基于openOffice和python实现office转pdf和html示例代码

Posted reg183

tags:

篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了基于openOffice和python实现office转pdf和html示例代码相关的知识，希望对你有一定的参考价值。


将office文件转化为html格式或者pdf格式

在转换之前，需要启动openOffice的服务：在openOffice目录下的命令窗口中执行soffice -headless -accept=”socket,host=127.0.0.1,port=8100;urp;” -nofirststartwizard即可启动
不知道如何启动的参照我的​​​另外一篇文章​​

我电脑上安装的是python3.8

基于openOffice和python实现office转pdf和html示例代码_前端


python的安装，在这里我就不多说了，在坐的老司机应该都熟悉了。

准备好了环境之后，话不多说，开始编写脚本。
脚本代码如下：

#
# PyODConverter (Python OpenDocument Converter) v1.1 - 2009-11-14
#
# This script converts a document from one office format to another by
# connecting to an OpenOffice.org instance via Python-UNO bridge.
#
# Copyright (C) 2008-2009 Mirko Nasato <mirko@artofsolving.com>
# Licensed under the GNU LGPL v2.1 - http://www.gnu.org/licenses/lgpl-2.1.html
# - or any later version.
#
DEFAULT_OPENOFFICE_PORT = 8100

import uno
from os.path import abspath, isfile, splitext
from com.sun.star.beans import PropertyValue
from com.sun.star.task import ErrorCodeIOException
from com.sun.star.connection import NoConnectException

FAMILY_TEXT = "Text"
FAMILY_WEB = "Web"
FAMILY_SPREADSHEET = "Spreadsheet"
FAMILY_PRESENTATION = "Presentation"
FAMILY_DRAWING = "Drawing"

# ---------------------#
# Configuration Start #
# ---------------------#

# see http://wiki.services.openoffice.org/wiki/Framework/Article/Filter

# most formats are auto-detected; only those requiring options are defined here
IMPORT_FILTER_MAP = 
    "txt": 
        "FilterName": "Text (encoded)",
        "FilterOptions": "utf8"
    ,
    "csv": 
        "FilterName": "Text - txt - csv (StarCalc)",
        "FilterOptions": "44,34,0"
    


EXPORT_FILTER_MAP = 
    "pdf": 
        FAMILY_TEXT: "FilterName": "writer_pdf_Export",
        FAMILY_WEB: "FilterName": "writer_web_pdf_Export",
        FAMILY_SPREADSHEET: "FilterName": "calc_pdf_Export",
        FAMILY_PRESENTATION: "FilterName": "impress_pdf_Export",
        FAMILY_DRAWING: "FilterName": "draw_pdf_Export"
    ,
    "html": 
        FAMILY_TEXT: "FilterName": "HTML (StarWriter)",
        FAMILY_SPREADSHEET: "FilterName": "HTML (StarCalc)",
        FAMILY_PRESENTATION: "FilterName": "impress_html_Export"
    ,
    "odt": 
        FAMILY_TEXT: "FilterName": "writer8",
        FAMILY_WEB: "FilterName": "writerweb8_writer"
    ,
    "doc": 
        FAMILY_TEXT: "FilterName": "MS Word 97"
    ,
    "rtf": 
        FAMILY_TEXT: "FilterName": "Rich Text Format"
    ,
    "txt": 
        FAMILY_TEXT: 
            "FilterName": "Text",
            "FilterOptions": "utf8"
        
    ,
    "ods": 
        FAMILY_SPREADSHEET: "FilterName": "calc8"
    ,
    "xls": 
        FAMILY_SPREADSHEET: "FilterName": "MS Excel 97"
    ,
    "csv": 
        FAMILY_SPREADSHEET: 
            "FilterName": "Text - txt - csv (StarCalc)",
            "FilterOptions": "44,34,0"
        
    ,
    "odp": 
        FAMILY_PRESENTATION: "FilterName": "impress8"
    ,
    "ppt": 
        FAMILY_PRESENTATION: "FilterName": "MS PowerPoint 97"
    ,
    "swf": 
        FAMILY_DRAWING: "FilterName": "draw_flash_Export",
        FAMILY_PRESENTATION: "FilterName": "impress_flash_Export"
    


PAGE_STYLE_OVERRIDE_PROPERTIES = 
    FAMILY_SPREADSHEET: 
        # --- Scale options: uncomment 1 of the 3 ---
        # a) Reduce / enlarge printout: Scaling factor
        "PageScale": 100,
        # b) Fit print range(s) to width / height: Width in pages and Height in pages
        # "ScaleToPagesX": 1, "ScaleToPagesY": 1000,
        # c) Fit print range(s) on number of pages: Fit print range(s) on number of pages
        # "ScaleToPages": 1,
        "PrintGrid": False
    



