python html转word_Python实现批量将word转html并将html内容发布至网站的方法

#coding=utf-8

__author__ = 'zhm'

from win32com import client as wc

import os

import time

import random

import MySQLdb

import re

def wordsToHtml(dir):

#批量把文件夹的word文档转换成html文件

#金山WPS调用，抢先版的用KWPS，正式版WPS

word = wc.Dispatch('KWPS.Application')

for path, subdirs, files in os.walk(dir):

for wordFile in files:

wordFullName = os.path.join(path, wordFile)

#print "word:" + wordFullName

doc = word.Documents.Open(wordFullName)

wordFile2 = unicode(wordFile, "gbk")

dotIndex = wordFile2.rfind(".")

if(dotIndex == -1):

print '********************ERROR: 未取得后缀名！'

fileSuffix = wordFile2[(dotIndex + 1) : ]

if(fileSuffix == "doc" or fileSuffix == "docx"):

fileName = wordFile2[ : dotIndex]

htmlName = fileName + ".html"

htmlFullName = os.path.join(unicode(path, "gbk"), htmlName)

# htmlFullName = unicode(path, "gbk") + "\\" + htmlName

print u'生成了html文件：' + htmlFullName

doc.SaveAs(htmlFullName, 8)

doc.Close()

word.Quit()

print ""

print "Finished!"

def html_add_to_db(dir):

#将转换成功的html文件批量插入数据库中。

conn = MySQLdb.connect(

host='localhost',

port=3306,

user='root',

passwd='root',

db='test',

charset='utf8'

)

cur = conn.cursor()

for path, subdirs, files in os.walk(dir):

for htmlFile in files:

htmlFullName = os.path.join(path, htmlFile)

title = os.path.splitext(htmlFile)[0]

targetDir = 'D:/files/htmls/'

#D:/files为web服务器配置的静态目录

sconds = time.time()

msconds = sconds * 1000

targetFile = os.path.join(targetDir, str(int(msconds))+str(random.randint(100, 10000)) +'.html')

htmlFile2 = unicode(htmlFile, "gbk")

dotIndex = htmlFile2.rfind(".")

if(dotIndex == -1):

print '********************ERROR: 未取得后缀名！'

fileSuffix = htmlFile2[(dotIndex + 1) : ]

if(fileSuffix == "htm" or fileSuffix == "html"):

if not os.path.exists(targetDir):

os.makedirs(targetDir)

htmlFullName = os.path.join(unicode(path, "gbk"), htmlFullName)

htFile = open(htmlFullName,'rb')

#获取网页内容

htmStrCotent = htFile.read()

#找出里面的图片

img=re.compile(r"""

""",re.I)

m = img.findall(htmStrCotent)

for tagContent in m:

imgSrc = unicode(tagContent, "gbk")

imgSrcFullName = os.path.join(path, imgSrc)

#上传图片

imgTarget = 'D:/files/images/whzx/'

img_sconds = time.time()

img_msconds = sconds * 1000

targetImgFile = os.path.join(imgTarget, str(int(img_msconds))+str(random.randint(100, 10000)) +'.png')

if not os.path.exists(imgTarget):

os.makedirs(imgTarget)

if not os.path.exists(targetImgFile) or(os.path.exists(targetImgFile) and (os.path.getsize(targetImgFile) != os.path.getsize(imgSrcFullName))):

tmpImgFile = open(imgSrcFullName,'rb')

tmpWriteImgFile = open(targetImgFile, "wb")

tmpWriteImgFile.write(tmpImgFile.read())

tmpImgFile.close()

tmpWriteImgFile.close()

htmStrCotent=htmStrCotent.replace(tagContent,targetImgFile.split(":")[1])

if not os.path.exists(targetFile) or(os.path.exists(targetFile) and (os.path.getsize(targetFile) != os.path.getsize(htmlFullName))):

#用iframe包装转换好的html文件。

iframeHtml='''

希望本文所述对大家的Python程序设计有所帮助。

本条技术文章来源于互联网，如果无意侵犯您的权益请点击此处反馈版权投诉

本文系统来源：php中文网