def search_company_filings_by_cik(self, cik, filing_type, filing_subtype, no_of_entries, filing_date_before,
filing_pattern, filing_rsrc_cache):
# TODO: build dynamic from file
filing_types = ["425", "8-K", "10-K", "10-Q"]
filing_subtypes = ["EX-1", "EX-2", "EX-3", "EX-4", "EX-5", "EX-6", "EX-7", "EX-8", "EX-9", "EX-10", "EX-11",
"EX-12", "EX-13", "EX-14", "EX-15", "EX-16", "EX-17", "EX-18", "EX-19", "EX-20", "EX-21",
"EX-22", "EX-23", "EX-24", "EX-25", "EX-25", "AEX-26", "EX-28", "EX-29", "EX-31", "EX-32",
"EX-33", "EX-34", "EX-35", "EX-99"]
if filing_type in filing_types:
if filing_subtype in filing_subtypes or \
re.match(r'EX-\d\d\.*', filing_subtype, re.IGNORECASE) or \
filing_subtype in filing_types :
edgar = Edgar()
self.alogger.debug("Getting company registration from endpoint")
company_name = edgar.get_company_name_by_cik(cik=cik)
self.search_company(company_name, cik,
filing_type, filing_subtype,
no_of_entries, filing_date_before, filing_pattern, filing_rsrc_cache)
else:
print("{} not a recognized filing subtype.".format(filing_subtype))
print("Supported filing subtypes:")
for filing_subtype in filing_subtypes:
print(filing_subtype)
else:
print("{} not a recognized filing type.".format(filing_type))
print("Supported filing types:")
for filing_type in filing_types:
print(filing_type)
def find_company_by_name(self, name):
"""
Requests EDGAR for a company by name and obtains it's CIK number
:param name: Company name
:return: None.
"""
if not "".__eq__(name):
edgar = Edgar()
try:
company_cik = edgar.get_cik_by_company_name(name=name.upper())
print("{0}:{1}".format(name.upper(), company_cik))
except Exception as e:
print("Error: ", e)
else:
print("No name provided (-n|-N options)")
def find_company_by_names_fuzzy(self, names):
"""
Requests EDGAR for a company by name pattern to obtain a list of potentials
:param names: A pattern for a name
:return: None. Prints list of possible matches
"""
if len(names) != 0:
edgar = Edgar()
for n in names:
if not "".__eq__(n):
possible_companies = edgar.find_company_name(n)
for pc in possible_companies:
cik = edgar.get_cik_by_company_name(pc)
# Provide more details to help choose the right one
if self.aconfig['args'].edgar_company_names_fuzzy_detail:
print("\nName/CIK: {0}:{1}".format(pc, cik))
cik_feed = self.aconfig['args'].endpoint + \
"/cgi-bin/browse-edgar?action=getcompany&CIK=" + \
cik + "&output=atom"
try:
response = requests.get(cik_feed)
od = xmltodict.parse(response.content)
state_inc = od['feed']['company-info']['state-of-incorporation']
state_loc = od['feed']['company-info']['state-location']
print("{0:>10} : {1}/{2}".format("State Incorporated/State Located", state_inc, state_loc))
print("{0:>5}".format("Addresses:"))
for k, addresses in od['feed']['company-info']['addresses'].items():
for addr in addresses:
print()
for k, v in addr.items():
print("{0:>10} {1}".format(k,v))
except requests.ConnectionError as ce:
print("Error fetching atom feed: ", ce)
except xml.parsers.expat.ExpatError as xe:
print("Error fetching atom feed: ", xe)
print("---")
else:
print("{0}:{1}".format(pc, cik))
else:
print("Skipping empty name")
else:
print("No names provided (-N option)")
def main():
# initialize the EDGAR database
edgar = Edgar()
# has_ex_10(edgar)
training_sentences = get_training_sentences(
'training_sentences/sentences_200_2.csv')
entity_finder_ui(training_sentences)
def fetch10K(company, start, end):
edgar = Edgar(company, '10')
docs = edgar.getFilingDocuments(start, end)
print "get back doc count: ", len(docs)
for d in docs:
print d
from edgar import Company, TXTML, XBRLElement, XBRL, Edgar
db = Edgar()
comp_name = 'TESLA, INC.'
company = Company(comp_name, db.all_companies_dict[comp_name])
'''
company = Company("Oracle Corp", "0001341439")
tree = company.get_all_filings(filing_type = "10-K")
docs = Company.get_documents(tree, no_of_documents=5)
print (docs)
text = TXTML.parse_full_10K(docs[0])
#print (text)
#company = edgar.Company(Ticker,"21344")
#print company
company = Company("Oracle Corp", "0001341439")
results = company.get_data_files_from_10K("EX-101.INS", isxml=True)
xbrl = XBRL(results[0])
element = XBRLElement(xbrl.relevant_children_parsed[15]).to_dict()#// returns a dictionary of name, value, and schemaRef
print(element)
'''
from edgar import Edgar
edgar = Edgar()
possible_companies = edgar.find_company_name("Cisco System")
from edgar import Edgar, Company
import pandas as pd
import os
import pickle
companies = "data/companies.csv"
edgar = Edgar()
df_companies = pd.read_csv(companies, sep=";")
companies_unique = df_companies["company"].dropna().unique()
def is_item_header(nr, title, text, prev, title_key_word):
bare_len = len("item " + nr + title)
for c in [" ", ".", " ", "\n", "\xa0"]:
text = text.replace(c, "")
text = text.lower()
length = len(text)
if nr in text and length < len(nr) + 2 and "item" in prev.lower() and len(prev.replace(" ", "")) < 10:
return True
if length < len("item " + nr) + 4:
if length < 4 + len(nr) and "m" in text and nr in text:
return True
if length < 5 + len(nr) and "em" in text and nr in text:
return True
if length < 6 + len(nr) and "tem" in text and nr in text:
from edgar import Edgar
edgar = Edgar()
possible_companies = edgar.find_company_name("microsoft corp")
print(possible_companies)
# edgar.download_index("/home/sroot/kaizha/temp/", 2020, skip_all_present_except_last=Tr
print(edgar.get_company_name_by_cik("0000789019"))