Python docx.Document方法代码示例

# 需要导入模块: import docx [as 别名]
# 或者: from docx import Document [as 别名]
def test_finds_run_nodes_in_complex_field_without_separate_correctly(self):
        document = Document(docx_path('complex_field_without_separate.docx'))
        properties = CustomProperties(document).find_docprops_in_document()

        assert 2 == len(properties), \
            'input should contain two complex field docproperties'

        # The "User.FullName" docproperty should be the one without a separate run
        # In this field, there are the following runs: begin, docprop and end
        matches = [prop for prop in properties if prop.name == 'User.FullName']
        assert 1 == len(matches), \
            "There should be only one User.FullName docproperty"
        prop = matches[0]
        assert prop.get_separate_run() is None, \
            "This complex field should not have a separate run."
        assert [] == prop.get_runs_for_update(), \
            "As there is no separate run, there should be no run to update"

        # As there are no separate, all runs should be removed when dissolving
        # the property.
        runs = prop.get_runs_to_replace_field_with_value()
        assert 3 == len(runs)
        assert runs[0] == prop.begin_run
        assert runs[1] == prop.w_r
        assert runs[2] == prop.end_run 

# 需要导入模块: import docx [as 别名]
# 或者: from docx import Document [as 别名]
def generate_document(employee_data, agenda):
    document = Document()
    for emp in employee_data:
        if emp['isDue']:
            name = emp['name']
            document.add_heading('Your New Hire Orientation\n', level=1)
            document.add_paragraph('Dear %s,' % name)
            document.add_paragraph('Welcome to Google Inc. You have been selected for our new hire orientation.')
            document.add_paragraph('Based on your department you will go through below sessions:')
            department = emp['department']
            for session in agenda[department]:
                document.add_paragraph(
                    session , style='ListBullet'
                )
            document.add_paragraph('Thanks,\n HR Manager')
            document.save('orientation_%s.docx' % emp['id']) 

# 需要导入模块: import docx [as 别名]
# 或者: from docx import Document [as 别名]
def iter_block_items(self, parent):
        """
        Yield each paragraph and table child within *parent*, in document order.
        Each returned value is an instance of either Table or Paragraph. *parent*
        would most commonly be a reference to a main Document object, but
        also works for a _Cell object, which itself can contain paragraphs and tables.
        """
        if isinstance(parent, Document):
            parent_elm = parent.element.body
        elif isinstance(parent, _Cell):
            parent_elm = parent._tc
        else:
            raise ValueError("something's not right")

        for child in parent_elm.iterchildren():
            if isinstance(child, CT_P):
                yield Paragraph(child, parent)
            elif isinstance(child, CT_Tbl):
                yield Table(child, parent) 

# 需要导入模块: import docx [as 别名]
# 或者: from docx import Document [as 别名]
def translate_doc(filename, destination='zh-CN', mix=True):
    """
    translate a word document type of file and save the result as document and keep the exactly same file format.
        :param filename: word doc file
        :param destination='zh-CN':
        :param mix=True: if True, will have original language and target language into the same doc. paragraphs by paragraphs.
    """
    def tx(t): return Translator().translate(t, dest=destination).text
    doc = Document(filename)
    for p in doc.paragraphs:
        txd = tx(p.text)

        p.text = p.text + ('\n' + txd if mix else '')

    for table in doc.tables:
        for row in table.rows:
            for cell in row.cells:
                txd = tx(cell.text)
                p.text = cell.text + ('\n' + txd if mix else '')

    f = filename.replace('.doc', destination.lower() + '.doc')
    doc.save(f) 

# 需要导入模块: import docx [as 别名]
# 或者: from docx import Document [as 别名]
def test_complex_docprop_fields_with_multiple_textnodes_are_updated(self):
        document = Document(docx_path('spellchecked_docproperty.docx'))
        paragraphs = xpath(document.element.body, '//w:p')
        assert 1 == len(paragraphs), 'input file contains one paragraph'
        assert 1 == len(xpath(document.element.body, '//w:instrText')), \
            'input contains one complex field docproperty'
        w_p = paragraphs[0]

        cached_values = cached_complex_field_values(w_p)
        assert 4 == len(cached_values), \
            'doc property value is scattered over 4 parts'
        assert 'i will be spllchecked!' == ''.join(cached_values)

