Online-Examination-System/extract_plan_sources.py

# -*- coding: utf-8 -*-
from pathlib import Path
from docx import Document

ROOT = Path(__file__).resolve().parent
FILES = [
    "在线考试系统技术文案（方案B）.docx",
    "在线考试系统两方案可行性评审报告.docx",
]
for name in FILES:
    doc = Document(ROOT / name)
    out = []
    out.append(f"SOURCE: {name}")
    for block in doc.element.body.iterchildren():
        if block.tag.endswith("}p"):
            for p in doc.paragraphs:
                if p._p is block:
                    if p.text.strip():
                        out.append(f"[{p.style.name}] {p.text}")
                    break
        elif block.tag.endswith("}tbl"):
            for table in doc.tables:
                if table._tbl is block:
                    out.append("[TABLE]")
                    for row in table.rows:
                        out.append(" | ".join(cell.text.replace("\n", " / ") for cell in row.cells))
                    out.append("[/TABLE]")
                    break
    target = ROOT / (Path(name).stem + "_提取.txt")
    target.write_text("\n".join(out), encoding="utf-8")
    print(f"{target.name}: {len(out)} blocks")