pip install spire.doc

from spire.doc import *


# 加載原始文檔
original = Document()
original.LoadFromFile("原始.docx")

# 加載修訂文檔
revised = Document()
revised.LoadFromFile("修訂.docx")

# 執(zhí)行對比
original.Compare(revised, "Reviewer")

# 保存對比結(jié)果（包含修訂標(biāo)記）
original.SaveToFile("對比結(jié)果.docx", FileFormat.Docx2013)

from spire.doc import *

original = Document()
original.LoadFromFile("原始.docx")
revised = Document()
revised.LoadFromFile("修訂.docx")

# 設(shè)置對比選項
options = CompareOptions()
options.IgnoreFormatting = True   # 忽略字體、顏色和樣式變化

# 執(zhí)行對比
original.Compare(revised, "Reviewer", DateTime.get_Now(), options)

# 保存結(jié)果
original.SaveToFile("忽略格式差異.docx", FileFormat.Docx2013)

from spire.doc import *

def save_text(fname: str, content: str):
    """將字符串內(nèi)容保存到文本文件"""
    with open(fname, "w", encoding="utf-8") as fp:
        fp.write(content)

def format_revision(index: int, revision, content: str) -> str:
    """格式化修訂信息，包含序號、類型、作者和修訂內(nèi)容"""
    return (
        f"序號: {index}\n"
        f"修訂類型: {revision.Type.name}\n"
        f"作者: {revision.Author}\n"
        f"修訂內(nèi)容: {content}\n"
    )

# 輸入的對比結(jié)果文檔
input_file = "文檔比對結(jié)果.docx"
# 輸出文件：插入修訂
output_insert = "插入修訂.txt"
# 輸出文件：刪除修訂
output_delete = "刪除修訂.txt"

# 創(chuàng)建 Document 對象并加載 Word 文件
document = Document()
document.LoadFromFile(input_file)

# 用于收集插入和刪除修訂結(jié)果
insert_revisions = ["【插入修訂列表】"]
delete_revisions = ["【刪除修訂列表】"]

# 插入和刪除修訂的計數(shù)器
index_insert = 0
index_delete = 0

# 遍歷文檔中的所有節(jié)
for k in range(document.Sections.Count):
    sec = document.Sections.get_Item(k)

    # 遍歷節(jié)中的所有子對象
    for m in range(sec.Body.ChildObjects.Count):
        doc_item = sec.Body.ChildObjects.get_Item(m)

        # 判斷對象是否為段落
        if isinstance(doc_item, Paragraph):
            para = doc_item

            # 段落級別的插入修訂
            if para.IsInsertRevision:
                index_insert += 1
                insert_revisions.append(format_revision(index_insert, para.InsertRevision, para.Text))

            # 段落級別的刪除修訂
            elif para.IsDeleteRevision:
                index_delete += 1
                delete_revisions.append(format_revision(index_delete, para.DeleteRevision, para.Text))

            # 遍歷段落中的所有子對象
            for j in range(para.ChildObjects.Count):
                obj = para.ChildObjects.get_Item(j)

                # 判斷對象是否為文本范圍
                if isinstance(obj, TextRange):
                    text_range = obj

                    # 文本級別的插入修訂
                    if text_range.IsInsertRevision:
                        index_insert += 1
                        insert_revisions.append(format_revision(index_insert, text_range.InsertRevision, text_range.Text))

                    # 文本級別的刪除修訂
                    elif text_range.IsDeleteRevision:
                        index_delete += 1
                        delete_revisions.append(format_revision(index_delete, text_range.DeleteRevision, text_range.Text))

# 將結(jié)果保存到文本文件
save_text(output_insert, "\n".join(insert_revisions))
save_text(output_delete, "\n".join(delete_revisions))