一个全自动处理word文档广告内容的python脚本

import os
import win32com.client
from docx import Document
import re
import shutil
import zipfile

def unzip_all_archives(folder_path):
    for file in os.listdir(folder_path):
        if file.lower().endswith(".zip"):
            file_path = os.path.join(folder_path, file)
            try:
                with zipfile.ZipFile(file_path, 'r') as zip_ref:
                    for member in zip_ref.infolist():
                        # 尝试修正中文乱码：原始文件名是 cp437 → 解码成 gbk
                        try:
                            corrected_name = member.filename.encode('cp437').decode('gbk')
                        except UnicodeDecodeError:
                            corrected_name = member.filename  # fallback

                        target_path = os.path.join(folder_path, corrected_name)

                        # 确保目录存在
                        if member.is_dir():
                            os.makedirs(target_path, exist_ok=True)
                        else:
                            os.makedirs(os.path.dirname(target_path), exist_ok=True)
                            with open(target_path, 'wb') as f:
                                f.write(zip_ref.read(member))

                print(f"[解压] 已解压（含中文修复）：{file}")
            except Exception as e:
                print(f"[错误] 解压失败：{file} - {e}")
def convert_doc_to_docx(doc_path):
    word = win32com.client.Dispatch("Word.Application")
    word.Visible = False
    doc = word.Documents.Open(doc_path)
    docx_path = doc_path + "x"
    doc.SaveAs(docx_path, FileFormat=16)

    # 清除页眉页脚
    for section in doc.Sections:
        for hdr in [section.Headers(1), section.Footers(1)]:
            try:
                # 清除内容
                hdr.Range.Delete()

                # 移除段落边框线（横线）
                for para in hdr.Range.Paragraphs:
                    borders = para.Borders
                    for i in range(1, 7):  # 1~6：上下左右及内外边框
                        borders(i).LineStyle = 0  # 0 = wdLineStyleNone

                # 清除页脚页码字段（如果有）
                fields = hdr.Range.Fields
                for f in reversed(range(fields.Count)):
                    try:
                        fields.Item(f + 1).Delete()
                    except:
                        pass

            except Exception as e:
                print(f"[警告] 清除页眉/页脚样式失败：{e}")

    doc.Close()
    word.Quit()
    print(f"[转换+清除页眉页脚] 成功：{os.path.basename(docx_path)}")
    return docx_path


def delete_paragraphs(doc, indices):
    for i in sorted(indices, reverse=True):
        doc._body._element.remove(doc.paragraphs[i]._element)


def delete_empty_paragraphs_above_title(doc, keyword="合同"):
    for i, para in enumerate(doc.paragraphs):
        if keyword in para.text.strip():
            to_delete = []
            for j in range(i - 1, -1, -1):
                if doc.paragraphs[j].text.strip() == "":
                    to_delete.append(j)
                else:
                    break
            delete_paragraphs(doc, to_delete)
            print(f"[处理] 删除标题上方空段落：{len(to_delete)} 段")
            break


def delete_single_empty_paragraph_above_title(doc, keywords=("合同", "协议")):
    for i, para in enumerate(doc.paragraphs):
        if any(k in para.text for k in keywords):
            if i > 0 and doc.paragraphs[i - 1].text.strip() == "":
                delete_paragraphs(doc, [i - 1])
                print("[处理] 删除标题前的 1 个空段落")
            else:
                print("[跳过] 标题上方无空段落")
            break


def delete_after_title(doc, keywords=("合同", "协议", "书"), lines=6):
    for i, para in enumerate(doc.paragraphs):
        text = para.text.strip()
        if any(keyword in text for keyword in keywords):
            delete_paragraphs(doc, list(range(i + 1, i + 1 + lines)))
            print(f"[处理] 删除标题“{text}”下方的 {lines} 行")
            break


