Python如何批量实现查找替换Word文档的文本内容

pip install spire.doc.free

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

document = Document()
document.LoadFromFile("sample.docx")

# 替换公司名称
document.Replace("TechCorp Solutions", "Innovatech Partners", False, True)

# 替换客户名称
document.Replace("Global Systems Inc", "Apex Dynamics Ltd", False, True)

# 替换日期
document.Replace("January 15, 2026", "March 20, 2026", False, True)

document.SaveToFile("after_text_replace.docx", FileFormat.Docx)
document.Close()

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

document = Document()
document.LoadFromFile("sample.docx")

# 创建正则表达式，匹配 #TAG 后跟字母数字
regex = Regex("#TAG\\w+", RegexOptions.none)

# 查找所有匹配项
textSections = document.FindAllPattern(regex)

# 逐项替换文本
for ts in textSections:
    textRange = ts.GetAsOneRange()
    textRange.Text = "RESOLVED"

document.SaveToFile("after_regex_replace.docx", FileFormat.Docx)
document.Close()

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

document = Document()
document.LoadFromFile("sample.docx")

# 查找 "Agreement" 并高亮为黄色
selections = document.FindAllString("Agreement", False, True)
for selection in selections:
    selection.GetAsOneRange().CharacterFormat.HighlightColor = Color.get_Yellow()

# 查找 "Provider" 并高亮为绿色
selections = document.FindAllString("Provider", False, True)
for selection in selections:
    selection.GetAsOneRange().CharacterFormat.HighlightColor = Color.get_Green()

# 查找 "Client" 并高亮为橙色
selections = document.FindAllString("Client", False, True)
for selection in selections:
    selection.GetAsOneRange().CharacterFormat.HighlightColor = Color.FromArgb(255, 255, 128, 0)

document.SaveToFile("after_highlight.docx", FileFormat.Docx)
document.Close()

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

document = Document()
document.LoadFromFile("sample.docx")

# 查找所有 [LOGO] 占位符
selections = document.FindAllString("[LOGO]", False, False)

for selection in selections:
    # 创建图片对象并加载文件
    pic = DocPicture(document)
    pic.LoadImage("logo.png")

    # 获取文本范围在段落中的位置
    textRange = selection.GetAsOneRange()
    index = textRange.OwnerParagraph.ChildObjects.IndexOf(textRange)

    # 先插入图片，再移除文本
    textRange.OwnerParagraph.ChildObjects.Insert(index, pic)
    textRange.OwnerParagraph.ChildObjects.Remove(textRange)

document.SaveToFile("after_image_replace.docx", FileFormat.Docx)
document.Close()

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

document = Document()
document.LoadFromFile("sample.docx")

section = document.Sections[0]

# 查找 [PRICING_TABLE] 占位符
selection = document.FindString("[PRICING_TABLE]", False, False)

# 获取占位符所在的段落和文档体
range = selection.GetAsOneRange()
paragraph = range.OwnerParagraph
body = paragraph.OwnerTextBody
index = body.ChildObjects.IndexOf(paragraph)

# 创建 4 行 3 列的定价表
table = section.AddTable(True)
table.ResetCells(4, 3)

# 填充表头
header = ["Service Item", "Unit Price (USD)", "Quantity"]
for col, text in enumerate(header):
    cell = table.Rows[0].Cells[col]
    cellParagraph = cell.AddParagraph()
    cellParagraph.AppendText(text)

# 填充数据行
data = [
    ["Cloud Infrastructure", "2,500/month", "1"],
    ["Data Migration", "8,000", "1"],
    ["Technical Support", "1,200/month", "1"],
]
for rowIdx, rowData in enumerate(data):
    for col, text in enumerate(rowData):
        cell = table.Rows[rowIdx + 1].Cells[col]
        cellParagraph = cell.AddParagraph()
        cellParagraph.AppendText(text)

# 用表格替换占位符段落
body.ChildObjects.Remove(paragraph)
body.ChildObjects.Insert(index, table)

document.SaveToFile("after_table_replace.docx", FileFormat.Docx)
document.Close()

import os
import shutil
from spire.doc import *
from spire.doc.common import *

# 定义替换规则：(查找文本, 替换文本, 区分大小写, 全词匹配)
replacements = [
    ("TechCorp Solutions", "Innovatech Partners", False, True),
    ("Global Systems Inc", "Apex Dynamics Ltd", False, True),
    ("January 15, 2026", "March 20, 2026", False, True),
]

# 准备批量输入目录（3 份文档副本）
batch_dir = "batch_input"
os.makedirs(batch_dir, exist_ok=True)
for i in range(1, 4):
    shutil.copy("sample.docx", os.path.join(batch_dir, f"agreement_{i}.docx"))

# 处理目录中的所有 .docx 文件
output_dir = "batch_output"
os.makedirs(output_dir, exist_ok=True)

for filename in sorted(os.listdir(batch_dir)):
    if not filename.endswith(".docx"):
        continue

    doc = Document()
    doc.LoadFromFile(os.path.join(batch_dir, filename))

    for findText, replaceText, isCase, isWhole in replacements:
        doc.Replace(findText, replaceText, isCase, isWhole)

    doc.SaveToFile(os.path.join(output_dir, filename), FileFormat.Docx)
    doc.Close()
    print(f"  Processed: {filename}")