AiDOPWarehouse/doc/_tmp_read_bp_text.py

# -*- coding: utf-8 -*-
"""导出无图蓝图（S9/运营诊断/运营改善/系统集成/ChatBI）的正文与表格，供撰写技术方案取材。"""

import os
import shutil
import sys
import tempfile

sys.stdout.reconfigure(encoding="utf-8", errors="replace")

from docx import Document
from docx.oxml.ns import qn
from docx.table import Table
from docx.text.paragraph import Paragraph

ROOT = r"C:\Users\skygu\OneDrive\Projects\AIDOP\项目\项目管理\产互联项目管理\交付文档"
OUT = os.path.join(os.path.dirname(os.path.abspath(__file__)),
                   "_tmp_bp_text.txt")

FILES = [
    "S9/S9运营指标与智慧看板模块蓝图设计方案.docx",
    "运营诊断/运营诊断模块蓝图设计方案.docx",
    "运营改善/运营改善模块蓝图设计方案.docx",
    "系统集成/系统集成模块蓝图设计方案.docx",
    "ChatBI/ChatBI智能报表模块蓝图设计方案.docx",
]

tmpdir = tempfile.mkdtemp()
out = []
for rel in FILES:
    src = os.path.join(ROOT, rel.replace("/", os.sep))
    local = os.path.join(tmpdir, os.path.basename(src))
    shutil.copy2(src, local)
    doc = Document(local)
    out.append("\n" + "#" * 80)
    out.append(f"### {rel}")
    out.append("#" * 80)
    for el in doc.element.body.iterchildren():
        if el.tag == qn("w:p"):
            p = Paragraph(el, doc)
            t = p.text.strip()
            if not t:
                continue
            s = p.style.name if p.style is not None else ""
            pref = f"[{s}] " if s.startswith(("Heading", "标题")) else ""
            out.append(pref + t)
        elif el.tag == qn("w:tbl"):
            tb = Table(el, doc)
            out.append(f"--- TABLE {len(tb.rows)}x{len(tb.columns)} ---")
            for r in tb.rows:
                seen, cells = set(), []
                for c in r.cells:
                    if c._tc in seen:
                        continue
                    seen.add(c._tc)
                    cells.append(c.text.strip().replace("\n", " / "))
                out.append("   | " + " | ".join(cells))

shutil.rmtree(tmpdir, ignore_errors=True)
with open(OUT, "w", encoding="utf-8") as f:
    f.write("\n".join(out))
print(f"导出 {len(FILES)} 份 -> {OUT}  ({sum(len(x) for x in out):,} 字符)")