def get_filings(cik, ticker):
t1 = time.time()
# create object
seccrawler = SecCrawler()
companyCode = ticker # company code for apple
cik = cik # cik code for apple
date = '20170101' # date from which filings should be downloaded
count = '10' # no of filings
seccrawler.filing_10K(str(companyCode), str(cik), str(date), str(count))
t2 = time.time()
print("Total Time taken: "),
print(t2 - t1)
def get_filings(cik, ticker):
t1 = time.time()
# create object
seccrawler = SecCrawler()
companyCode = ticker
cik = cik
date = '20170101'
count = '10'
seccrawler.filing_10K(str(companyCode), str(cik), str(date), str(count))
t2 = time.time()
print("Total Time taken: "),
print(t2 - t1)
def get_filings(companyCode, date='20200101', cik=None, count=100):
if cik is None:
with open('company_list.txt', 'r') as f:
for line in f:
if companyCode in line:
line_arr = line.rstrip().split(' ')
cik = line_arr[-1]
if cik is None:
print("cik not provided and not found in list. please try again.")
return
# create object
seccrawler = SecCrawler()
seccrawler.filing_10K(str(companyCode), str(cik), str(date), str(count))
dest_dir = companyCode + "/"
src_dir = dest_dir + cik + "/10-K/"
years_downloaded = []
for old_filename in os.listdir(src_dir):
parts = old_filename.split('-')
old_year = parts[1]
if int(old_year) > 50:
new_year = '19' + old_year
else:
new_year = '20' + old_year
years_downloaded.append(new_year)
os.rename(src_dir + old_filename, dest_dir + companyCode + '_10K_' + new_year + '.txt')
shutil.rmtree(dest_dir + cik + '/')
# create object
seccrawler = SecCrawler()
seccrawler.filing_10Q(str(companyCode), str(cik), str(date), str(count))
dest_dir = companyCode + "/"
src_dir = dest_dir + cik + "/10-Q/"
years_downloaded = []
for old_filename in os.listdir(src_dir):
parts = old_filename.split('-')
old_year = parts[1]
if int(old_year) > 20:
new_year = '19' + old_year
else:
new_year = '20' + old_year
years_downloaded.append(new_year)
os.rename(src_dir + old_filename, dest_dir + companyCode + '_10Q_' + new_year + '.txt')
shutil.rmtree(dest_dir + cik + '/')
return years_downloaded
def getfilings():
t1 = time.time()
# create object
seccrawler = SecCrawler()
companyCode = 'AAPL' # compnay ticker symbol for Apple
cik = '0000320193' # cik code for Apple
date = '20010101' # date from which filings should be downloaded (01/01/2001 in this case)
count = '10' # the number of filings
seccrawler.filing_10Q(str(companyCode), str(cik), str(date), str(count))
seccrawler.filing_10K(str(companyCode), str(cik), str(date), str(count))
seccrawler.filing_8K(str(companyCode), str(cik), str(date), str(count))
seccrawler.filing_13F(str(companyCode), str(cik), str(date), str(count))
t2 = time.time()
print("Total time taken: ")
print(t2 - t1)
def get_filings():
t1 = time.time()
DEFAULT_DATA_PATH = os.path.join(os.path.abspath(os.getcwd()), 'output')
# create object
seccrawler = SecCrawler()
companyCode = 'AAPL' # company code for apple
cik = '0000320193' # cik code for apple
date = '20010101' # date from which filings should be downloaded
count = '10' # no of filings
seccrawler.filing_10Q(str(companyCode), str(cik), str(date), str(count))
seccrawler.filing_10K(str(companyCode), str(cik), str(date), str(count))
seccrawler.filing_8K(str(companyCode), str(cik), str(date), str(count))
seccrawler.filing_13F(str(companyCode), str(cik), str(date), str(count))
t2 = time.time()
print("Total Time taken: "),
