[python]word转pdf、doc转docx、word转html

python Word文件转换为pdf文件（doc/docx文件转化为pdf文件）

# -*- encoding: utf-8 -*-
import  os
from win32com import client
#pip instatll win32com
def doc2pdf(doc_name, pdf_name):
    """
    :word文件转pdf
    :param doc_name word文件名称
    :param pdf_name 转换后pdf文件名称
    """
    try:
        word = client.DispatchEx("Word.Application")
        if os.path.exists(pdf_name):
            os.remove(pdf_name)
        worddoc = word.Documents.Open(doc_name,ReadOnly = 1)
        worddoc.SaveAs(pdf_name, FileFormat = 17)
        worddoc.Close()
        return pdf_name
    except:
        return 1
if __name__=='__main__':
    doc_name = "f:/test.doc"
    ftp_name = "f:/test.pdf"
    doc2pdf(doc_name, ftp_name)

python doc转docx

from win32com import client
def doc2docx(doc_name,docx_name):
    """
    :doc转docx
    """
    try:
        # 首先将doc转换成docx
        word = client.Dispatch("Word.Application")
        doc = word.Documents.Open(doc_name)
        #使用参数16表示将doc转换成docx
        doc.SaveAs(docx_name,16)
        doc.Close()
        word.Quit()
    except:
        pass
if __name__ == '__main__':
    doc2docx(f:test.doc','f:/test.docx')

python docx转html

#coding:utf-8
import docx
from docx2html import convert
import HTMLParser
def  docx2html(docx_name,new_name):
    """
    :docx转html
    """
    try:
        #读取word内容
        doc = docx.Document(docx_name,new_name)
        data = doc.paragraphs[0].text
        # 转换成html
        html_parser = HTMLParser.HTMLParser()
        #使用docx2html模块将docx文件转成html串，随后你想干吗都行
        html = convert(new_name)
        #docx2html模块将中文进行了转义，须要将生成的字符串从新转义
        return html_parser.enescape(html)
    except:
        pass
if __name__ == '__main__':
    docx2html('f:/test.docx','f:/test1.docx')