Online-Examination-System/dump_docx.py

# -*- coding: utf-8 -*-
import zipfile, re, json, sys, io
sys.stdout.reconfigure(encoding="utf-8")
p = r"C:\Users\aroun\Desktop\在线考试系统\在线考试系统技术文案（方案B）.docx"
z = zipfile.ZipFile(p)
xml = z.read("word/document.xml").decode("utf-8")
paras = re.findall(r"<w:p[ >].*?</w:p>", xml, re.S)
out = []
for pa in paras:
    texts = re.findall(r"<w:t[^>]*>(.*?)</w:t>", pa, re.S)
    t = "".join(texts)
    t = t.replace("&amp;", "&").replace("&lt;", "<").replace("&gt;", ">").replace("&quot;", '"')
    m = re.search(r'<w:pStyle w:val="([^"]+)"', pa)
    out.append({"style": m.group(1) if m else "", "text": t})
with open(r"C:\Users\aroun\Desktop\在线考试系统\_paras.json", "w", encoding="utf-8") as f:
    json.dump(out, f, ensure_ascii=False, indent=0)
print("paras", len(out))