def main():
args = get_args()
ch = CompaniesHouseAPI(_API_KEY, int(args.ratelimit))
_LAST_NUM_SC = 0
_LAST_NUM_BR = 0
empty_counter = 0
empty_limit = int(args.empty_limit)
with open(args.last_file, 'r+') as last_file:
data = json.load(last_file)
_LAST_NUM_BR = int(data["british_company_last_number"])
_LAST_NUM_SC = int(data["scottish_company_last_number"])
# British companies
with open(args.result_file, "a+", newline='') as res:
res.write(
"Company, Fullname, Address, Country, City, Postal Code\n")
writer = csv.writer(res)
while True:
_LAST_NUM_BR += 1
details = get_company_details(_LAST_NUM_BR, ch)
print(details)
if not details: # happens only if API returned http error or company doesn't meet our requirements
continue
if details == -1:
print("Empty counter 1 " + str(empty_counter))
if empty_counter == empty_limit:
_LAST_NUM_BR = _LAST_NUM_BR - 1
print("Empty counter 2 " + str(empty_counter))
break
else:
empty_counter += 1
continue
empty_counter = 0
writer.writerows(details)
# Scottish companies
empty_counter = 0
while True:
_LAST_NUM_SC += 1
details = get_company_details("SC" + str(_LAST_NUM_SC), ch)
if not details:
continue
if details == -1:
if empty_counter == empty_limit:
_LAST_NUM_SC = _LAST_NUM_SC - 1
break
else:
empty_counter += 1
continue
empty_counter = 0
writer.writerows(details)
data[
"british_company_last_number"] = _LAST_NUM_BR - empty_limit # because we are checking 100 extra numbers
data["scottish_company_last_number"] = _LAST_NUM_SC - empty_limit
last_file.seek(0)
last_file.truncate()
json.dump(data, last_file)
exit(0)
def get_director(number: str, ch: CompaniesHouseAPI) -> str:
director: str = ""
psc = ch.list_company_officers(company_number=number)
if not psc:
psc = ch.list_company_persons_with_significant_control(
company_number=number)
if not psc:
psc = ch.list_company_persons_with_significant_control_statements(
company_number=number)
if not psc:
return None
if psc.get("active_count") == 1:
officers = psc.get("items")
for officer in officers:
if officer.get("officer_role") == "director":
director = officer.get("name")
return director
def get_company_details(number: str, ch: CompaniesHouseAPI) -> list:
company: dict = {}
res = None
try:
company = ch.get_company(company_number=number)
except HTTPError as e:
print("Companies House API returned error %sn " %
str(e)) # Sometimes companies house returns 502
sleep(15) # we ill just wait 15 seconds and than retry
company = ch.get_company(company_number=number)
if not company:
res = None
if company: # checking for empty dict
creation_date = datetime.datetime.strptime(
company.get("date_of_creation"), "%Y-%m-%d").date()
time_delta = (datetime.datetime.now().date() - creation_date).days
print("Company was registered " + str(time_delta) + " days ago")
if company.get(
"company_status"
) == "active" and "registered_office_address" in company and company.get(
'type') == "ltd":
director = get_director(number, ch)
name = company["company_name"]
if director:
address, country, city, postal_code = get_address(company)
print(name)
print(director)
print(address)
print(number)
res = [[
str(name).replace(',', ' '),
str(director).replace(',', ' '),
str(address).replace(',', ' '),
str(country).replace(',', ' '),
str(city).replace(',', ' '),
str(postal_code).replace(',', ' ')
]]
return res
else:
res = -1
print(str(number) + " company does not exist or meet our requirements")
return res
#!/home/kimgid/.virtualenvs/myproject/bin/python
from companies_house.api import CompaniesHouseAPI
ch = CompaniesHouseAPI('HwcI7GpyQ7KzwZjE9lf0cqXIlDU1M6dy0CyzgCvQ')
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from fuzzywuzzy import fuzz
import time
import datetime
import requests
import pytesseract
from pdf2image import convert_from_path
from PIL import Image
import json
import os
