| show | version | enable_checker |
|---|---|---|
step |
1.0 |
true |
- 上次综合运用python
- 生成了一篇文档
- 你可以生成一篇 属于自己的文档吗？
- 如果想要设置插入图片的版式怎么办呢？
from docx import Document
from docx.shared import Pt
document = Document()
p = document.add_paragraph()
r = p.add_run("before")
r.add_picture('m.png')
p.add_run("after")
document.save("o.docx")
- 图片模式为行内模式
- 观察document.xml
unzip -d oeasy oeasy.docx
cd oeasy/word
firefox document.xml
- 文档分成三段
- 图片在于中心
- 如果想要将图片做成其他版式
- 应该如何呢？
- 在libreoffice中
- 重新插入图片
- 并设置版式
- 然后设置位置
- 再次观察
unzip -d oeasy o.docx
cd oeasy/word
firefox document.xml
- 新的drawing 自起一run
- wp:anchor节点的behindDoc属性表明
- 图片版式为衬于文本下方
- wp:positionH和wp:positionV节点
- 表明水平和竖直绝对定位方式
- relativeFrom属性指定用于定位的参考对象
- 子节点wp:posOffset指定具体坐标值
pip3 show python-docx
- 查看库
cd /home/shiyanlou/.local/lib/python3.8/site-packages
grep add_picture *.py
- 查询add_picture的定义
- 在document.py中
vi document.py
- 查找函数定义
- /def add_picture
- document.add_picture
- 调用了run.add_picture
- 找到text/run.py
- 继续深入
grep -r "def new_pic_inline" --include="*.py"
- 找到位置
vi parts/story.py
- 找到函数
- /new_pic_inline
- 需要找到CT_Inline
grep -r "class CT_Inline" --include="*.py"
vi oxml/shape.py
- 这个应该是操作xml节点的具体执行函数了
- 100行以上
- 都是对xml的直接设置
cd ~
vi add_float_picture.py
- 编辑模块
# -*- coding: utf-8 -*-
# filename: add_float_picture.py
'''
Implement floating image based on python-docx.
- 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.__init__.py
register_element_cls('wp:anchor', CT_Anchor)
from docx import Document
from docx.shared import Inches, Pt
from add_float_picture import add_float_picture
if __name__ == '__main__':
document = Document()
# add a floating picture
p = document.add_paragraph()
add_float_picture(p, 'm.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')
- 最终效果
- 这次探索了结构
- 并制作了浮动图片的函数
- 以后可以做点类似于盖章之类的东西了
- 参考来源
- 还能玩点什么？
- 我们下次再说！👋🏻