spire.doc for python 12.2.1 支持通过固定布局获取页的内容-人生就是博尊龙凯时

spire.doc for python 12.2.1 已发布。本次更新新增支持通过固定布局获取页的内容。详情请阅读以下内容。

新功能:

• 支持通过固定布局获取页的内容。

def writealltext(fpath:str,content:str):
    with open(fpath,'w',encoding="utf-8") as fp:
        fp.write(content)
# 指定文件路径
inputfile = "./data/sample.docx"
outputfile = "output.txt"
# 创建一个新的 document 实例
doc = document()
# 从指定文件加载文档
doc.loadfromfile(inputfile, fileformat.docx)
# 使用加载的文档创建一个 fixedlayoutdocument 对象
layoutdoc = fixedlayoutdocument(doc)
result = ''
# 获取第一页第一列的第一行
line = layoutdoc.pages[0].columns[0].lines[0]
result  = "行: "
result  = line.text
result  = "\n"
# 获取与该行关联的原始段落
para = line.paragraph
result  = "段落文本: "
result  = para.text
result  = "\n"
# 获取以纯文本格式显示在第一页上的所有文本（包括页眉和页脚）。
pagetext = layoutdoc.pages[0].text
result  = pagetext
result  = "\n"
# 遍历文档中的每一页，并打印每页上出现的行数。
pages = layoutdoc.pages
for i in range(pages.count):
    page = pages[i]
    lines = page.getchildentities(layoutelementtype.line, true)
    result  = "第 "
    result  = str(page.pageindex)
    result  = " 页有 "
    result  = str(lines.count)
    result  = " 行。"
    result  = "\n"
# 对第一个段落执行反向查找布局实体
result  = "\n"
result  = "第一个段落的行："
result  = "\n"
tempchild = doc.firstchild
section = section(tempchild)
para = section.body.paragraphs[0]
paragraphlines = layoutdoc.getlayoutentitiesofnode(para)
for i in range(paragraphlines.count):
    templine = paragraphlines[i]
    paragraphline = fixedlayoutline(templine)
    result  = (paragraphline.text).strip()
    result  = "\n"
    result  = paragraphline.rectangle.tostring()
    result  = "\n"
    result  = "\n"
# 将提取的文本写入文件
writealltext(outputfile, result)
# 释放文档资源
doc.dispose()

https://www.e-iceblue.cn/downloads/spire-presentation-python.html