Python pypandoc 模块，convert_file() 实例源码

def read(*filenames, **kwargs):
    """
    Read file contents into string.

    Used by setup.py to concatenate long_description.

    :param string filenames: Files to be read and concatenated.
    :rtype: string

    """
    encoding = kwargs.get('encoding', 'utf-8')
    sep = kwargs.get('sep', '\n')
    buf = []
    for filename in filenames:
        if path.splitext(filename)[1] == ".md":
            try:
                import pypandoc
                buf.append(pypandoc.convert_file(filename, 'rst'))
                continue
            except:
                with io.open(filename, encoding=encoding) as f:
                    buf.append(f.read())
        with io.open(filename, encoding=encoding) as f:
            buf.append(f.read())
    return sep.join(buf)

def long_description(
    filename = "README.md"
    ):

    if os.path.isfile(os.path.expandvars(filename)):
        try:
            import pypandoc
            long_description = pypandoc.convert_file(filename, "rst")
        except ImportError:
            long_description = open(filename).read()
    else:
        long_description = ""
    return long_description

def long_description():
    try:
        import pypandoc
        long_desc = pypandoc.convert_file('README.md', 'rst')
        long_desc += '\n' + pypandoc.convert_file('AUTHORS.md', 'rst')
    except Exception as e:
        print(e)
        long_desc = imgkit.__doc__.strip()
    return long_desc

def read_md(filename):
    try:
        from pypandoc import convert_file
        return convert_file(filename, 'rst')
    except (ImportError, OSError):
        return open(filename).read()

def convert_md_to_rst(fp):
    try:
        import pypandoc
        output = pypandoc.convert_file(fp, 'rst')
        return output
    except ImportError:
        warnings.warn('cannot import pypandoc.', UserWarning)
        return open(fp).read()

def convert(file, stdin, instanceid):
    if stdin:
        text = ""
        with open(file, 'r') as filehandle:
            text = filehandle.read()
        # this fails
        pypandoc.convert_text(text, "asciidoc",
                              format="html",
                              outputfile="%s.asciidoc" % instanceid)
    else:  # this works
        output = pypandoc.convert_file(file, "asciidoc",
                                       format="html")

def printPosts(item, fields, docFormat=None, writeToFiles=False):
    template = """+++
{0}
+++

{1}
"""
    logger.debug(json.dumps(item,
                            sort_keys=True,
                            indent=2,
                            separators=(',', ': ')))
    if docFormat:
        logger.debug("Starting to print %s", item['id'])
        filename = None
        content = item["content"].encode('utf-8', "ignore")
        if writeToFiles:
            filename = getFilenameFromPostUrl(item['url'], docFormat)
            with open(filename, "wb") as outputFile:
                outputFile.write(content)
            converted = pypandoc.convert_file(
                filename,
                docFormat,
                format="html")
            content = template.format(getFrontMatter(item),
                                      converted).encode('utf-8',
                                                        'ignore')
            with open(filename, "wb") as outputfile:
                outputfile.write(content)
        else:
            print(content)
        logger.info("Finished print %s: %s", item['id'], filename)
    elif isinstance(fields, basestring):
        fields = fields.split(",")
        line = [str(item[k]) for k in fields if k in item]
        print(",".join(line))

def _load_readme(self):
        readme = self._config['package']['readme']
        readme_path = os.path.join(self._dir, readme)

        if self.has_markdown_readme():
            if not pypandoc:
                warnings.warn(
                    'Markdown README files require the pandoc utility '
                    'and the pypandoc package.'
                )
            else:
                self._readme = pypandoc.convert_file(readme_path, 'rst')
        else:
            with open(readme_path) as f:
                self._readme = f.read()

def makeLongDescription():
    return pypandoc.convert_file('README.md', 'rst')

def get_long_description(self, filename='README.md'):
        """ I really prefer Markdown to reStructuredText. PyPi does not.
        """
        try:
            import pypandoc
            description = pypandoc.convert_file('README.md', 'rst', 'md')
        except (IOError, ImportError):
            description = open("README.md").read()
        return description

def read_md(f):
        return convert_file(f, 'rst')

def long_description(
    filename = "README.md"
    ):

    if os.path.isfile(os.path.expandvars(filename)):
        try:
            import pypandoc
            long_description = pypandoc.convert_file(filename, "rst")
        except ImportError:
            long_description = open(filename).read()
    else:
        long_description = ""
    return long_description

def get_callback(file_meta, user):
    def callback(request_id, response, exception):
        if exception is None:
            file_name = file_meta['name'].replace(' ', '-')
            created_time_str = file_meta['createdTime']
            created_time = dateutil.parser.parse(created_time_str)


            docx_dir = '{0}/{1}/docx'.format(settings.CONVERSION_DIR_ROOT,
                                                user.email)
            ensure_dir(docx_dir)

            # write response to a docx file
            f = open('{0}/{1}.docx'.format(docx_dir, file_name), 'w+')
            f.write(response)
            f.close()

            md_dir = '{0}/{1}/md'.format(settings.CONVERSION_DIR_ROOT,
                                            user.email)
            ensure_dir(md_dir)

            # construct yaml matter
            template = loader.get_template('post_header_template.html')
            yaml_matter = template.render({
                "title": file_name,
                "date": created_time_str,
                "categories": ""
            })

            outputfile = '{0}/{1}-{2}.markdown'.format(md_dir, 
                created_time.strftime('%Y-%m-%d'),
                slugify(file_name))

            # convert file
            pypandoc.convert_file(
                '{0}/{1}.docx'.format(docx_dir, file_name), 
                'md', 
                outputfile=outputfile)

            # prepend yaml_matter to converted file
            # TODO: do this in-place, rather than in-memory
            prepend2file(outputfile, yaml_matter)
        else:
            # handle error
            pass
    return callback