Python 在Word中添加、或删除超链接

在Word文档中，超链接是一种将文本或图像连接到其他文档、网页或同一文档中不同部分的功能。通过添加超链接，用户可以轻松地导航到相关信息，从而增强文档的互动性和可读性。本文将介绍如何使用Python在Word中添加超链接、或删除Word文档中的超链接。

文章目录

- Python 在Word中添加超链接
- Python 删除Word中的超链接

要实现通过Python操作Word文档，我们需要安装 Spire.Doc for Python 库。该库的pip安装命令如下：

pip install Spire.Doc

Python 在Word中添加超链接

Spire.Doc for Python 库提供了 AppendHyperlink() 方法来添加超链接，其中三个参数：
• link – 代表超链接地址
• text – 代表显示文本（也可传入picture来为图片添加超链接）
• type – 代表超链接类型（包括网页链接WebLink、邮件链接EMailLink、书签链接Bookmark、文件链接FileLink）

示例代码如下：

from spire.doc import *
from spire.doc.common import *

# 创建Word文档
doc = Document()

# 添加一节
section = doc.AddSection()

# 添加一个段落
paragraph = section.AddParagraph()

# 添加一个简单网页链接
paragraph.AppendHyperlink("https://ABCD.com/", "主页", HyperlinkType.WebLink)

# 添加换行符
paragraph.AppendBreak(BreakType.LineBreak)
paragraph.AppendBreak(BreakType.LineBreak)

# 添加一个邮箱链接
paragraph.AppendHyperlink("mailto:support@e-iceblue.com", "邮箱地址", HyperlinkType.EMailLink)

# 添加换行符
paragraph.AppendBreak(BreakType.LineBreak)
paragraph.AppendBreak(BreakType.LineBreak)

# 添加一个文档链接
filePath = "C:\\Users\\Administrator\\Desktop\\排名.xlsx"
paragraph.AppendHyperlink(filePath, "点击查看文件", HyperlinkType.FileLink)

# 添加换行符
paragraph.AppendBreak(BreakType.LineBreak)
paragraph.AppendBreak(BreakType.LineBreak)

# 添加一个新节并创建书签
section2 = doc.AddSection()
bookmarkParagrapg = section2.AddParagraph()
bookmarkParagrapg.AppendText("添加一个新段落")
start = bookmarkParagrapg.AppendBookmarkStart("书签")
bookmarkParagrapg.Items.Insert(0, start)
bookmarkParagrapg.AppendBookmarkEnd("书签")

# 链接到书签
paragraph.AppendHyperlink("书签", "点击跳转到文档指定位置", HyperlinkType.Bookmark)

# 添加换行符
paragraph.AppendBreak(BreakType.LineBreak)
paragraph.AppendBreak(BreakType.LineBreak)

# 添加一个图片超链接
image = "C:\\Users\\Administrator\\Desktop\\work1.jpg"
picture = paragraph.AppendPicture(image)
paragraph.AppendHyperlink("https://ABCD.com/", picture, HyperlinkType.WebLink)

# 保存文档
doc.SaveToFile("Word超链接.docx", FileFormat.Docx2019);
doc.Dispose()

生成文档:
Word超链接

Python 删除Word中的超链接

要删除 Word 文档中的所有超链接，先用到了自定义方法 FindAllHyperlinks() 来查找文档中的所有超链接，然后再通过自定义方法 FlattenHyperlinks() 来扁平化超链接。

示例代码如下：

from spire.doc import *
from spire.doc.common import *

# 查找文档中的所有超链接
def FindAllHyperlinks(document):
    hyperlinks = []
    for i in range(document.Sections.Count):
        section = document.Sections.get_Item(i)
        for j in range(section.Body.ChildObjects.Count):
            sec = section.Body.ChildObjects.get_Item(j)
            if sec.DocumentObjectType == DocumentObjectType.Paragraph:
                for k in range((sec if isinstance(sec, Paragraph) else None).ChildObjects.Count):
                    para = (sec if isinstance(sec, Paragraph)
                            else None).ChildObjects.get_Item(k)
                    if para.DocumentObjectType == DocumentObjectType.Field:
                        field = para if isinstance(para, Field) else None
                        if field.Type == FieldType.FieldHyperlink:
                            hyperlinks.append(field)
    return hyperlinks

