import re
import zipfile
from pathlib import Path
from xml.etree import ElementTree as ET

# 1
def extract_text_from_docx(docx_path):
    text = ""
    try:
        with zipfile.ZipFile(docx_path) as docx_zip:
            with docx_zip.open('word/document.xml') as document_xml:
                tree = ET.parse(document_xml)
                root = tree.getroot()
                for elem in root.iter():
                    if elem.tag.endswith('}t'):
                        text += elem.text + ' '
    except Exception as e:
        print(f"Error processing {docx_path}: {e}")
    return text.strip()

# 2
def find_idcards(text: str) -> list:
    results = []
    pattern_18 = r'\b(\d{17}[\dXx])\b'

    for match in re.finditer(pattern_18, text):
        id_num = match.group(1)
        if id_num not in results:
            results.append(id_num)
    return results

if __name__ == '__main__':
    all_results = []
    docx_files = list(Path("./docs").rglob('*.docx'))
    total = len(docx_files)
    print(f"找到 {total} 个 Word 文档")
    idcard = []
    for i, filepath in enumerate(docx_files, 1):
        text = extract_text_from_docx(filepath)
        idcards = find_idcards(text)
        if len(idcards) > 0:
            print(f"[{i}/{total}] 扫描: {filepath.name} - 发现 {len(idcards)} 个身份证号")