python-pptxで作った提案資料に、自分で入れていない更新者名と「4:3」が残っていた

from pptx import Presentation
from pptx.util import Inches

prs = Presentation()
prs.slide_width = Inches(13.333)
prs.slide_height = Inches(7.5)

s1 = prs.slides.add_slide(prs.slide_layouts[0])
s1.shapes.title.text = "提案資料テンプレート"
s1.placeholders[1].text = "会社名をここに入れてください"

s2 = prs.slides.add_slide(prs.slide_layouts[1])
s2.shapes.title.text = "課題の整理"
s2.placeholders[1].text = "現状の3つの課題を書く"
s2.notes_slide.notes_text_frame.text = "値引きは10%まで。それ以上は断る。"

s3 = prs.slides.add_slide(prs.slide_layouts[1])
s3.shapes.title.text = "原価メモ"
s3.placeholders[1].text = "仕入れ原価は定価の42%"
s3._element.set("show", "0")  # 非表示スライド

prs.save("sample-deck.pptx")
print("saved", len(prs.slides), "slides")

import re, sys, zipfile
import xml.etree.ElementTree as ET

NS = {
    "a": "http://schemas.openxmlformats.org/drawingml/2006/main",
    "p": "http://schemas.openxmlformats.org/presentationml/2006/main",
    "dc": "http://purl.org/dc/elements/1.1/",
    "cp": "http://schemas.openxmlformats.org/package/2006/metadata/core-properties",
    "dcterms": "http://purl.org/dc/terms/",
    "ep": "http://schemas.openxmlformats.org/officeDocument/2006/extended-properties",
}

def check(path, allow=()):
    z = zipfile.ZipFile(path)
    names = z.namelist()
    found = []

    slides = sorted(n for n in names if re.fullmatch(r"ppt/slides/slide\d+\.xml", n))
    for n in slides:
        root = ET.fromstring(z.read(n))
        if root.get("show") == "0":
            found.append(f"hidden-slide  {n}")

    for n in sorted(x for x in names if re.fullmatch(r"ppt/notesSlides/notesSlide\d+\.xml", x)):
        text = "".join(t.text or "" for t in ET.fromstring(z.read(n)).iter(f"{{{NS['a']}}}t"))
        if text.strip():
            found.append(f"notes         {n}: {text.strip()[:30]}")

    core = ET.fromstring(z.read("docProps/core.xml"))
    for tag in ("dc:creator", "cp:lastModifiedBy", "dc:description"):
        v = (core.findtext(tag, namespaces=NS) or "").strip()
        if v and v not in allow:
            found.append(f"core          {tag} = {v}")
    created = core.findtext("dcterms:created", namespaces=NS) or ""
    if created[:4] and int(created[:4]) < 2020:
        found.append(f"core          created = {created} (template date)")

    sz = ET.fromstring(z.read("ppt/presentation.xml")).find("p:sldSz", NS)
    cx, cy = int(sz.get("cx")), int(sz.get("cy"))
    app = ET.fromstring(z.read("docProps/app.xml"))
    fmt = app.findtext("ep:PresentationFormat", namespaces=NS) or ""
    if "4:3" in fmt and cx / cy > 1.5:
        found.append(f"app           PresentationFormat = {fmt} but size is {cx}x{cy}")
    if sz.get("type") == "screen4x3" and cx / cy > 1.5:
        found.append(f"presentation  sldSz type=screen4x3 but size is {cx}x{cy}")
    n_app = int(app.findtext("ep:Slides", namespaces=NS) or 0)
    if n_app != len(slides):
        found.append(f"app           Slides = {n_app} but {len(slides)} slide files")

    if "docProps/thumbnail.jpeg" in names:
        found.append(f"thumbnail     docProps/thumbnail.jpeg ({z.getinfo('docProps/thumbnail.jpeg').file_size} bytes)")

    for n in names:
        if n.startswith("ppt/comments/") or n == "ppt/commentAuthors.xml":
            found.append(f"comments      {n}")
        if n.endswith(".rels"):
            for rel in ET.fromstring(z.read(n)):
                if rel.get("TargetMode") == "External":
                    found.append(f"external-link {n}: {rel.get('Target')}")
    return found

if __name__ == "__main__":
    allow = tuple(sys.argv[2:])
    items = check(sys.argv[1], allow)
    for i in items:
        print(i)
    print(f"{len(items)} findings")
    sys.exit(1 if items else 0)

import datetime as dt
from pptx import Presentation

prs = Presentation("sample-deck.pptx")

# 非表示スライドを外す
sld_ids = prs.slides._sldIdLst
for sld_id in list(sld_ids):
    slide = prs.slides.get(int(sld_id.get("id")))
    if slide._element.get("show") == "0":
        prs.part.drop_rel(sld_id.rId)
        sld_ids.remove(sld_id)

# ノートを空にする
for slide in prs.slides:
    if slide.has_notes_slide:
        slide.notes_slide.notes_text_frame.text = ""

# コア情報を自分の値にそろえる
cp = prs.core_properties
now = dt.datetime.now(dt.timezone.utc).replace(microsecond=0, tzinfo=None)
cp.author = "hibanas"
cp.last_modified_by = "hibanas"
cp.comments = ""
cp.created = now
cp.modified = now
cp.title = "提案資料テンプレート"

prs.save("clean-deck.pptx")
print("saved", len(prs.slides), "slides")

import re, sys, zipfile

src, dst = sys.argv[1], sys.argv[2]
zin = zipfile.ZipFile(src)
n_slides = len([n for n in zin.namelist() if re.fullmatch(r"ppt/slides/slide\d+\.xml", n)])
n_notes = len([n for n in zin.namelist() if re.fullmatch(r"ppt/notesSlides/notesSlide\d+\.xml", n)])

APP = (
    '<?xml version="1.0" encoding="UTF-8" standalone="yes"?>\n'
    '<Properties xmlns="http://schemas.openxmlformats.org/officeDocument/2006/extended-properties">'
    f"<Slides>{n_slides}</Slides><Notes>{n_notes}</Notes><HiddenSlides>0</HiddenSlides>"
    "<PresentationFormat>Widescreen</PresentationFormat></Properties>"
)

with zipfile.ZipFile(dst, "w", zipfile.ZIP_DEFLATED) as zout:
    for item in zin.infolist():
        if item.filename == "docProps/thumbnail.jpeg":
            continue
        data = zin.read(item.filename)
        if item.filename == "docProps/app.xml":
            data = APP.encode("utf-8")
        elif item.filename == "ppt/presentation.xml":
            data = data.replace(b' type="screen4x3"', b"")
        elif item.filename == "_rels/.rels":
            data = re.sub(rb'<Relationship [^>]*metadata/thumbnail[^>]*/>', b"", data)
        zout.writestr(item.filename, data)
print("written", dst)