Python编写简单的HTML页面合并脚本

import codecs
import webbrowser
import sys

charset = "utf-8" #文件编码

#读取text里的<include>标签及src属性中的文件，替换原标签
def replaceInclude (filename,text):
 try:
  posA = text.find("<include")
  while posA!= -1:
   posC = text.find(">",posA)
   tag = text[posA:posC+1]
   posA = text.find("src=",posA)
   posA += 5
   posB = text.find("\"",posA)
   file = text[posA:posB]#获取src中的文件名
   print ("正在处理:",file)
   tmpFile = codecs.open(file,"r",charset)
   tmpText = tmpFile.read()
   tmpText = replaceInclude(file,tmpText)#递归处理文件嵌套后的include标签
   text = text.replace(tag,tmpText)
   tmpFile.close()
   posA = text.find("<include")
  return text;
 except Exception as e:
  print ("错误:文件",filename,"中的",file,"处理失败！错误信息：\n",e)
  sys.exit(1)
   

readFile = codecs.open("index.html","r",charset)
writeFile = codecs.open("newhtml.html","w",charset)
try:
 text = readFile.read()
 text = replaceInclude("index.html",text)
 writeFile.write(text)
 webbrowser.open("newhtml.html")
finally:
 readFile.close()
 writeFile.close()</pre>