python 通过关键字对代码扫描测试，并将扫描的结果放到excel表格中进行呈现

最近在做安全测试时，需要对项目工程类的文件进行检查，所以根据项情况 ，整理代码搜索关键词，并对代码进行搜索，检查是否符合安全要求,并将查询出的结果写入到excel表格中，以方便查看结果。

---

对excle操作之前选用xlwt库进行处理，但有以下xlwt缺点：
版本
只能处理Excel97-2003或Excel 97之前版本的xls格式
存储数据过大
存储数据过大时，会报错Exception: String longer than 32767 characters

---

因查询数据较大，因此使用的是XlsxWrite库进行（ https://github.com/jmcnamara/XlsxWriter ），以此来弥补以上缺点：

代码如下：

# -*- coding: utf-8 -*-

import os

def findAllFiles(path):
    find_files = []
    for root, dirs, files in os.walk(path):   #
        for file in files:
            pathWithFile = os.path.join(root,file)
            if os.path.splitext(pathWithFile)[1] in [".java",".xml",".iml",".bat"]:
                find_files.append(pathWithFile)
            else:
                pass

    return find_files

# read file
def readfile (readfilepath):
    newStr = []

    keywords = ["qq","mail","tel","phone","sex","key","password","passwd",
                "pwd","username","TGC","token","TOKEN","GPS","gps","admin",
                "test","Test","log.","system.println.","SSL","AES","sha1",
                "md5","MD5","Base64","base64","crash","MSG","msg"]

    with open(readfilepath,'r',encoding='utf-8') as f:

        #enumerate与for 联用，多用于计数
        for num,lines in enumerate(f):
            for i in range(len(keywords)):
                if keywords[i] in lines:
                    strName = readfilepath
                    if strName:
                        getLines = lines.strip()
                        strName = readfilepath.strip()
                        newStr.append(strName)
                        newStr.append(num)
                        newStr.append(keywords[i])
                        newStr.append(getLines)

    #return strName,kw,strCon  #默认返回的是tuple,相当于返回类型为：return (strName,newStr)
    return newStr

def perLinesResult(srcFilePath):
    newcontent = []
    needReadFiles = findAllFiles(srcFilePath)

    for i in range(len(needReadFiles)):
        getContent = readfile(needReadFiles[i])  # 对返回的元组值，分别定义参数进行接收，并分别对接收后的值进行处理
        if getContent: #判断getContent如果存在值，则为真
            newcontent.extend(getContent)
    return newcontent


import xlsxwriter

def write_excel(code_path,result_path):
    workbook = xlsxwriter.Workbook(result_path)
    worksheet = workbook.add_worksheet("test")

    #表头样式
    formatHeader = workbook.add_format({
        'bold': True,  # 字体加粗
        'border': 1,  # 单元格边框宽度
        'align': 'center',
        'valign': 'vcenter',
        'fg_color': '#F4B084',
    })

    #单元格样式
    wsformat = workbook.add_format({
        "font_size":10,
        "top":1,
        "left":1,
        "right":1,
        "bottom":1,
    })

    worheader = [u"文件路径",u"行号",u"关键词", u"查询的内容"]
    for i in range(len(worheader)):
        worksheet.write(0,i,worheader[i],formatHeader)
    content = perLinesResult(code_path)
    column = 0
    row = 1
    for j in range(len(content)):
        worksheet.write(row,column,content[j],wsformat)
        column = column + 1
        if column % 4 == 0:
            row = row + 1
            column = 0
    workbook.close()


if __name__ == '__main__':
    #src_File_Path = "D:/Code/iOS/IOS"
    Code_src_File_Path = "D:/Code/Android"
    result_file_path = "F:/Leanring_Files/xxx.xlsx"
    write_excel(Code_src_File_Path,result_file_path)