import re
"""url = "https://beta.companieshouse.gov.uk//company/05396788/filing-history/MzI2MDEzNTAwMmFkaXF6a2N4/document?format=pdf"
r = requests.get(url)
with open('test1.pdf', 'wb') as fp:
fp.write(r.content)"""
# Load today's links
with open('todays_links.json', 'r') as fp:
data = json.load(fp)
matches = []
# Create test tech giants to check
#!/home/kimgid/.virtualenvs/myproject/bin/python
from companies_house.api import CompaniesHouseAPI
ch = CompaniesHouseAPI('HwcI7GpyQ7KzwZjE9lf0cqXIlDU1M6dy0CyzgCvQ')
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from fuzzywuzzy import fuzz
import time
allcompanies2010 = pd.read_csv('data2010.csv').to_dict(orient='records')
company_names1 = []
for i in allcompanies2010:
company_names1.append(i['0'])
companydata = []
for i in company_names1:
d = {}
time.sleep(0.55)
d['search'] = i
d['companiesinsearch'] = ch.search_companies(q=i)
d['numbercompanies'] = len(d['companiesinsearch']['items'])
companydata.append(d)
print(d)
companydata2 = []
for i in companydata:
for j in i['companiesinsearch']['items']:
score = fuzz.token_sort_ratio(j['title'], i['search'])
m = {}
m['search'] = i['search']
with open('player_list.csv', 'r', encoding='utf-8-sig') as f:
csv_reader = csv.DictReader(f)
for row in csv_reader:
d = dict()
d['club'] = row['Club']
d['name'] = row['Name']
d['position'] = row['Position']
d['country'] = row['Country']
player_list.append(d)
return player_list
if __name__ == '__main__':
with open('config.yaml', 'r') as f:
config = yaml.safe_load(f)
ch = CompaniesHouseAPI(config['chapi_key'])
players = load_player_list()
if len(players) > 600:
print(f'Warning: {len(players)} will likely cause the API rate limit to be exceeded.')
for player in players[0:10]:
results = ch.search_officers(q=player['name'])
print(f"{player['name']}: {results['total_results']}")
for item in results['items']:
found_name = item['title']
lev = levenshtein_score(player['name'], found_name)
if lev > 0.9:
print(f"good hit: {found_name} >< {player['name']} ({lev})")
else:
#!/home/kimgid/.virtualenvs/myproject/bin/python
from companies_house.api import CompaniesHouseAPI
ch = CompaniesHouseAPI('HwcI7GpyQ7KzwZjE9lf0cqXIlDU1M6dy0CyzgCvQ')
import pandas as pd
import numpy as np
import json
import matplotlib.pyplot as plt
from fuzzywuzzy import fuzz
import time
import datetime
# Read the pre-gathered list of UK startup names
allcompanies2010 = pd.read_csv('companydata3.csv').to_dict(orient='records')
# Call API for filing history
todayslinks = []
df2010 = []
for j, i in enumerate(allcompanies2010):
f = {}
f['chnumber'] = i['chnumber']
f['company_name'] = i['officialname']
f['search'] = i['search']
print('checking:')
print(f['company_name'])
try:
f['filhis'] = ch.list_company_filing_history(
company_number=f['chnumber'], items_per_page='10')['items']
for d in f['filhis']:
b = {}
def setUp(self):
self.base_api: CompaniesHouseAPIBase = CompaniesHouseAPIBase(API_KEY)
self.api: CompaniesHouseAPI = CompaniesHouseAPI(API_KEY)
from companies_house.api import CompaniesHouseAPI
from datetime import datetime
from string import capwords
import pprint
api_key = 'gHggW0wcFUkPigIifYRo864nCxGBqqIYMLm3Pd_O'
ch = CompaniesHouseAPI(api_key)
company_request_cache = {}
officers_request_cache = {}
def get_officers(company_number):
officers_request = None
if company_number in officers_request_cache is True:
officers_request = officers_request_cache[company_number]
else:
company_request = get_company(company_number)
if company_request is not None:
officers_request = ch.list_company_officers(
company_number=company_number)
if officers_request is not None:
ps = datetime.fromisoformat(
company_request['accounts']['next_accounts']
['period_start_on'])
pe = datetime.fromisoformat(company_request['accounts']
['next_accounts']['period_end_on'])