基于Python的网页文档处理脚本实现

#/usr/bin/python
import os
import binascii
import shutil 
from functools import partial

def FileReduce(inpath, outpath):
        infp = open(inpath, "r", encoding="utf-8")
        outfp = open(outpath, "w", encoding="utf-8")
        print(outpath+" 压缩成功")
        for li in infp.readlines():
            if li.split():
                li = li.replace(‘\n‘, ‘‘).replace(‘\t‘, ‘‘);
                li = ‘ ‘.join(li.split())
                outfp.writelines(li)
        infp.close()
        outfp.close()

#shell命令行调用(用ugllifyjs2来压缩js文件)
def ShellReduce(inpath, outpath):
    Command = "uglifyjs "+inpath+" -m -o "+outpath
    print(Command)
    os.system(Command)

#将文件以二进制读取, 并转化成数组保存
def filehex(inpath, outpath):
    i = 0
    count = 0
    a = ‘‘
    inf = open(inpath, ‘rb‘);
    outf = open(outpath, ‘w‘)
    records = iter(partial(inf.read,1), b‘‘)
    print(outpath + " 转换成数组成功")
    for r in records:
        r_int = int.from_bytes(r, byteorder=‘big‘)  
        a +=  hex(r_int) + ‘, ‘
        i += 1
        count += 1
        if i == 16:             
            a += ‘\n‘
            i = 0
    a = "const static char " + outpath.split(‘.‘)[0].split(‘/‘)[-1] + "["+ str(count) +"]={\n" + a + "\n}\n\n" 
    outf.write(a)
    inf.close()
    outf.close()

#创建一个新文件夹
def mkdir(path):
    path=path.strip()
    isExists=os.path.exists(path)
 
    #判断文件夹是否存在，不存在则创建
    if not isExists:
        print(path+‘ 创建成功‘)
        os.makedirs(path)
    else:
        pass
    return path

#删除一个文件夹(包含内部所有文件)
def deldir(path):
    path = path.strip()

    isExists=os.path.exists(path)
 
    #判断文件夹是否存在，存在则删除
    if isExists:
        print(path + "删除成功")
        shutil.rmtree(path)
    else:
        pass


def WebProcess(path):
        #原网页 ..\basic\  
        #压缩网页 ..\reduce\
        #编译完成.c网页 ..\programe
        BasicPath = path + "\\basic"
        ProgramPath = path + "\\program"
        ReducePath = path + "\\reduce"
        
        #删除原文件夹，再创建新文件夹
        deldir(ProgramPath)
        deldir(ReducePath)
        mkdir(ProgramPath)
        for root, dirs, files in os.walk(BasicPath):
                for item in files:
                        ext = item.split(‘.‘)
                        InFilePath = root + "/" + item
                        OutReducePath = mkdir(root.replace("basic", "reduce")) + "/" + item
                        OutProgramPath = ProgramPath + "/" + item.replace(‘.‘, ‘_‘) + ‘.c‘
                        
                        #根据后缀不同进行相应处理
                        #html/css 去除‘\n‘,‘\t‘, 空格字符保留1个
                        #js 调用uglifyjs2进行压缩
                        #gif jpg ico 直接拷贝 
                        #其它 直接拷贝
                        #除其它外，剩余文件同时转化成16进制数组, 保存为.c文件
                        if ext[-1] in ["html", "css"]:
                            FileReduce(InFilePath, OutReducePath)
                            filehex(OutReducePath, OutProgramPath)
                        elif ext[-1] in ["js"]:
                            ShellReduce(InFilePath, OutReducePath)
                            filehex(OutReducePath, OutProgramPath)
                        elif ext[-1] in ["gif", "jpg", "ico"]:
                            shutil.copy(InFilePath, OutReducePath)
                            filehex(OutReducePath, OutProgramPath)
                        else:
                            shutil.copy(InFilePath, OutReducePath)

#获得当前路径
path = os.path.split(os.path.realpath(__file__))[0];
WebProcess(path)

#/usr/bin/python
import os

total_count = 0; 
empty_count = 0;

def CountLine(path):
        global total_count
        global empty_count
        tempfile = open(path)
        for lines in tempfile:
                total_count += 1
                if len(lines.strip()) == 0:
                       empty_count += 1
 
def TotalLine(path):
        for root, dirs, files in os.walk(path):
                for item in files:
                        ext = item.split(‘.‘)
                        ext = ext[-1]  
                        if(ext in ["cpp", "c", "h", "java", "php"]):
                                subpath = root + "/" + item
                                CountLine(subpath)

path = os.path.split(os.path.realpath(__file__))[0];
TotalLine(path)
print("Input Path:", path)
print("total lines: ",total_count)
print("empty lines: ",empty_count)
print("code lines: ", (total_count-empty_count))