python 检索文件内容工具

公司内部需求一个工具检索目录下的文件在另外的目录中使用次数， 用来优化包体的大小。

此代码效率并不高效， 另添加对应的 后缀检索。 用python 实现比较快速， 另还有缺点是只支持 utf-8 格式内容。

各位用到的可以自己摘一下。

（本人习惯使用cc++，目前发现这种脚本类的确实实现方便，接口齐全， 我能想到的接口， 真的全都有， 用python 写工具， 应该是一个调试起来还可以的过程）

代码如下：

#coding=utf-8

import os
import sys
import time

#private:
def checkSuffix(strFileName, strCompareSuffix):
    strPreFileName = ''
    strFileSuffix = ''
    bIsCheckOk = False
    strArray = strFileName.split('.')
    if len(strArray) > 1:
        strPreFileName = strArray[0]
        strFileSuffix = strArray[1]
    #print(strFileSuffix)
    #print(strCompareSuffix)
    if strCompareSuffix == '*' or strFileSuffix == strCompareSuffix:
        bIsCheckOk = True
    return bIsCheckOk, strPreFileName

def readFileName(file_dir):
    for root, dirs, files in os.walk(file_dir):
        return files,dirs, root
    return '', '', ''

def findString(pathFile, findKey):
    #print("open pathFile:", pathFile)
    fp = open(pathFile, "r", encoding='utf-8')
    strr = fp.read()
    if(strr.find(findKey) != -1):
        return True
    return False

def startFind(files, dirs, root, findKey, strSuffix):
    for fileName in files:
        try:
            bIsCheckOk, strPreFileName = checkSuffix(fileName, strSuffix)
            if bIsCheckOk == False:
                #print("fileName", fileName, " is not suffx :", strSuffix)
                continue
            if(findString(root + "\" + fileName, findKey)):
                return True, fileName
        except Exception as err:
            continue

    for jj in dirs:
        fi, di, ro = readFileName(root + jj)
        bIsFind, fileName = startFind(fi, di, ro, findKey, strSuffix)
        if(bIsFind == True):
            return bIsFind, fileName
    return False, ''

#public:
def findUse(dirPath, findKey, strSuffix):
    files, dirs, root = readFileName(dirPath)
    return startFind(files, dirs, root, findKey, strSuffix)

def getDirsFiles(dirPath):
    dirfiles = [];
    for root, dirs, files in os.walk(dirPath):
        dirfiles += files;
    return dirfiles

def writeResult(strFileName, strWriteSign, list):
    fp = open(strFileName, 'a+')
    fp.write(strWriteSign)
    #fp.writelines(list)
    for str in list:
        fp.write(str)
        fp.write('
')
    fp.close()

if __name__ == '__main__':
    """
    findDir = u"E:\mmo2018001\artist\open\ui\free\"
    findAimDir = u"E:\mmo2018001\artist\open\effect\"
    findsuffix = "prefab" # 哪些要搜索的文件的后缀
    findAimsuffix = "*" # 搜索那些后缀的文件
    """
    bt = time.clock() # 记录时间

    findDir = sys.argv[1]
    findAimDir = sys.argv[2]
    findsuffix = sys.argv[3]
    findAimsuffix = sys.argv[4]

    thisPath = os.getcwd()
    print("this path is ", thisPath)
    print(findDir)
    print(findAimDir)
    print(findsuffix)
    print(findAimsuffix)

    dirFiles = getDirsFiles(findAimDir)
    useFiles = []
    notUseFiles = []
    nLen = len(dirFiles)
    i = 0
    for filesName in dirFiles :

        bIsCheckOk, strPreFileName = checkSuffix(filesName, findsuffix)
        if bIsCheckOk == True:
            isFind, fileName = findUse(findDir, strPreFileName, findAimsuffix)
            #print("filesName:	", filesName, " 
IsFind:		", isFind)
            if(isFind):
                useFiles.append(filesName)
            else:
                notUseFiles.append(filesName)
        i += 1
        p = round(i * 100 / nLen)
        duration = round(time.clock() - bt, 2)
        remaining = round(duration * 100 / (0.01 + p) - duration, 2)
        print("进度:{0}%，已耗时:{1}s，预计剩余时间:{2}s".format(p, duration, remaining), end="
")

    writePath = thisPath + "\Result.txt"
    try:
        os.remove(writePath)
    except Exception as err:
        print(err)
    writeResult(writePath, "***************NotUseFiles:***************
", notUseFiles)
    writeResult(writePath, "***************UseFiles:***************
", useFiles)
    useTime = time.clock() - bt
    print("已完成 总耗时：", useTime)