        CustomProperties(document).update_all()

        w_p = xpath(document.element.body, '//w:p')[0]
        cached_values = cached_complex_field_values(w_p)
        assert 1 == len(cached_values), \
            'doc property value has been reset to one cached value'
        assert 'i will be spllchecked!' == cached_values[0] 

# 需要导入模块: import docx [as 别名]
# 或者: from docx import Document [as 别名]
def test_complex_field_gets_updated(self):
        document = Document(docx_path('docproperties.docx'))
        assert 6 == len(document.paragraphs), 'input file should contain 6 paragraphs'

        properties = xpath(document.element.body, './/w:instrText')
        assert 5 == len(properties),\
            'input should contain five complex field docproperties'

        expected_paragraphs = [u'Custom Doc Properties',
                               u'Text: Foo Bar',
                               u'Number: 123',
                               u'Boolean: Y',
                               u'Date: 11.06.2019',
                               u'Float: 1.1']
        actual_paragraphs = [paragraph.text for paragraph in document.paragraphs]
        assert actual_paragraphs == expected_paragraphs

        CustomProperties(document).update("Number Property", 423)

        expected_paragraphs[2] = u'Number: 423'
        actual_paragraphs = [paragraph.text for paragraph in document.paragraphs]
        assert actual_paragraphs == expected_paragraphs 

# 需要导入模块: import docx [as 别名]
# 或者: from docx import Document [as 别名]
def test_removes_simple_field_but_keeps_value(self):
        document = Document(docx_path('outdated_docproperty_with_umlauts.docx'))
        assert 1 == len(document.paragraphs), 'input file should contain 1 paragraph'
        fields = xpath(
            document.element.body,
            simple_field_expression(u"F\xfc\xfc"))
        assert 1 == len(fields), 'should contain one simple field docproperty'

        assert u'Hie chund ds property: ' == document.paragraphs[0].text
        assert u'xxx' == fields[0].text

        CustomProperties(document).dissolve_fields(u"F\xfc\xfc")
        fields = xpath(
            document.element.body,
            simple_field_expression(u"F\xfc\xfc"))
        assert 0 == len(fields), 'should not contain any docproperties anymore'
        # when simple field is removed, the value is moved one up in the hierarchy
        assert u'Hie chund ds property: xxx' == document.paragraphs[0].text 

# 需要导入模块: import docx [as 别名]
# 或者: from docx import Document [as 别名]
def test_dissolves_all_instances_of_given_field(self):
        document = Document(docx_path('multiple_identical_properties.docx'))
        assert 3 == len(document.paragraphs), 'input file should contain 3 paragraphs'
        assert 3 == len(xpath(document.element.body, './/w:instrText')), \
            'document should contain three complex field docproperties'

        for paragraph in document.paragraphs:
            assert u'Foo' == paragraph.text

        CustomProperties(document).dissolve_fields("Text Property")

        assert 3 == len(document.paragraphs)
        assert 0 == len(xpath(document.element.body, './/w:instrText')), \
            'document should not contain any complex field anymore'
        for paragraph in document.paragraphs:
            assert u'Foo' == paragraph.text, "value should have been kept in document" 

# 需要导入模块: import docx [as 别名]
# 或者: from docx import Document [as 别名]
def test_dissolving_field_when_three_complex_docprop_in_same_paragraph(self):
        document = Document(docx_path('three_props_in_same_paragraph.docx'))
        assert 1 == len(document.paragraphs), 'input file should contains one paragraph'
        paragraph = document.paragraphs[0]
        properties = CustomProperties(document)
        assert 3 == len(properties.find_docprops_in_document()), \
            'input should contain three complex field docproperties'

        text = u'{text} / {num} mor between the fields {text} and some afte the three fields'
        assert text.format(text="I was spellcecked", num=0) == paragraph.text

        properties.dissolve_fields("Text Property")

        assert 1 == len(document.paragraphs)
        assert 1 == len(properties.find_docprops_in_document()), \
            'document should contain one complex field after removal'
        assert text.format(text="I was spellcecked", num=0) == paragraph.text 

