# -*- coding: utf-8 -*-
import zipfile, re, html, os

docx = r"docx/邮件/模板/附件下载_邮件识别/邮件识别.docx"
with zipfile.ZipFile(docx) as z:
    xml = z.read("word/document.xml").decode("utf-8")
text = re.sub(r"<w:tab[^/]*/>", "\t", xml)
text = re.sub(r"</w:p>", "\n", text)
text = re.sub(r"<[^>]+>", "", text)
text = html.unescape(text)
text = re.sub(r"\n{3,}", "\n\n", text)
out = r"data/logs/mail-recognize-docx.txt"
os.makedirs("data/logs", exist_ok=True)
open(out, "w", encoding="utf-8").write(text)
print(out, "chars", len(text))
print(text[:4000])