pip install python-docx

from docx import Document
from datetime import datetime

def get_doc_properties(doc_path):
    doc = Document(doc_path)
    core_props = doc.core_properties
    
    info = {
        "標(biāo)題": core_props.title,
        "作者": core_props.author,
        "分類": core_props.category,
        "狀態(tài)": core_props.content_status,
        "創(chuàng)建時(shí)間": core_props.created,
        "修改時(shí)間": core_props.modified,
        "最后保存者": core_props.last_modified_by,
        "修訂次數(shù)": core_props.revision
    }
    return info

props = get_doc_properties("項(xiàng)目報(bào)告.docx")
for key, value in props.items():
    print(f"{key}: {value}")

def count_word_document(doc_path):
    doc = Document(doc_path)
    
    total_chars = 0
    
    for paragraph in doc.paragraphs:
        text = paragraph.text.strip()
        total_chars += len(text)
    
    for table in doc.tables:
        for row in table.rows:
            for cell in row.cells:
                text = cell.text.strip()
                total_chars += len(cell.text)
    
    return total_chars

word_count = count_word_document("項(xiàng)目報(bào)告.docx")
print(f"文檔總字符數(shù): {word_count}")

def count_with_headers(doc_path):
    doc = Document(doc_path)
    total_chars = 0
    
    for paragraph in doc.paragraphs:
        total_chars += len(paragraph.text)
    
    for table in doc.tables:
        for row in table.rows:
            for cell in row.cells:
                total_chars += len(cell.text)
    
    for section in doc.sections:
        header = section.header
        for paragraph in header.paragraphs:
            total_chars += len(paragraph.text)
        
        footer = section.footer
        for paragraph in footer.paragraphs:
            total_chars += len(paragraph.text)
    
    return total_chars

def estimate_pages(doc_path):
    doc = Document(doc_path)
    page_breaks = sum(1 for p in doc.paragraphs if p.contains_page_break)
    return page_breaks + 1

import os
from docx import Document
from datetime import datetime

def analyze_doc(doc_path):
    try:
        doc = Document(doc_path)
        props = doc.core_properties
        
        char_count = 0
        for para in doc.paragraphs:
            char_count += len(para.text)
        for table in doc.tables:
            for row in table.rows:
                for cell in row.cells:
                    char_count += len(cell.text)
        
        return {
            "文件": os.path.basename(doc_path),
            "字符數(shù)": char_count,
            "作者": props.author,
            "創(chuàng)建時(shí)間": props.created.strftime("%Y-%m-%d") if props.created else "未知"
        }
    except Exception as e:
        print(f"處理失敗 {doc_path}: {e}")
        return None

folder = "./reports"
for filename in os.listdir(folder):
    if filename.endswith(".docx"):
        full_path = os.path.join(folder, filename)
        result = analyze_doc(full_path)
        if result:
            print(f"{result['文件']} - {result['字符數(shù)']}字 - {result['作者']}")