# 需要导入模块: import docx [as 别名]
# 或者: from docx import Document [as 别名]
def Analyze_Metadata_pdf(filename):
####### FUNCTION AnalyzeMetadata ######
	pdfFile = PdfFileReader(file(filename, 'rb'))
	metadata = pdfFile.getDocumentInfo()
	print ' - Document: ' + str(filename)
	for meta in metadata:
		value=(metadata[meta])
		print ' - ' + meta + ':' + metadata[meta]
		if meta == "/Author":
			if value not in meta_author_array:
				meta_author_array.append(value)
		elif meta =="/Producer":
			if value not in meta_producer_array:
				meta_producer_array.append(value)
		elif meta == "/Creator":
			if value not in meta_creator_array:
				meta_creator_array.append(value)
	#Group the different arrays in one with all metadata
	metadata_files.append(meta_author_array)
	metadata_files.append(meta_producer_array)
	metadata_files.append(meta_creator_array)

####### FUNCTION AnalyzeMetadata doc ###### 

# 需要导入模块: import docx [as 别名]
# 或者: from docx import Document [as 别名]
def Analyze_Metadata_doc(fileName):
	#Open file
	docxFile = docx.Document(file(fileName,'rb'))
	#Get the structure
	docxInfo= docxFile.core_properties
	#Print the metadata which it wants to display
	attribute = ["author", "category", "comments", "content_status", 
	    "created", "identifier", "keywords", "language", 
	    "last_modified_by", "last_printed", "modified", 
	    "revision", "subject", "title", "version"]
	#run the list in a for loop to print the value of each metadata
	print ' - Document: ' + str(fileName)
	for meta in attribute:
	    metadata = getattr(docxInfo,meta)
	    if metadata:
	        #Separate the values unicode and time date
	        if isinstance(metadata, unicode): 
	            print " \n\t" + str(meta)+": " + str(metadata)
	        elif isinstance(metadata, datetime.datetime):
	            print " \n\t" + str(meta)+": " + str(metadata) 

# 需要导入模块: import docx [as 别名]
# 或者: from docx import Document [as 别名]
def Analyze_Metadata_pdf(filename):
####### FUNCTION AnalyzeMetadata ######
	pdfFile = PdfFileReader(file(filename, 'rb'))
	metadata = pdfFile.getDocumentInfo()
	print ' - Document: ' + str(filename)
	for meta in metadata:
		value=(metadata[meta])
		print ' - ' + meta + ':' + metadata[meta]
		if meta == "/Author":
			if value not in meta_author_array:
				meta_author_array.append(value)
		elif meta =="/Producer":
			if value not in meta_producer_array:
				meta_producer_array.append(value)
		elif meta == "/Creator":
			if value not in meta_creator_array:
				meta_creator_array.append(value)
	#Group the different arrays in one with all metadata
	metadata_files.append(meta_author_array)
	metadata_files.append(meta_producer_array)
	metadata_files.append(meta_creator_array)
	#print metadata_files
####### FUNCTION AnalyzeMetadata doc ###### 

# 需要导入模块: import docx [as 别名]
# 或者: from docx import Document [as 别名]
def _docx2text(file_path=None):
    '''

    :param file_path: 文件路径
    :return:
    '''
    document = docx.Document(file_path)

    data_str = []
    for i in range(len(document.paragraphs)):
        if document.paragraphs[i].text != '':
            text_one = document.paragraphs[i].text
            data_str.append(text_one)

    return data_str 

# 需要导入模块: import docx [as 别名]
# 或者: from docx import Document [as 别名]
def insetImgToDocx(image):
    document = Document(docx_file)
    p = document.add_paragraph()
    r = p.add_run()
    r.add_picture(image, width=Inches(5.5)) #inces sesuai yang ada di garis
    r.add_text('Ini picture: {}'.format(image))
    document.save(docx_file) 

# 需要导入模块: import docx [as 别名]
# 或者: from docx import Document [as 别名]
def __init__(self, project_root, lines_to_extract=3000, output_file='extracted_code.docx', output=True):
        self.info = ProjectInfo(project_root, lines_to_extract)
        self.output = output
        if output:
            self.output_path = self.info.get_output_file_path(output_file)
            # self.output_file = open(
            # self.info.get_output_file_path(output_file), 'w+')
            self.output_file = Document(os.path.join(
                os.path.dirname(__file__), 'data/template.docx'))
            self.paragraph = None
        return