def findWord(comp,cik):
try:
company = Company(comp,cik)
doc = company.get_10K()
text = TXTML.parse_full_10K(doc)
#print(text)
if (re.search('blockchain', text , re.IGNORECASE)):
return("exists")
else :
return("dosenot")
except:
return("No 10-k")
from sumy.utils import get_stop_words
from sumy.parsers.plaintext import PlaintextParser
from sumy.nlp.tokenizers import Tokenizer
import sys
# company = Company("INTERNATIONAL BUSINESS MACHINES CORP", "0000051143")
# company2 = Company("twitter", "0001418091")
# company3 = Company("Oracle Corp", "0001341439")
company4 = Company("GOOGLE INC", "0001288776")
# edgar = Edgar()
# possible_companies = edgar.find_company_name("Cisco System")
#
# print(possible_companies)
doc = company4.get_10K()
text = TXTML.parse_full_10K(doc)
print('1')
f = open("text2.txt", "w+")
f.write(text)
f.close()
# f = open('text.txt', 'r')
# for line in f:
# print(line)
# print()
# print()
# print()
from edgar import Company, TXTML
import re
import pandas as pd
df = pd.read_excel(r'companylist.xls')
expense_estimates = []
for i in df.index:
print(expense_estimates)
CIK_string = df['CIK'][i].split("; ")
print(df['Company Name'][i])
company = Company("df['Company Name'][i]", CIK_string[0])
try:
doc = company.get_10K()
text = TXTML.parse_full_10K(doc)
except IndexError:
expense_estimates.append(float("NaN"))
continue
if not ('hipping' in text):
expense_estimates.append(float("NaN"))
continue
matches = [m.start() for m in re.finditer('hipping', text)]
#print(matches)
string = ""
est_available = False
for i in matches:
if '$' in text[i:i + 50]:
string = text[i:i + 200]
est_available = True
break
if not est_available: