def extractHtmlFile(htmlFilePath):

''' Extracthtmltextandsavetotextfile.

'''

htmlData = file(htmlFilePath, ' r ' ).read()

import win32com.client

html = win32com.client.Dispatch( ' htmlfile ' )

html.writeln(htmlData)

text = html.body.innerText.encode( ' gbk ' , ' ignore ' )

...

# !/usr/bin/envpython

import sys,os,re,codecs

import time

import win32com.client

class htmlfile:

def __init__ (self):

self. __ie = win32com.client.Dispatch( ' InternetExplorer.Application ' )

self. __ie .Silent = True

self. __filename = ''

self. __document = None

def __del__ (self):

self. __ie .Quit()

def __getdocument (self,filename):

filename = os.path.abspath(filename)

if self. __filename != filename:

self. __filename = filename

self. __ie .Navigate2(filename)

self. __ie .Document.close()

while self. __ie .Document.Body is None:

time.sleep( 0.1 )

self. __document = self. __ie .Document

return self. __document

def gettext(self,filename):

return self. __getdocument (filename).Body.innerText

def gettitle(self,filename):

return self. __getdocument (filename).title

def formattextpath(dir,htmlfile,htmltitle):

''' Formatthetextfilepathandreturn.

'''

fname = htmltitle[: 6 ]

fname = re.sub(r ' (/|/|:|*|?|<|>|||") ' , ' - ' ,fname)

fname = fname + ' _ ' + os.path.splitext(htmlfile)[0] + ' .txt '

return os.path.join(root,fname)

if __name__ == ' __main__ ' :

hf = htmlfile()

for root,dirs,names in os.walk(u ' . ' ):

for name in names:

if name.endswith( ' htm ' ) or name.endswith( ' html ' ):

htmlpath = os.path.join(root,name)

textpath = formattextpath(root,name,hf.gettitle(htmlpath))

print htmlpath, ' -> ' ,textpath

file(textpath, ' wb ' ).write(hf.gettext(htmlpath).encode( ' mbcs ' ))

# Endofif.

# Endofforname.

# Endofforroot.

del hf

# Endofif.