python - 使用 Python2 合并 CSV 行并保留单个任意列中的数据

Question

我知道关于这个主题有很多问题，但答案并没有得到很好的解释，因此很难适应我的用例。一个here看起来很有前途，但语法相当复杂，我很难理解和适应它。

我需要将 Nessus 的原始 CSV 输出转换为标准格式，这实际上会转储许多列，仅保留每个发现的严重性、IP 地址和输出。我已经将一个脚本放在一起，但如果发现的结果位于多个主机/端口上，则每个主机/端口都有不同的行。

我需要的是根据漏洞名称合并行，但只保留 IP 地址数据。

示例输入 - 为方便起见而缩短

High,10.10.10.10,MS12-345(this is the name),Hackers can do bad things
High,10.10.10.11,MS12-345(this is the name),Hackers can do bad things

示例输出

High,10.10.10.10 10.10.10.11,MS12-345(this is the name),Hackers can do bad things

下面是到目前为止我的脚本。如果您使您的答案能够轻松适应(阅读:防白痴)以供 future 的读者使用，我将不胜感激，我相信他们也会的。

奖金:

有时，具有相同名称的结果的输出字段会有所不同，有时则相同。如果您有时间，为什么不帮助一个人检查这一点，并在输出中存在差异时以与 IP 地址相同的方式进行附加？

import sys
import csv

def manipulate(inFile):

    with open(inFile, 'rb') as csvFile:
        fileReader = csv.reader(csvFile, dialect='excel')

        # Check for multiple instances of findings and merge the rows
        # This happens when the finding is on multiple hosts/ports

        //YOUR CODE WILL GO HERE (Probably...)

        # Place findings into lists: crits, highs, meds, lows for sorting later
        crits = []
        highs = []
        meds = []
        lows = []

        for row in fileReader:

            if row[3] == "Critical":    
                crits.append(row)
            elif row[3] == "High":
                highs.append(row)
            elif row[3] == "Medium":
                meds.append(row)
            elif row[3] == "Low":
                lows.append(row)

        # Open an output file for writing
        with open('output.csv', 'wb') as outFile: 
            fileWriter = csv.writer(outFile)

            # Add in findings from lists in order of severity. Only relevant columns included
            for c in crits:
                fileWriter.writerow( (c[3], c[4], c[7], c[12]) )

            for h in highs:
                fileWriter.writerow( (h[3], h[4], h[7], h[12]) )

            for m in meds:
                fileWriter.writerow( (m[3], m[4], m[7], m[12]) )

            for l in lows:
                fileWriter.writerow( (l[3], l[4], l[7], l[12]) )


# Input validation
if len(sys.argv) != 2:
    print 'You must provide a csv file to process'
    raw_input('Example: python nesscsv.py foo.csv')
else:
    print "Working..."
    # Store filename for use in manipulate function
    inFile = str(sys.argv[1])
    # Call manipulate function passing csv
    manipulate(inFile)

print "Done!"   
raw_input("Output in output.csv. Hit return to finish.")

Answer 1

以下解决方案使用 OrderedDict 以保留行顺序的方式收集行，同时还允许按漏洞名称查找任何行。

import sys
import csv
from collections import OrderedDict

def manipulate(inFile):

    with open(inFile, 'rb') as csvFile:
        fileReader = csv.reader(csvFile, dialect='excel')

        # Check for multiple instances of findings and merge the rows
        # This happens when the finding is on multiple hosts/ports

        # Dictionary mapping vulns to merged rows.
        # It's ordered to preserve the order of rows.
        mergedRows = OrderedDict()

        for newRow in fileReader:
            vuln = newRow[7]
            if vuln not in mergedRows:
                # Convert the host and output fields into lists so we can easily
                # append values from rows that get merged with this one.
                newRow[4] = [newRow[4], ]
                newRow[12] = [newRow[12], ]
                # Add row for new vuln to dict.
                mergedRows[vuln] = newRow
            else:
                # Look up existing row for merging.
                mergedRow = mergedRows[vuln]
                # Append values of host and output fields, if they're new.
                if newRow[4] not in mergedRow[4]:
                    mergedRow[4].append(newRow[4])
                if newRow[12] not in mergedRow[12]:
                    mergedRow[12].append(newRow[12])

        # Flatten the lists of host and output field values into strings.
        for row in mergedRows.values():
            row[4] = ' '.join(row[4])
            row[12] = ' // '.join(row[12])

        # Place findings into lists: crits, highs, meds, lows for sorting later
        crits = []
        highs = []
        meds = []
        lows = []

        for row in mergedRows.values():

            if row[3] == "Critical":
                crits.append(row)
            elif row[3] == "High":
                highs.append(row)
            elif row[3] == "Medium":
                meds.append(row)
            elif row[3] == "Low":
                lows.append(row)

        # Open an output file for writing
        with open('output.csv', 'wb') as outFile:
            fileWriter = csv.writer(outFile)

            # Add in findings from lists in order of severity. Only relevant columns included
            for c in crits:
                fileWriter.writerow( (c[3], c[4], c[7], c[12]) )

            for h in highs:
                fileWriter.writerow( (h[3], h[4], h[7], h[12]) )

            for m in meds:
                fileWriter.writerow( (m[3], m[4], m[7], m[12]) )

            for l in lows:
                fileWriter.writerow( (l[3], l[4], l[7], l[12]) )


# Input validation
if len(sys.argv) != 2:
    print 'You must provide a csv file to process'
    raw_input('Example: python nesscsv.py foo.csv')
else:
    print "Working..."
    # Store filename for use in manipulate function
    inFile = str(sys.argv[1])
    # Call manipulate function passing csv
    manipulate(inFile)

print("Done!")
raw_input("Output in output.csv. Hit return to finish.")