AiDOPWarehouse/doc/_tmp_read_xunbi.py

# -*- coding: utf-8 -*-
import os
import sys

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

src = r"d:\Projects\Ai-DOP\SourceCode\ZZYDOP\doc\_tmp_xunbi.docx"
out = r"d:\Projects\Ai-DOP\SourceCode\ZZYDOP\doc\_tmp_xunbi_extract.txt"

from docx import Document
from docx.table import Table
from docx.text.paragraph import Paragraph

doc = Document(src)


def iter_block_items(parent):
    from docx.document import Document as _Doc
    from docx.oxml.ns import qn

    if isinstance(parent, _Doc):
        parent_elm = parent.element.body
    else:
        parent_elm = parent._tc
    for child in parent_elm.iterchildren():
        if child.tag == qn("w:p"):
            yield Paragraph(child, parent)
        elif child.tag == qn("w:tbl"):
            yield Table(child, parent)


lines = []
idx = 0
for block in iter_block_items(doc):
    if isinstance(block, Paragraph):
        t = block.text.strip()
        if not t:
            continue
        idx += 1
        style = block.style.name if block.style is not None else ""
        lines.append(f"[P{idx}|{style}] {t}")
    else:
        idx += 1
        lines.append(f"[TABLE{idx}] rows={len(block.rows)} cols={len(block.columns)}")
        for ri, row in enumerate(block.rows):
            cells = [c.text.strip().replace("\n", " / ") for c in row.cells]
            lines.append("    | " + " | ".join(cells))

with open(out, "w", encoding="utf-8") as f:
    f.write("\n".join(lines))

print("wrote", out, os.path.getsize(out), "bytes,", len(lines), "lines")