text 섹션 ngram 추출 코드 작업 중 ...

import pefile
import re
import numpy as np
import pickle
def main():
    f = re.compile(pattern=".text")
    targetPath = "C:/Users/sleep/Desktop/driver/chromedriver.exe"
    pe_data = pefile.PE(targetPath)
    tmp    = []
    n_gram = []
    with open(targetPath, 'rb') as binary_file:
        for sec in pe_data.sections:
            # .text section 만 추출하겠습니다. !!!
            if f.search(sec.Name.decode('utf-8')):
                ptrRaw, sizeRaw, sizeEnd = \
                    sec.PointerToRawData//0x40, (sec.SizeOfRawData-16)//0x40, (sec.SizeOfRawData-16)%0x40
                print ("ptrRaw  => {}, "
                       "sizeRaw => {}, "
                       "sizeEnd => {}  ".format(ptrRaw, sizeRaw, sizeEnd))
                for i in range(65):
                    s = binary_file.read(0x10)
                tmp.extend([ hex(i) for i in s[:]])
                #     print ("{0:02x}".format(i), end= " ")
                # print ("\n")
                #
                for i in range(sizeRaw):
                    s = binary_file.read(0x10)
                    tmp.extend([hex(i) for i in s[:]])
                for i in range(1, len(tmp)-5):
                    n_gram.append(tmp[i:i+4])

                #     for i in s[:]:
                #         print("{0:02x}".format(i), end=" ")
                #     print ("\n")

                # indx = 1
                # for i in range(0, len(text_section[0]), 0x10):
                #     print ("{0:x} => ".format(indx), end=" ")
                #     for k in text_section[0][i:i+0xf]:
                #         print ("{0:02x}".format(k), end=" ")
                #     print ('\n')
                #     indx += 1
    print (n_gram)
if __name__ == "__main__":
    main()