# -------------------#
# Configuration End #
# -------------------#

class DocumentConversionException(Exception):

    def __init__(self, message):
        self.message = message

    def __str__(self):
        return self.message


class DocumentConverter:

    def __init__(self, port=DEFAULT_OPENOFFICE_PORT):
        localContext = uno.getComponentContext()
        resolver = localContext.ServiceManager.createInstanceWithContext("com.sun.star.bridge.UnoUrlResolver",
                                                                         localContext)
        try:
            context = resolver.resolve("uno:socket,host=localhost,port=%s;urp;StarOffice.ComponentContext" % port)
        except NoConnectException:
            raise DocumentConversionException("failed to connect to OpenOffice.org on port %s" % port)
        self.desktop = context.ServiceManager.createInstanceWithContext("com.sun.star.frame.Desktop", context)

    def convert(self, inputFile, outputFile):

        inputUrl = self._toFileUrl(inputFile)
        outputUrl = self._toFileUrl(outputFile)

        loadProperties = "Hidden": True
        inputExt = self._getFileExt(inputFile)
        if IMPORT_FILTER_MAP.has_key(inputExt):
            loadProperties.update(IMPORT_FILTER_MAP[inputExt])

        document = self.desktop.loadComponentFromURL(inputUrl, "_blank", 0, self._toProperties(loadProperties))
        try:
            document.refresh()
        except AttributeError:
            pass

        family = self._detectFamily(document)
        self._overridePageStyleProperties(document, family)

        outputExt = self._getFileExt(outputFile)
        storeProperties = self._getStoreProperties(document, outputExt)

        try:
            document.storeToURL(outputUrl, self._toProperties(storeProperties))
        finally:
            document.close(True)

    def _overridePageStyleProperties(self, document, family):
        if PAGE_STYLE_OVERRIDE_PROPERTIES.has_key(family):
            properties = PAGE_STYLE_OVERRIDE_PROPERTIES[family]
            pageStyles = document.getStyleFamilies().getByName(PageStyles)
            for styleName in pageStyles.getElementNames():
                pageStyle = pageStyles.getByName(styleName)
                for name, value in properties.items():
                    pageStyle.setPropertyValue(name, value)

    def _getStoreProperties(self, document, outputExt):
        family = self._detectFamily(document)
        try:
            propertiesByFamily = EXPORT_FILTER_MAP[outputExt]
        except KeyError:
            raise DocumentConversionException( "unknown output format: %s" % outputExt)
        try:
            return propertiesByFamily[family]
        except KeyError:
            raise DocumentConversionException("unsupported conversion: from %s to %s" % (family, outputExt))

    def _detectFamily(self, document):
        if document.supportsService("com.sun.star.text.WebDocument"):
            return FAMILY_WEB
        if document.supportsService("com.sun.star.text.GenericTextDocument"):
            # must be TextDocument or GlobalDocument
            return FAMILY_TEXT
        if document.supportsService("com.sun.star.sheet.SpreadsheetDocument"):
            return FAMILY_SPREADSHEET
        if document.supportsService("com.sun.star.presentation.PresentationDocument"):
            return FAMILY_PRESENTATION
        if document.supportsService("com.sun.star.drawing.DrawingDocument"):
            return FAMILY_DRAWING
        raise DocumentConversionException( "unknown document family: %s" % document)

    def _getFileExt(self, path):
        ext = splitext(path)[1]
        if ext is not None:
            return ext[1:].lower()

    def _toFileUrl(self, path):
        return uno.systemPathToFileUrl(abspath(path))

    def _toProperties(self, dict):
        props = []
        for key in dict:
            prop = PropertyValue()
            prop.Name = key
            prop.Value = dict[key]
            props.append(prop)
        return tuple(props)


if __name__ == "__main__":
    from sys import argv, exit

    if len(argv) < 3:
        print("USAGE: python %s <input-file> <output-file>" % argv[0])
        exit(255)
    if not isfile(argv[1]):
        print("no such input file: %s" % argv[1])
        exit(1)

    try:
        converter = DocumentConverter()
        converter.convert(argv[1], argv[2])
    except DocumentConversionException as exception:
        print("ERROR! " + str(exception))
        exit(1)
    except ErrorCodeIOException as exception:
        print("ERROR! ErrorCodeIOException %d" % exception.ErrCode)
        exit(1)

编写完上面的脚本之后要放到

基于openOffice和python实现office转pdf和html示例代码_ide_02


因为如果不放openOffice的目录下很多类库都引用不到，会导致程序执行不了。

最后万事具备，只欠东风了。

打开cmd命令行，输入这个命令

基于openOffice和python实现office转pdf和html示例代码_html_03


可以把doc转为pdf，pdf文件已经生成了

基于openOffice和python实现office转pdf和html示例代码_html_04


输入这个命令

基于openOffice和python实现office转pdf和html示例代码_python_05


可以把doc转为html，html文件已经生成了

基于openOffice和python实现office转pdf和html示例代码_python_06


其他的office文件转pdf和html，大家可以按需自行尝试。


以上是关于基于openOffice和python实现office转pdf和html示例代码的主要内容，如果未能解决你的问题，请参考以下文章

python https://admintuts.com/how-to-check-the-availability-of-a-steam-id-without-using-the-official-

用于 Libreoffice-calc 和 Openoffice-calc 的 Python“Hello World”[关闭]

Openoffice 中是不是可以实现单词自动化

保证金 Openoffice python

Java怎么操作OpenOffice创建word文档并向其设置内容

页面方向在带有 Python 的 OpenOffice 中不起作用