使用Python网页文档处理脚本实例代码
程序员文章站
2022-05-24 14:44:44
...
嵌入式web服务器不同于传统服务器,web需要转换成数组格式保存在flash中,才方便lwip网络接口的调用,最近因为业务需求,需要频繁修改网页,每次的压缩和转换就是个很繁琐的过程,因此我就有了利用所掌握的知识,利用python编写个能够批量处理网页文件,压缩并转换成数组的脚本。
脚本运行背景(后续版本兼容):
Python 3.5.1(下载、安装、配置请参考网上教程)
node.js v4.4.7, 安装uglifyjs管理包,支持js文件非文本压缩
uglifyjs 用来压缩JS文件的引擎
具体实现代码如下:
#/usr/bin/python import os import binascii import shutil from functools import partial import re import gzip #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: os.makedirs(path) print(path+' 创建成功') 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: shutil.rmtree(path) print(path + "删除成功") else: pass #网页一次压缩文件 def FileReduce(inpath, outpath): infp = open(inpath, "r", encoding="utf-8") outfp = open(outpath, "w", encoding="utf-8") for li in infp.readlines(): if li.split(): #去除多余的\r \n li = li.replace('\n', '').replace('\t', ''); #空格只保留一个 li = ' '.join(li.split()) outfp.writelines(li) infp.close() outfp.close() print(outpath+" 压缩成功") #shell命令行调用(用ugllifyjs来压缩js文件) def ShellReduce(inpath, outpath): Command = "uglifyjs "+inpath+" -m -o "+outpath print(Command) os.system(Command) #gzip压缩模块 def FileGzip(inpath, outpath): with open(inpath, 'rb') as plain_file: with gzip.open(outpath, 'wb') as zip_file: zip_file.writelines(plain_file) print(outpath+" gzip-压缩成功") #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'') for r in records: r_int = int.from_bytes(r, byteorder='big') a += strzfill(hex(r_int), 2, 2) + ', ' i += 1 count += 1 if i == 16: a += '\n' i = 0 a = "const static char " + outpath.split('.')[-2].split('/')[-1] + "["+ str(count) +"]={\n" + a + "\n}\n\n" outf.write(a) inf.close() outf.close() print(outpath + " 转换成数组成功") #在指定位置填充0 def strzfill(istr, index, n): return istr[:index] + istr[index:].zfill(n) #去css注释 /*.....*/ def unCommentReduce(inpath, outpath): infp = open(inpath, "r", encoding="utf-8") outfp = open(outpath, "w", encoding="utf-8") fileByte = infp.read(); replace_reg = re.compile('/\*[\s\S]*?\*/') fileByte = replace_reg.sub('', fileByte) fileByte = fileByte.replace('\n', '').replace('\t', ''); fileByte = ' '.join(fileByte.split()) outfp.write(fileByte) infp.close() outfp.close() print(outpath+"去注释 压缩成功!") #程序处理主函数 def WebProcess(path): #原网页 ..\basic\ #压缩网页 ..\reduce\ #gzip二次压缩 ..\gzip #编译完成.c网页 ..\programe BasicPath = path + "\\basic" ReducePath = path + "\\reduce" GzipPath = path + "\\gzip" ProgramPath = path + "\\program" #删除原文件夹,再创建新文件夹 deldir(ProgramPath) deldir(ReducePath) deldir(GzipPath) 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 OutGzipPath = mkdir(root.replace("basic", "gzip")) + "/" + item + '.gz' OutProgramPath = ProgramPath + "/" + item.replace('.', '_') + '.c' #根据后缀不同进行相应处理 #html 去除'\n','\t', 空格字符保留1个 #css 去除\*......*\注释数据、'\n'和'\t', 同时空格字符保留1个 #js 调用uglifyjs2进行压缩 #gif jpg ico 直接拷贝 #其它 直接拷贝 #上述执行完毕后压缩成.gz文件 #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] == 'html': FileReduce(InFilePath, OutReducePath) FileGzip(OutReducePath, OutGzipPath) FileHex(OutGzipPath, OutProgramPath) elif ext[-1] == 'css': unCommentReduce(InFilePath, OutReducePath) FileGzip(OutReducePath, OutGzipPath) FileHex(OutGzipPath, OutProgramPath) elif ext[-1] == 'js': ShellReduce(InFilePath, OutReducePath) FileGzip(OutReducePath, OutGzipPath) FileHex(OutGzipPath, OutProgramPath) elif ext[-1] in ["gif", "jpg", "ico"]: shutil.copy(InFilePath, OutReducePath) FileGzip(OutReducePath, OutGzipPath) FileHex(OutGzipPath, OutProgramPath) else: shutil.copy(InFilePath, OutReducePath) #获得当前路径 path = os.path.split(os.path.realpath(__file__))[0]; WebProcess(path)
上述实现的原理主要包含:
1.遍历待处理文件夹(路径为..\basic,需要用户创建,并将处理文件复制到其中,并将脚本放置到该文件夹上一层)--WebProcess
2.创建压缩页面文件夹(..\reduce, 用于存储压缩后文件), 由脚本完成,处理动作:
htm: 删除文本中的多余空格,换行符
css: 删除文本中的多余空格,换行符及注释文件/*......*/
js:调用uglifyjs进行压缩处理
gif, jpg, ico和其它: 直接进行复制处理
3.创建gzip文件处理文件夹(..\gzip, 用于保存二次压缩后文件), 由脚本调用gzip模块完成。
4.创建处理页面文件夹(..\program, 用于存储压缩后文件), 由脚本完成,处理动作:
在文件夹下(shift+鼠标右键)启用windows命令行,并输入python web.py, 就可以通过循环重复这三个过程就可以完成所有文件的处理。
特别注意:所有处理的文件需要以utf-8格式存储,否则读取时会报"gbk"读取错误。
实现效果如下图
html文件:
转换数组:
另外附送一个小的脚本,查询当前目录及子文件夹下选定代码行数和空行数(算是写这个脚本测试时衍生出来的):
#/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))
以上就是使用Python网页文档处理脚本实例代码的详细内容,更多请关注其它相关文章!