Convert Word (DOCX) to Markdown With Python (Standard Library Only) for LLM Prompts and Chatbot Knowledge

#!/usr/bin/env python3 """Convert a .docx file to Markdown with the Python standard library only.""" import posixpath import re import sys import zipfile import xml.etree.ElementTree as ET from pathlib import Path W = "{http://schemas.openxmlformats.org/wordprocessingml/2006/main}" R = "{http://schemas.openxmlformats.org/officeDocument/2006/relationships}" A = "{http://schemas.openxmlformats.org/drawingml/2006/main}" WP = "{http://schemas.openxmlformats.org/drawingml/2006/wordprocessingDrawing}" PR = "{http://schemas.openxmlformats.org/package/2006/relationships}" def read_xml(z, name): try: return ET.fromstring(z.read(name)) except KeyError: return None def is_on(el): """<w:b/> means on; <w:b w:val="0"/> or "false" means off.""" return el is not None and el.get(W + "val", "true") not in ("0", "false", "none") class Docx: def __init__(self, path, media_dir=None): self.z = zipfile.ZipFile(path) self.media_dir = Path(media_dir) if media_dir else None self.heading_level = self._load_styles() self.num_formats = self._load_numbering() self.rels = self._load_rels() self.counters = {} def _load_styles(self): """Map styleId -> heading level, using the style name or outline level.""" levels, self.style_num, self.style_depth = {}, {}, {} root = read_xml(self.z, "word/styles.xml") if root is None: return levels for st in root.iter(W + "style"): sid = st.get(W + "styleId") name_el = st.find(W + "name") name = (name_el.get(W + "val") if name_el is not None else "").lower() m = re.fullmatch(r"heading (\d)", name) outline = st.find(f"{W}pPr/{W}outlineLvl") deep = re.fullmatch(r"list (?:bullet|number) (\d)", name) # "List Bullet 2"  if deep: self.style_depth[sid] = int(deep.group(1)) - 1 num = st.find(f"{W}pPr/{W}numPr") # list styles such as "List Bullet"  if num is not None and num.find(W + "numId") is not None: ilvl = num.find(W + "ilvl") self.style_num[sid] = (num.find(W + "numId").get(W + "val"), ilvl.get(W + "val") if ilvl is not None else "0") if name == "title": levels[sid] = 1 elif m: levels[sid] = int(m.group(1)) elif outline is not None: levels[sid] = int(outline.get(W + "val")) + 1 return levels def _load_numbering(self): """Map (numId, ilvl) -> numFmt such as 'bullet' or 'decimal'.""" fmts = {} root = read_xml(self.z, "word/numbering.xml") if root is None: return fmts abstract = {} for an in root.findall(W + "abstractNum"): lv = {} for lvl in an.findall(W + "lvl"): f = lvl.find(W + "numFmt") lv[lvl.get(W + "ilvl")] = f.get(W + "val") if f is not None else "bullet" abstract[an.get(W + "abstractNumId")] = lv for num in root.findall(W + "num"): ref = num.find(W + "abstractNumId").get(W + "val") for ilvl, fmt in abstract.get(ref, {}).items(): fmts[(num.get(W + "numId"), ilvl)] = fmt return fmts def _load_rels(self): rels = {} root = read_xml(self.z, "word/_rels/document.xml.rels") if root is not None: for rel in root.findall(PR + "Relationship"): rels[rel.get("Id")] = rel.get("Target") return rels # ---- inline content -------------------------------------------------  def runs(self, parent, link=None): """Yield (text, bold, italic, link) segments for a paragraph.""" for child in parent: if child.tag == W + "r": rpr = child.find(W + "rPr") bold = rpr is not None and is_on(rpr.find(W + "b")) ital = rpr is not None and is_on(rpr.find(W + "i")) for el in child: if el.tag == W + "t": yield el.text or "", bold, ital, link elif el.tag == W + "tab": yield " ", bold, ital, link elif el.tag in (W + "br", W + "cr"): yield "\n", False, False, None elif el.tag == W + "drawing": yield self.image(el), False, False, None elif child.tag == W + "hyperlink": rid = child.get(R + "id") target = self.rels.get(rid) if rid else None if target is None and child.get(W + "anchor"): target = "#" + child.get(W + "anchor") if target and not re.match(r"(https?:|mailto:|#)", target): target = None # drop javascript:, file: and other odd targets  yield from self.runs(child, target) elif child.tag in (W + "ins", W + "smartTag", W + "sdt", W + "sdtContent"): yield from self.runs(child, link) # tracked insertions, content controls  def image(self, drawing): blip = drawing.find(f".//{A}blip") doc_pr = drawing.find(f".//{WP}docPr") alt = (doc_pr.get("descr") or doc_pr.get("name") or "") if doc_pr is not None else "" target = self.rels.get(blip.get(R + "embed")) if blip is not None else None if not target: return "" name = posixpath.basename(target) if self.media_dir: self.media_dir.mkdir(parents=True, exist_ok=True) part = posixpath.normpath(posixpath.join("word", target)) (self.media_dir / name).write_bytes(self.z.read(part)) return f"![{alt}]({self.media_dir.name}/{name})" # relative to the .md file  return f"![{alt}]({name})" def inline(self, p): # merge neighbouring segments with the same formatting  merged = [] for text, b, i, link in self.runs(p): if merged and merged[-1][1:] == [b, i, link] and not text.startswith("!["): merged[-1][0] += text else: merged.append([text, b, i, link]) out = [] for text, b, i, link in merged: core = text.strip() if not core: out.append(text) continue lead = text[: len(text) - len(text.lstrip())] trail = text[len(text.rstrip()):] mark = "**" * b + "*" * i core = f"{mark}{core}{mark[::-1]}" if link: core = f"[{core}]({link})" out.append(lead + core + trail) return "".join(out) # ---- blocks ---------------------------------------------------------  def paragraph(self, p): self.last_num = None text = self.inline(p).strip() ppr = p.find(W + "pPr") style = ppr.find(W + "pStyle") if ppr is not None else None sid = style.get(W + "val") if style is not None else None num = ppr.find(W + "numPr") if ppr is not None else None if not text: return None if sid in self.heading_level: plain = text.replace("**", "").replace("\n", " ") # headings are bold already  return "#" * min(self.heading_level[sid], 6) + " " + plain num_id, ilvl = self.style_num.get(sid, (None, "0")) if num is not None and num.find(W + "numId") is not None: num_id = num.find(W + "numId").get(W + "val") ilvl_el = num.find(W + "ilvl") ilvl = ilvl_el.get(W + "val") if ilvl_el is not None else ilvl self.last_num = num_id if num_id and num_id != "0": fmt Source：https://dev.to/appierun_66/convert-word-docx-to-markdown-with-python-standard-library-only-for-llm-prompts-and-chatbot-5d15
My favorites