def get_comp_tuples(companies,data_folder):
'''
'''
with open('sp500tickcik', 'rb') as file:
data = pickle.load(file)
names = []
for idx in range(len(data)):
names = np.append(names,data[idx][3])
tick_cik = []
edgar_t = edgar.Edgar()
for name in companies:
score=[]
for textTemp in names:
score = np.append(score, fuzz.ratio(textTemp, name))
maxInd = np.where(score == np.amax(score))[0][0]
bmc = str(data[maxInd][3])
bmc = bmc.replace("'" , "")
bmc = bmc.replace("." , "")
comp = edgar_t.findCompanyName(bmc)
tick_cik = np.append(tick_cik,(comp[0],data[maxInd][1]))
import os
import requests
import xlrd
import edgar
from company import Company
import xlsxwriter
from bs4 import BeautifulSoup
edg = edgar.Edgar()
oo = 1e9
def print_log(mess, log_file, verbose=True):
if verbose:
print(mess)
if log_file is not None:
log_file.write(mess + "\n")
def format_cik_file(input_file="cik.xlsx",
output_file="cik.xlsx",
verbose=True,
log_file=None):
cik_sheet = xlrd.open_workbook(input_file).sheet_by_index(0)
if os.path.exists(output_file):
os.remove(output_file)
output_wb = xlsxwriter.Workbook(output_file)
output_sheet = output_wb.add_worksheet()
import edgar
edgar = edgar.Edgar()
possible_companies = edgar.findCompanyName("Cisco System")
print(possible_companies)
#get Oracle Corp's last 5 form 10-K's
company = edgar.Company("Oracle Corp", "0001341439")
tree = company.getAllFilings(filingType="10-K")
docs = edgar.getDocuments(tree, noOfDocuments=5)
#docs is an array of strings, each one is the full text doc
#SIC CODES
url = "https://www.sec.gov/info/edgar/siccodes.htm"
#Developer page
#https://www.sec.gov/developer
# Get the page number of the "financial report" section
y = re.sub("[^0-9]", "", line) # Remove non-numeric characters
fyear = int(y[-4:])
return fyear
return fyear
def countStatesApperance(doc):
table = {}
for word in doc.split():
if word in states:
table[word] = 1
return len(table)
ed = edgar.Edgar()
c = "785814"
c = c.zfill(10)
#n = ed.getCompanyNameByCik(c)
company = edgar.Company("INTEGRATED HEALTH SVCS INC", c)
tree = company.getAllFilings(filingType="10-K")
docs = edgar.getDocuments(tree, noOfDocuments=30)
with io.open("C:/Users/William/Desktop/Output.txt", "w",
encoding="utf-8") as f:
f.write(docs[0])
if len(docs) > 0:
print(countStatesApperance(docs[0]))
print(extractYear(docs[0]))
URL = 'http://www.sec.gov/cgi-bin/browse-edgar?CIK={}&Find=Search&owner=exclude&action=getcompany'
CIK_RE = re.compile(r'.*CIK=(\d{10}).*')
# change Ticker into CIK
cik_dict = {}
for ticker in DEFAULT_TICKERS:
f = requests.get(URL.format(ticker), stream=True)
results = CIK_RE.findall(f.text)
if len(results):
cik = str(results[0])
cik_dict[str(ticker).upper()] = str(results[0])
print(cik_dict)
# Use edgar to get text compilation of the lxml
# Get Company name from CIK
edgar1 = edgar.Edgar()
cmp_name = edgar1.getCompanyNameByCik(results[0])
print(cmp_name)
company = edgar.Company(cmp_name, cik)
# Creating filename and url structure
file_name = [
f for f in os.listdir(out_path)
if os.path.isfile(os.path.join(out_path, f))
]
switched_filename = file_name[0]
switched_filename = switched_filename.replace('-', '').replace(
'.txt', '/index.json')
print(switched_filename)
print(file_name)