# 扁平化超链接域
def FlattenHyperlinks(field):
    ownerParaIndex = field.OwnerParagraph.OwnerTextBody.ChildObjects.IndexOf(
        field.OwnerParagraph)
    fieldIndex = field.OwnerParagraph.ChildObjects.IndexOf(field)
    sepOwnerPara = field.Separator.OwnerParagraph
    sepOwnerParaIndex = field.Separator.OwnerParagraph.OwnerTextBody.ChildObjects.IndexOf(
        field.Separator.OwnerParagraph)
    sepIndex = field.Separator.OwnerParagraph.ChildObjects.IndexOf(
        field.Separator)
    endIndex = field.End.OwnerParagraph.ChildObjects.IndexOf(field.End)
    endOwnerParaIndex = field.End.OwnerParagraph.OwnerTextBody.ChildObjects.IndexOf(
        field.End.OwnerParagraph)

    FormatFieldResultText(field.Separator.OwnerParagraph.OwnerTextBody,
                           sepOwnerParaIndex, endOwnerParaIndex, sepIndex, endIndex)

    field.End.OwnerParagraph.ChildObjects.RemoveAt(endIndex)
    
    for i in range(sepOwnerParaIndex, ownerParaIndex - 1, -1):
        if i == sepOwnerParaIndex and i == ownerParaIndex:
            for j in range(sepIndex, fieldIndex - 1, -1):
                field.OwnerParagraph.ChildObjects.RemoveAt(j)

        elif i == ownerParaIndex:
            for j in range(field.OwnerParagraph.ChildObjects.Count - 1, fieldIndex - 1, -1):
                field.OwnerParagraph.ChildObjects.RemoveAt(j)

        elif i == sepOwnerParaIndex:
            for j in range(sepIndex, -1, -1):
                sepOwnerPara.ChildObjects.RemoveAt(j)
        else:
            field.OwnerParagraph.OwnerTextBody.ChildObjects.RemoveAt(i)

# 将域转换为文本范围并清除文本格式
def FormatFieldResultText(ownerBody, sepOwnerParaIndex, endOwnerParaIndex, sepIndex, endIndex):
    for i in range(sepOwnerParaIndex, endOwnerParaIndex + 1):
        para = ownerBody.ChildObjects[i] if isinstance(
            ownerBody.ChildObjects[i], Paragraph) else None
        if i == sepOwnerParaIndex and i == endOwnerParaIndex:
            for j in range(sepIndex + 1, endIndex):
               if isinstance(para.ChildObjects[j], TextRange):
                 FormatText(para.ChildObjects[j])

        elif i == sepOwnerParaIndex:
            for j in range(sepIndex + 1, para.ChildObjects.Count):
                if isinstance(para.ChildObjects[j], TextRange):
                  FormatText(para.ChildObjects[j])
        elif i == endOwnerParaIndex:
            for j in range(0, endIndex):
               if isinstance(para.ChildObjects[j], TextRange):
                 FormatText(para.ChildObjects[j])
        else:
            for j, unusedItem in enumerate(para.ChildObjects):
                if isinstance(para.ChildObjects[j], TextRange):
                  FormatText(para.ChildObjects[j])

# 设置文本样式
def FormatText(tr):
    tr.CharacterFormat.TextColor = Color.get_Black()
    tr.CharacterFormat.UnderlineStyle = UnderlineStyle.none

# 加载Word文档
doc = Document()
doc.LoadFromFile("Word超链接.docx")

# 获取所有超链接
hyperlinks = FindAllHyperlinks(doc)

# 扁平化超链接
for i in range(len(hyperlinks) - 1, -1, -1):
    FlattenHyperlinks(hyperlinks[i])

# 保存文件
doc.SaveToFile("删除超链接.docx", FileFormat.Docx)
doc.Close()