import glob
from collections import Counter
import re
import xlwt
from xlwt import Workbook
import xlsxwriter
import xlrd
import errno
import time
from datetime import datetime
import datetime
import os
import os.path
import warnings
from xlutils.copy import copy
import openpyxl
from xlrd import open_workbook
warnings.filterwarnings("ignore")
timestr = time.strftime("%Y%m%d-%H%M%S")
yourpath = "D:\\mainfolder\\subfolders"
loc = ("D:\\sample.xlsx")
cnt = Counter()
wb = xlrd.open_workbook(loc)
sheet = wb.sheet_by_index(0)
rows = sheet.nrows
excel_word=[]
for i in range(1,rows):
excel_word.append(sheet.cell_value(i,1))
report_txt="D:\\mainfolder\\report"+timestr+".txt"
FO = open(report_txt, 'w')
str3="|"+"Pattern"+" "*(20-len("Pattern"))+"|"+"Vuernabilitiy in file"+" "*(200-len("Vuernabilitiy in file"))+"|"+"Line No"+" "*(10-len("Line No"))+"|" +"\n"
FO.write(str3)
FO.write("--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------"+"\n")
for root, dirs, files in os.walk(yourpath, topdown=False):
line=0
for name in files:
path=os.path.join(root, name)
files = glob.glob(path)
for name in files:
try:
with open(name,encoding="utf8",errors='ignore') as f:
text_string1 = f.read()
for i in range(0,len(excel_word)):
str2=''
for num, line in enumerate(name, 1):
if excel_word[i] in text_string1:
cnt[excel_word[i]] += 1
str2="|"+excel_word[i]+" "*(20-len(excel_word[i]))+"|"+os.path.join(root, name)+" "*(200-len(os.path.join(root, name)))+"|"+str(num)+" "*(10-len(str(num)))+"|" +"\n"
else:
cnt[excel_word[i]]+=0
FO.write(str2)
except IOError as exc:
if exc.errno != errno.EISDIR:
raise
FO.close()