print(t2 - t1)
def get_all_filings(self, deadline):
''' get the SEC filings for all companies in US stock universe'''
t1 = time.time()
# create object
seccrawler = SecCrawler()
companyCode = 'AAPL' # company code for apple
cik = '0000320193' # cik code for apple
date = '20160101' # date from which filings should be downloaded
count = '100' # no of filings
seccrawler.filing_10Q(str(companyCode), str(cik), str(date), str(count))
seccrawler.filing_10K(str(companyCode), str(cik), str(date), str(count))
seccrawler.filing_8K(str(companyCode), str(cik), str(date), str(count))
seccrawler.filing_13F(str(companyCode), str(cik), str(date), str(count))
t2 = time.time()
print "Total Time taken: " + str(t2-t1),
def get_filings():
t1 = time.time()
# create object
seccrawler = SecCrawler()
companyCode = "AAPL" # company code for apple
cik = "0000320193" # cik code for apple
date = "20010101" # date from which filings should be downloaded
count = "10" # no of filings
seccrawler.filing_10Q(str(companyCode), str(cik), str(date), str(count))
seccrawler.filing_10K(str(companyCode), str(cik), str(date), str(count))
seccrawler.filing_8K(str(companyCode), str(cik), str(date), str(count))
seccrawler.filing_13F(str(companyCode), str(cik), str(date), str(count))
t2 = time.time()
print
"Total Time taken: ",
print(t2 - t1)
def test():
t1 = time.time()
# file containing company name and corresponding cik codes
seccrawler = SecCrawler()
company_code_list = list() # company code list
cik_list = list() # cik code list
date_list = list() # pror date list
count_list = list()
try:
crs = open("data.txt", "r")
except:
print("No input file Found")
# get the company quotes and cik number from the file.
for columns in (raw.strip().split() for raw in crs):
company_code_list.append(columns[0])
cik_list.append(columns[1])
date_list.append(columns[2])
count_list.append(columns[3])
# call different API from the crawler
#for i in range(1, len(cik_list)):
# seccrawler.filing_SD(str(company_code_list[i]), str(cik_list[i]),
# str(date_list[i]), str(count_list[i]))
# seccrawler.filing_10K(str(company_code_list[i]), str(cik_list[i]),
# str(date_list[i]), str(count_list[i]))
# seccrawler.filing_8K(str(company_code_list[i]), str(cik_list[i]),
# str(date_list[i]), str(count_list[i]))
seccrawler.filing_10Q('AAPL', '0000320193', '20170101', '1')
t2 = time.time()
print("Total Time taken: "),
print(t2 - t1)
crs.close()
def get_filings(): t1 = time.time() # create object seccrawler = SecCrawler() companyCode = 'AAPL' # company code for apple cik = '0000320193' # cik code for apple date = '20010101' # date from which filings should be downloaded count = '10' # no of filings seccrawler.filing_10Q(str(companyCode), str(cik), str(date), str(count)) seccrawler.filing_10K(str(companyCode), str(cik), str(date), str(count)) seccrawler.filing_8K(str(companyCode), str(cik), str(date), str(count)) seccrawler.filing_13F(str(companyCode), str(cik), str(date), str(count)) t2 = time.time() print "Total Time taken: ", print (t2-t1) if __name__ == '__main__': get_filings()
def scrape_edgar(self):
"""This is the function that will scrape the SEC Edgar website and download all 10-Ks.
We are using a third-party package called SECEdgar which does the job, but this would
be improved if we wrote our own web crawler that could pre-filter any amended 10-Ks and
10-Ks that fall outside of our date range before downloading them."""
# Remove any duplicates where CUSIP, PERMNO, and CIK match
ciks = self.data.drop_duplicates(subset=['CUSIP', 'PERMNO', 'cik'])
# Only keep the cik and ticker column
ciks = ciks[['cik', 'tic']]
# Iterate over each CIK and pull the relevant 10k filings
crawler = SecCrawler()
end_date = str(self.end) + '1231'
count = str(math.ceil((self.end - self.start) / 10) * 10)
p = Pool()
rows = ciks.to_dict(orient='records')
results = p.starmap(crawl, zip(rows, repeat(end_date), repeat(count), repeat(crawler)))
def crawler():
obj = SecCrawler()
return obj
"""
#%%
import re
from SECEdgar.crawler import SecCrawler
#%% GEt names of companies
sector_code = '10'
list_companies = []
with open('tic_company_gics.txt') as file:
for line in file:
sector = line[-3:-1]
if sector == sector_code:
name_company = re.search('[\w\.]+', line).group()#[:-1]
list_companies.append(name_company)
list_companies = list(set(list(list_companies)))
#%% Download the 10K
number_of_companies = 50
date_retrieve = '20150101'
number_10K = 5
secCrawler = SecCrawler()
for company in list_companies[0:number_of_companies]:
secCrawler.filing_10K(company, date_retrieve, number_10K)
def crawler():
_crawler = SecCrawler()
yield _crawler
shutil.rmtree(_crawler.data_path)
CIK_RE = re.compile(r'.*CIK=(\d{10}).*')
cik = ''
results = CIK_RE.findall(get(URL.format(name)).content)
if len(results):
cik = str(results[0])
return cik
list_companies = []
with open('tic_company_gics.txt') as file:
for line in file:
sector = line[-3:-1]
if sector == sector_code:
name_company = re.search('[\w\.]+', line).group()#[:-1]
list_companies.append(name_company)
list_companies = list(set(list(list_companies)))
#%% GEt SIC code for each company
list_companies_cik = []
for company in list_companies:
cik = get_cik(company)
if len(cik) > 0:
list_companies_cik.append((company, cik))
#%% Get 10K
secCrawler = SecCrawler()
for name, cik in list_companies_cik:
secCrawler.filing_10K(name, cik, '20150101', '1')
from SECEdgar.crawler import SecCrawler
crawler = SecCrawler()
def get(symbol):
crawler.filing_10Q(symbol, '0000320193', '20010101', '10')
# http://rankandfiled.com/#/data/tickers
from SECEdgar.crawler import SecCrawler
filings = SecCrawler()
filings.filing_10Q("MSFT", "0000789019", "20190101", 100)
from SECEdgar.crawler import SecCrawler
secCrawler = SecCrawler()
secCrawler.filing_8K("", "0001527166", "", "2000")
secCrawler.filing_8K("AAPL", "0000320193", "", "2000")
secCrawler.filing_10Q("AAPL", "0000320193", "20010101", "10")
secCrawler.filing_DEF14A("AAPL", "0000320193", "20010101", "10")
secCrawler.filing_DEF14A("", "0000320193", "", "")
secCrawler.filing_DEF14A("", "0001629210", "", "")
# http://www.sec.gov/cgi-bin/browse-edgar?action=getcompany&CIK=0000320193&type=8-K&dateb=20010101&owner=exclude&output=xml&count=10
# https://www.sec.gov/Archives/edgar/data/320193/000091205700010000/0000912057-00-010000.txt
# https://www.sec.gov/Archives/edgar/data/320193/000091205700010000/0000912057-00-010000.txt
# https://www.sec.gov/Archives/edgar/data/320193/0000912057-00-010000-.txt
# www.sec.gov/Archives/edgar/data/320193/000104746999003858/0001047469-99-003858-.txt
# https://www.sec.gov/Archives/edgar/data/320193/0001047469-99-003858.txt
# http://www.sec.gov/Archives/edgar/data/320193/0001047469-99-003858-.txt
from tqdm import tqdm
import requests
url = "http://www.sec.gov/Archives/edgar/data/320193/000091205700053623/0000912057-00-053623.txt"
response = requests.get(url, stream=True)
with open("d:/SEC-Edgar-data/AAPL/0000320193/10-K/0000912057-00-053623.txt", "w") as handle:
for data in tqdm(response.iter_content()):
def crawler():
_crawler = SecCrawler()
yield _crawler
