image - 如何在 python-docx 中使用 add_picture() 在背景上插入图像（与文本重叠）？

python-docxv0.8.10尚不支持浮动图片。但是基于创建内嵌图片的实现，我探索了一种解决方法，并在我的项目中使用。

https://github.com/dothinking/pdf2docx/issues/54#issuecomment-715925252

探索浮动图像的步骤：

创建两个 docx 文件，一个插入内联图像，另一个插入浮动图像（在本例中为使用behind text模式）
检查这两个文件之间源xml的差异
基于观察到的结构和python-docx内联图像源代码实现浮动图像

xml结构结果：

内联图像是<wp:inline>下的一个节点<w:drawing>
浮动图像是<wp:anchor>下一个节点<w:drawing>
除了内嵌图像的所有子节点，浮动图像还包含<wp:positionH>和<wp:positionV>定义固定位置

所以，想法是创建<wp:anchor>节点，然后附加子节点：不仅是所有具有内联图像的相同节点，而且还有额外的<wp:positionH>和<wp:positionV>。

# -*- coding: utf-8 -*-

'''
Implement floating image based on python-docx 0.8.10.

- Text wrapping style: BEHIND TEXT <wp:anchor behindDoc="1">
- Picture position: top-left corner of PAGE `<wp:positionH relativeFrom="page">`.

Create a docx sample (Layout | Positions | More Layout Options) and explore the 
source xml (Open as a zip | word | document.xml) to implement other text wrapping
styles and position modes per `CT_Anchor._anchor_xml()`.
'''

from docx.oxml import parse_xml, register_element_cls
from docx.oxml.ns import nsdecls
from docx.oxml.shape import CT_Picture
from docx.oxml.xmlchemy import BaseOxmlElement, OneAndOnlyOne

# refer to docx.oxml.shape.CT_Inline
class CT_Anchor(BaseOxmlElement):
    """
    ``<w:anchor>`` element, container for a floating image.
    """
    extent = OneAndOnlyOne('wp:extent')
    docPr = OneAndOnlyOne('wp:docPr')
    graphic = OneAndOnlyOne('a:graphic')

    @classmethod
    def new(cls, cx, cy, shape_id, pic, pos_x, pos_y):
        """
        Return a new ``<wp:anchor>`` element populated with the values passed
        as parameters.
        """
        anchor = parse_xml(cls._anchor_xml(pos_x, pos_y))
        anchor.extent.cx = cx
        anchor.extent.cy = cy
        anchor.docPr.id = shape_id
        anchor.docPr.name = 'Picture %d' % shape_id
        anchor.graphic.graphicData.uri = (
            'http://schemas.openxmlformats.org/drawingml/2006/picture'
        )
        anchor.graphic.graphicData._insert_pic(pic)
        return anchor

    @classmethod
    def new_pic_anchor(cls, shape_id, rId, filename, cx, cy, pos_x, pos_y):
        """
        Return a new `wp:anchor` element containing the `pic:pic` element
        specified by the argument values.
        """
        pic_id = 0  # Word doesn't seem to use this, but does not omit it
        pic = CT_Picture.new(pic_id, filename, rId, cx, cy)
        anchor = cls.new(cx, cy, shape_id, pic, pos_x, pos_y)
        anchor.graphic.graphicData._insert_pic(pic)
        return anchor

    @classmethod
    def _anchor_xml(cls, pos_x, pos_y):
        return (
            '<wp:anchor distT="0" distB="0" distL="0" distR="0" simplePos="0" relativeHeight="0" \n'
            '           behindDoc="1" locked="0" layoutInCell="1" allowOverlap="1" \n'
            '           %s>\n'
            '  <wp:simplePos x="0" y="0"/>\n'
            '  <wp:positionH relativeFrom="page">\n'
            '    <wp:posOffset>%d</wp:posOffset>\n'
            '  </wp:positionH>\n'
            '  <wp:positionV relativeFrom="page">\n'
            '    <wp:posOffset>%d</wp:posOffset>\n'
            '  </wp:positionV>\n'                    
            '  <wp:extent cx="914400" cy="914400"/>\n'
            '  <wp:wrapNone/>\n'
            '  <wp:docPr id="666" name="unnamed"/>\n'
            '  <wp:cNvGraphicFramePr>\n'
            '    <a:graphicFrameLocks noChangeAspect="1"/>\n'
            '  </wp:cNvGraphicFramePr>\n'
            '  <a:graphic>\n'
            '    <a:graphicData uri="URI not set"/>\n'
            '  </a:graphic>\n'
            '</wp:anchor>' % ( nsdecls('wp', 'a', 'pic', 'r'), int(pos_x), int(pos_y) )
        )


# refer to docx.parts.story.BaseStoryPart.new_pic_inline
def new_pic_anchor(part, image_descriptor, width, height, pos_x, pos_y):
    """Return a newly-created `w:anchor` element.

    The element contains the image specified by *image_descriptor* and is scaled
    based on the values of *width* and *height*.
    """
    rId, image = part.get_or_add_image(image_descriptor)
    cx, cy = image.scaled_dimensions(width, height)
    shape_id, filename = part.next_id, image.filename    
    return CT_Anchor.new_pic_anchor(shape_id, rId, filename, cx, cy, pos_x, pos_y)


# refer to docx.text.run.add_picture
def add_float_picture(p, image_path_or_stream, width=None, height=None, pos_x=0, pos_y=0):
    """Add float picture at fixed position `pos_x` and `pos_y` to the top-left point of page.
    """
    run = p.add_run()
    anchor = new_pic_anchor(run.part, image_path_or_stream, width, height, pos_x, pos_y)
    run._r.add_drawing(anchor)

# refer to docx.oxml.shape.__init__.py
register_element_cls('wp:anchor', CT_Anchor)


if __name__ == '__main__':

    from docx import Document
    from docx.shared import Inches, Pt

    document = Document()

    # add a floating image
    p = document.add_paragraph()
    add_float_picture(p, 'test.png', width=Inches(5.0), pos_x=Pt(20), pos_y=Pt(30))

    # add text
    p.add_run('Hello World'*50)


    document.save('output.docx')

image - 如何在 python-docx 中使用 add_picture() 在背景上插入图像（与文本重叠）？

问题描述

解决方案

推荐阅读