def delete_trailing_ad_and_blank_pages(doc):
    keywords = ["法宝", "pkulaw", "下载日期", "原文链接", "扫描二维码", "©", "https://", "www."]
    total = len(doc.paragraphs)
    to_delete = []

    for i in range(total - 1, -1, -1):
        para = doc.paragraphs[i]
        text = para.text.strip()

        if text == "":
            to_delete.append(i)
            continue

        if any(k in text for k in keywords):
            to_delete.append(i)
            continue

        if to_delete:
            break

    if to_delete:
        delete_paragraphs(doc, to_delete)
        print(f"[处理] 删除尾部广告/空段落：{len(to_delete)} 段")


def process_docx(docx_path, output_path):
    doc = Document(docx_path)
    delete_single_empty_paragraph_above_title(doc)
    delete_empty_paragraphs_above_title(doc)
    delete_after_title(doc, keywords=("合同", "协议", "书"), lines=6)
    delete_trailing_ad_and_blank_pages(doc)
    doc.save(output_path)
    print(f"[完成] 保存为：{os.path.basename(output_path)}")

def delete_processed_doc_folder(folder_path):
    processed_folder = os.path.join(folder_path, "已处理原文件")
    if os.path.exists(processed_folder):
        try:
            shutil.rmtree(processed_folder)
            print(f"[清理] 已删除文件夹：{processed_folder}")
        except Exception as e:
            print(f"[错误] 删除文件夹失败：{e}")
    else:
        print("[跳过] 没有已处理原文件夹，无需删除")

def delete_unnumbered_docx_files(folder_path):
    pattern = re.compile(r"^\d+_.*\.docx$", re.IGNORECASE)
    for file in os.listdir(folder_path):
        if file.lower().endswith(".docx") and not pattern.match(file):
            try:
                os.remove(os.path.join(folder_path, file))
                print(f"[清理] 删除未编号文件：{file}")
            except Exception as e:
                print(f"[错误] 删除 {file} 失败：{e}")


def process_all_docs_in_folder(folder_path):
    unzip_all_archives(folder_path)  # ✅ 自动解压所有 zip
    processed_folder = os.path.join(folder_path, "已处理原文件")
    os.makedirs(processed_folder, exist_ok=True)

    counter = 1  # 从1开始编号

    for file in os.listdir(folder_path):
        if file.lower().endswith(".doc") and not file.lower().endswith(".docx"):
            full_path = os.path.join(folder_path, file)

            try:
                # 转换为 docx 并清除页眉页脚
                docx_path = convert_doc_to_docx(full_path)

                # 构造简洁输出名（保留前缀）并加编号
                prefix = file.split("(")[0].strip()
                output_file = f"{counter}_{prefix}.docx"
                output_path = os.path.join(folder_path, output_file)

                process_docx(docx_path, output_path)

                # 移动原始 .doc 文件
                os.rename(full_path, os.path.join(processed_folder, file))
                print(f"[移动] 已移动原始文件至：{processed_folder}")

                counter += 1  # 编号递增

            except Exception as e:
                print(f"[错误] 处理 {file} 失败：{e}")
    delete_unnumbered_docx_files(folder_path)
    print("[完成] 所有文件处理完成，已清理未编号 .docx 文件")
    delete_processed_doc_folder(folder_path)  # ✅ 删除已处理原文件夹
    print("[完成] 所有文件处理完成，环境已清理")
    delete_zip_files(folder_path)  # ✅ 删除所有 zip

def delete_zip_files(folder_path):
    for file in os.listdir(folder_path):
        if file.lower().endswith(".zip"):
            try:
                os.remove(os.path.join(folder_path, file))
                print(f"[清理] 已删除压缩包：{file}")
            except Exception as e:
                print(f"[错误] 删除压缩包失败：{file} - {e}")



# ========= 修改为你的文件夹路径 =========
folder = r"D:\U盘备份资料\合同范本\7建设工程合同 (712)\2工程设计合同 (41)"  # ← 替换为你自己的路径
process_all_docs_in_folder(folder)