视频1 视频21 视频41 视频61 视频文章1 视频文章21 视频文章41 视频文章61 推荐1 推荐3 推荐5 推荐7 推荐9 推荐11 推荐13 推荐15 推荐17 推荐19 推荐21 推荐23 推荐25 推荐27 推荐29 推荐31 推荐33 推荐35 推荐37 推荐39 推荐41 推荐43 推荐45 推荐47 推荐49 关键词1 关键词101 关键词201 关键词301 关键词401 关键词501 关键词601 关键词701 关键词801 关键词901 关键词1001 关键词1101 关键词1201 关键词1301 关键词1401 关键词1501 关键词1601 关键词1701 关键词1801 关键词1901 视频扩展1 视频扩展6 视频扩展11 视频扩展16 文章1 文章201 文章401 文章601 文章801 文章1001 资讯1 资讯501 资讯1001 资讯1501 标签1 标签501 标签1001 关键词1 关键词501 关键词1001 关键词1501 专题2001
Python实现批量将word转html并将html内容发布至网站的方法
2020-11-27 14:34:25 责编:小采
文档
 本文实例讲述了Python实现批量将word转html并将html内容发布至网站的方法。分享给大家供大家参考。具体实现方法如下:

#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。

下载本文
显示全文
专题