使用Python和run概念用超链接替换docx中的字符串，同时保持原始字体样式和大小

Question

我有一个Python脚本，旨在解析

docx Doc

以用带有超链接的文本替换代码（可能是无意中写错的）。我已经从文档中找到的字符串中获得了原始值和清理后的值：

extracted_tv = [{'raw': 'TV-FRM-05496', 'cleaned': 'TV-FRM-05496'}, {'raw': 'TV-SOP-25663', 'cleaned': 'TV-SOP-25663'}, {'raw': 'TV--REF----66655', 'cleaned': 'TV-REF-66655'}, {'raw': 'TV-FRM-   054912', 'cleaned': 'TV-FRM-054912'}, {'raw': 'TVXFRM01496', 'cleaned': 'TV-XFRM-01496'}, {'raw': 'TV  WI  05496', 'cleaned': 'TV-WI-05496'}]

该 docx 包含以下内容： 电视-FRM-05496 ASDASTV-SOP-25663aS 电视--REF----66655 电视-FRM-054912 电视-XFRM-01496 电视-WI-05496

但是，当执行下面的脚本时，上面除了“TV--REF----66655”之外的所有字符串都被超链接正确替换。

我尝试删除 lower() 函数并尝试连接运行。有什么想法我可能做错了什么或有任何指示吗？我在下面提供了我的尝试。

import docx
from docx.oxml import OxmlElement
from docx.oxml.ns import qn
from docx.enum.dml import MSO_THEME_COLOR_INDEX
import docx

def add_hyperlink(document, run, url, name):
"""
Add a hyperlink to a run while preserving the original font size and style,
but applying the hyperlink color and no underline.

    :param document: The Document being edited.
    :param run: The Run the hyperlink is being added to.
    :param url: The url to be added to the link.
    :param name: The text for the link to be displayed in the paragraph
    :return: None
    """
    
    # Preserve original font size and style
    font = run.font
    original_size = font.size
    original_bold = font.bold
    original_italic = font.italic
    original_name = font.name
    
    part = document.part
    rId = part.relate_to(url, docx.opc.constants.RELATIONSHIP_TYPE.HYPERLINK, is_external=True)
    
    # Create the hyperlink element
    hyperlink = OxmlElement('w:hyperlink')
    hyperlink.set(qn('r:id'), rId)
    hyperlink.set(qn('w:history'), '1')
    
    # Create a new run element
    new_run = OxmlElement('w:r')
    rPr = OxmlElement('w:rPr')
    
    # Set the hyperlink style
    rStyle = OxmlElement('w:rStyle')
    rStyle.set(qn('w:val'), 'Hyperlink')
    rPr.append(rStyle)
    
    # Apply the original font properties to the hyperlink
    if original_size:
        size = OxmlElement('w:sz')
        size.set(qn('w:val'), str(int(original_size.pt * 2)))  # Font size in half-points
        rPr.append(size)
    
    if original_bold:
        bold = OxmlElement('w:b')
        bold.set(qn('w:val'), 'true')
        rPr.append(bold)
    
    if original_italic:
        italic = OxmlElement('w:i')
        italic.set(qn('w:val'), 'true')
        rPr.append(italic)
    
    if original_name:
        rFonts = OxmlElement('w:rFonts')
        rFonts.set(qn('w:ascii'), original_name)
        rFonts.set(qn('w:hAnsi'), original_name)
        rPr.append(rFonts)
    
    # Apply the hyperlink color and remove underline
    color = OxmlElement('w:color')
    color.set(qn('w:val'), "0000FF")  # Blue color
    rPr.append(color)
    
    u = OxmlElement('w:u')
    u.set(qn('w:val'), 'none')  # Remove underline
    rPr.append(u)
    
    new_run.append(rPr)
    
    # Set the text for the new run
    new_run_text = OxmlElement('w:t')
    new_run_text.text = name
    new_run.append(new_run_text)
    
    # Append the new run to the hyperlink element
    hyperlink.append(new_run)
    
    # Insert the hyperlink before the original run and clear the original run
    run._r.addprevious(hyperlink)
    run.clear()
    
    return None

# Example usage

intermediate_docx_file = "intermediate_file.docx"
doc = docx.Document(intermediate_docx_file)

# Process paragraphs
for paragraph in doc.paragraphs:
    for run in paragraph.runs:
        for tv_item in extracted_tv:
            raw_tv_number = tv_item['raw']
            cleaned_tv_number = tv_item['cleaned']
            if raw_tv_number.lower() in run.text.lower():
              hyperlink_url = f'https://hyperlink.com/DocNum={cleaned_tv_number}'
              add_hyperlink(doc, run, hyperlink_url, cleaned_tv_number)
              run.text = run.text.replace(cleaned_tv_number, '')  # Remove the TV number from the run

output_docx_file = 'document_with_hyperlinks.docx'
doc.save(output_docx_file)

Answer 1

如果您愿意切换到商业库，您可以考虑使用 Aspose.Words 用超链接替换文档中的文本。我们的想法是用占位符本身替换占位符，使其表示为单个

Run

，然后找到

Run

并插入超链接。这是演示该技术的简单代码：

doc = aw.Document("C:\\Temp\\in.docx")
builder = aw.DocumentBuilder(doc)

# This is placeholder we would like to replace with hyperlink.
word = "test"
hyperlink = "https://www.aspose.com"

# Use Range.replace method to make each searched word a separate Run node.
opt = aw.replacing.FindReplaceOptions()
opt.use_substitutions = True
doc.range.replace(word, "$0", opt)

# Get all runs
runs = doc.get_child_nodes(aw.NodeType.RUN, True).to_array()

for r in runs :
    run = r.as_run()
    # process the runs with text that matches the searched word.
    if run.text == word:
        # Inset hyperlink
        builder.move_to(run)
        builder.insert_hyperlink(word, hyperlink, False)
        # remove the matched run, since we inserted hyperlink with the same text
        run.remove()

doc.save("C:\\Temp\\out.docx")