Question

我创建了这段代码，以扫描samples_vsdt.txt以获得一定的值，然后将其写入csv，我遇到了错误StopIteration，甚至没有读取文本文件。我试图解决这个问题数小时，不知道是什么原因引起的？

这是我的代码的工作方式，例如以下行：

Scanning samples_extracted\82e5b144cb5f1c10629e72fc1291f535db7b0b40->(Word 2003 XML Document 1003-1)

将以这种方式写入csv：

82e5b144cb5f1c10629e72fc1291f535db7b0b40,Word 2003 XML Document 1003-1

这是我的代码，它适用于我所有的txt_files，但是此sample_vsdt.txt无法正常工作

import csv,re
out_vsdt            = "samples_vsdt.txt"
out_sha1_vsdt       = "sha1_vsdt.csv"

def read_text_file(out_vsdt):

    with open(out_vsdt) as f:
        data  = []
        for line in f:
            if "Scanning " + new  in line and "(" in line:

                try:
                    sha = re.search('\\\(.*)->', line).group(1)
                    desc= re.search('->\((.*)\)', line).group(1)
                except AttributeError:
                    desc = None
                    sha = None
                mix = sha,desc
                data.append(mix)

                continue
            if "Scanning " + new in line:
                try:
                    sha= re.search('\\\(.*)$', line).group(1)
                    while True:
                        i = next(f)
                        if "(" in i:
                            try:
                                desc = re.search('->\((.*)\)', i).group(1)
                                break
                            except AttributeError:
                                desc = None
                                sha = None
                    mix = sha,desc
                    data.append(mix)
                except AttributeError:
                    sha = None
    return data

def write_csv_file(data,out_sha1_vsdt):
    with open(out_sha1_vsdt, 'wb') as csvfile:
        csvwriter = csv.writer(csvfile, delimiter=',', quotechar='"')
        csvwriter.writerow(['SHA-1','VSDT','DESC'])
        for row in data:

            csvwriter.writerow(row)

def main():
    data = read_text_file(out_vsdt)
    write_csv_file(data, out_sha1_vsdt)

if __name__ == '__main__':
    main()

print "Parsing Successful"

给我错误：

Traceback (most recent call last):
  File "C:\Users\trendMICRO\Desktop\ojt\scanner\parser.py", line 65, in <module>
    main()
  File "C:\Users\trendMICRO\Desktop\ojt\scanner\parser.py", line 61, in main
    data = read_text_file(out_vsdt)
  File "C:\Users\trendMICRO\Desktop\ojt\scanner\parser.py", line 37, in read_text_file
    i = next(f)
StopIteration

Answer 1

另一种方法可能是仅使用正则表达式提取整个块：

import csv
import re

out_vsdt = "samples_vsdt.txt"
out_sha1_vsdt = "sha1_vsdt.csv"

with open(out_vsdt) as f_input:
    vscan32 = f_input.read()

with open(out_sha1_vsdt, 'w', newline='') as f_output:
    csv_output = csv.writer(f_output)
    csv_output.writerow(['SHA-1', 'VSDT', 'DESC'])

    for sha, desc, vsdt in re.findall(r'Scanning.*?\\([0-9a-f]+)(.*?)->\((.*?)\)$', vscan32, re.S + re.M):
        desc = '|'.join(line.strip() for line in desc.splitlines() if len(line.strip()))
        desc = ''.join(filter(lambda x: x in string.printable, desc))    # remove non-printable characters
        csv_output.writerow([sha, vsdt, desc])

这使用多行表达式来查找以Scanning开头的块。如果有多行，则使用|将这些行剥离并连接在一起。最后，所有不可打印的字符将从说明中删除。

这将为您提供类似以下内容的输出：

SHA-1,VSDT,DESC
004d44eeecae27314f8bd3825eb82d2f40182b51,WIN32 EXE 7-2,
07eab9ea58d4669febf001d52c5182ecf579c407,WIN32 EXE 7-2,
0d558bb5e0a5b544621af0ffde1940615ac39deb,WIN32 EXE 7-2,
5172c70c1977bbddc2a163f6ede46595109c7835,WIN32 EXE 7-2,- $R0\NsCpuCNMiner32.exe->Found Virus [WORM_CO.331300D2]|- $R0\NsCpuCNMiner64.exe->Found Virus [WORM_CO.331300D2]|- $R0\NsGpuCNMiner.exe->Found Virus [TROJ64_.743CC567]

这假设您使用的是Python 3.x

在使用next（）

1 个答案: