pair, raw_string)
if regex_search:
value = regex_search.group(1)
if 'name of donor' in pair[0].lower():
donor = value
elif 'address of donor' in pair[0].lower():
address = value
elif 'destination' in pair[0].lower():
destination = value
elif 'date' in pair[0].lower():
dates = value
elif 'dates' in pair[0].lower():
dates = value
elif 'purpose' in pair[0].lower():
pretty = value
item = VisitsOutsideUKItem(item_id, self.category_id, raw_string,
pretty, registered, amount)
item.donor = donor
item.address = address
item.destination = destination
item.dates = dates
self.items.append(item)
def do_logic(self, raw_string, raw_data):
"""
Method performing the logic of parsing raw data into dictionary
"""
next_id = len(self.items) + 1
item_id = '%04d' % next_id
# not much we can really split on
pretty = raw_string.split(' (Registered')[0]
registered = regex_for_registered(raw_string)
amount = regex_for_amount(raw_string)
donor = raw_data['raw_string']
address = ''
status = ''
for key in raw_data:
if 'name of donor' in key.lower():
donor = raw_data[key]
pretty = donor
elif 'address' in key.lower():
address = raw_data[key]
elif 'status' in key.lower():
status = raw_data[key]
item = GiftsItem(item_id, self.category_id, raw_string, pretty, registered, amount)
item.donor = donor
item.address = address
item.status = status
item.raw_data = raw_data
item.lookup()
self.items.append(item)
def do_logic(self, raw_string):
"""
Method performing the logic of parsing raw data into dictionary
"""
amount = 0
next_id = len(self.items) + 1
item_id = '%04d' % next_id
# not much we can really split on
pretty = raw_string
registered = regex_for_registered(raw_string)
# hold a list of lists with search pair, to then regex out the value between them
regex_pairs = []
regex_pairs.append(['Name of donor: ', 'Address of donor: '])
regex_pairs.append([
'Address of donor: ',
'Amount of donation or nature and value if donation in kind: '
])
regex_pairs.append([
'Amount of donation or nature and value if donation in kind:',
'Date received: '
])
regex_pairs.append(['Donor status: ', r'\(Registered '])
amount = regex_for_amount(raw_string)
donor = None
address = None
status = None
for pair in regex_pairs:
regex_search = get_regex_pair_search(pair, raw_string)
if regex_search:
value = regex_search.group(1)
if 'name of donor' in pair[0].lower():
donor = value
pretty = value
elif 'address of donor' in pair[0].lower():
address = value
elif 'donor status' in pair[0].lower():
status = value
item = IndirectDonationsItem(item_id, self.category_id, raw_string,
pretty, registered, amount)
item.donor = donor
item.address = address
item.status = status
self.items.append(item)
def do_logic(self, raw_string, raw_data):
"""
Method performing the logic of parsing raw data into item class
"""
next_id = len(self.items) + 1
item_id = '%04d' % next_id
# not much we can really split on
pretty = raw_string.split(' (Registered')[0]
registered = regex_for_registered(raw_string)
amount = regex_for_amount(raw_string)
self.items.append(MiscellaneousItem(item_id, self.category_id, raw_string, pretty, registered, amount))
def do_logic(self, raw_string, raw_data):
"""
Method performing the logic of parsing raw data into dictionary
"""
amount = 0
next_id = len(self.items) + 1
item_id = '%04d' % next_id
# not much we can really split on
pretty = raw_string.split(' (Registered')[0]
registered = regex_for_registered(raw_string)
amount = regex_for_amount(raw_string)
donor = raw_data['raw_string']
address = ''
destination = ''
purpose = ''
status = 'visit'
indiv = re.search('\([0-9]+\)', donor)
for key in raw_data:
if 'purpose' in key.lower():
purpose = raw_data[key]
elif 'destination' in key.lower():
destination = raw_data[key]
for key in raw_data:
if 'name of donor' in key.lower():
# name of donor might be: (1) Policy Network (2) Les Gracques
# split to list
# TODO
donor = raw_data[key]
pretty = donor
elif 'address' in key.lower():
address = raw_data[key]
item = VisitsOutsideUKItem(item_id, self.category_id, raw_string,
pretty, registered, amount)
item.donor = donor
item.address = address
item.destination = destination
item.purpose = purpose
item.status = status
item.lookup()
self.items.append(item)
def do_logic(self, raw_string, raw_data):
"""
Method performing the logic of parsing raw data into item class.
Here im just look for the company link. I need to verify that the mp has significant control or
is an officer to double check.
"""
matched_company = {}
next_id = len(self.items) + 1
item_id = '%04d' % next_id
# not much we can really split on
pretty = raw_string.split(' (Registered')[0]
registered = regex_for_registered(raw_string)
if self.category_description == 'Shareholdings':
amount = 1
amount = regex_for_percent(raw_string)
elif self.category_description == 'Other Shareholdings':
amount = regex_for_amount(raw_string)
if amount == 0:
amount = 70000
# were looking for:
company = None
url = ''
# print '\tRaw String : %s' % raw_string
# check if we have pre-defined this
if raw_string in urls.keys():
# print '\tPatched : %s' % urls[raw_string]
company = patched_company(urls[raw_string])
# test the patch url, may have been set to ''
if company.has_key('company_name'):
company['title'] = company['company_name']
else:
# spoof the record
company['title'] = pretty
company['links'] = {'self': ''}
company_search_string = ''
if not company and company != {}:
# no patches have been applied
company_search_string = make_search_string(raw_string)
# print '\tSearch String : %s' % company_search_string
# do the query
limit = '50'
if len(company_search_string.split(' ')) > 5:
limit = '100'
companies = CompaniesHouseCompanySearch(
queries=[company_search_string], limit=limit)
for i in companies.data:
# check for matches, when one if found, break the loop
if check_match(i, company_search_string, self.month, self.year,
self.first, self.middle, self.last,
self.display):
company = i
break
if company:
# print '\tMatched Company : %s' % company['title']
link = company['links']['self']
url = 'https://beta.companieshouse.gov.uk%s' % link
else:
company = {
'title': raw_string,
'links': {
'self': ''
},
'company_status': 'active',
'company_name': raw_string,
}
# print '\tUnmatched Company : %s' % company['title']
self.items.append(
ShareholdingsItem(item_id, self.category_id, raw_string, pretty,
registered, amount, company, url))