#!/usr/bin/env python3 """Extract embedded PPTX videos and report their slide references and metadata.""" import argparse import html import json import os import posixpath import re import shutil import subprocess import sys import tempfile import zipfile from collections import defaultdict from pathlib import Path from urllib.parse import quote from xml.etree import ElementTree as ET VIDEO_EXTS = {'.mp4', '.m4v', '.mov', '.avi', '.wmv', '.webm', '.mpg', '.mpeg', '.mkv', '.asf', '.3gp', '.ts'} REL_NS = 'http://schemas.openxmlformats.org/package/2006/relationships' R_NS = 'http://schemas.openxmlformats.org/officeDocument/2006/relationships' P_NS = 'http://schemas.openxmlformats.org/presentationml/2006/main' REPORT_FORMATS = ('html', 'typst', 'pdf', 'md', 'txt', 'json') HEADERS = ('Slide(s)', 'Duration', 'Video', 'Size', 'Resolution', 'Codec') REPORT_NOTES = ( 'Duration is the original media file duration, not slide playback time ' '(PowerPoint trimming, looping, and animation are not applied).', 'Videos linked externally are not downloaded. Slide numbers follow presentation order.', ) def status(message, level='info'): """Keep redirected output plain and flush progress before slow operations.""" stream = sys.stderr if level in ('warning', 'error') else sys.stdout label, color = { 'info': ('INFO', '36'), 'success': ('OK', '32'), 'warning': ('WARN', '33'), 'error': ('ERROR', '31'), }[level] prefix = f'[{label}]' if stream.isatty() and 'NO_COLOR' not in os.environ and os.environ.get('TERM') != 'dumb': prefix = f'\033[{color}m{prefix}\033[0m' print(f'{prefix} {message}', file=stream, flush=True) def xml(z, name): try: return ET.fromstring(z.read(name)) except (KeyError, ET.ParseError): return None def rels(z, source): directory, basename = posixpath.split(source) path = posixpath.join(directory, '_rels', basename + '.rels') root = xml(z, path) if root is None: return {} result = {} for rel in root.findall(f'{{{REL_NS}}}Relationship'): rid = rel.get('Id') target = rel.get('Target', '') if not rid: continue if rel.get('TargetMode', '').lower() == 'external': result[rid] = (None, rel.get('Type', '')) else: # Targets can be package-root absolute or relative to the source part. target = target.split('#', 1)[0].split('?', 1)[0] resolved = posixpath.normpath(target.lstrip('/') if target.startswith('/') else posixpath.join(directory, target)) result[rid] = (resolved, rel.get('Type', '')) return result def slide_paths(z): root = xml(z, 'ppt/presentation.xml') mapping = rels(z, 'ppt/presentation.xml') if root is not None: ordered = [] for slide in root.findall(f'.//{{{P_NS}}}sldId'): target = mapping.get(slide.get(f'{{{R_NS}}}id'), (None, ''))[0] if target: ordered.append(target) if ordered: return ordered return sorted((n for n in z.namelist() if re.fullmatch(r'ppt/slides/slide\d+\.xml', n)), key=lambda n: int(re.search(r'slide(\d+)', n).group(1))) def discover(z): """Map actual archive media parts to presentation-order slide numbers.""" names = set(z.namelist()) videos = sorted((n for n in names if n.startswith('ppt/media/') and Path(n).suffix.lower() in VIDEO_EXTS)) uses = defaultdict(set) external = set() for index, slide in enumerate(slide_paths(z), 1): root = xml(z, slide) if root is None: continue mapping = rels(z, slide) # Only relationships referenced by videoFile or p14:media elements; # excludes audio-only attachments and poster images. for el in root.iter(): tag = el.tag.rsplit('}', 1)[-1] if tag not in ('videoFile', 'media'): continue for attr in (f'{{{R_NS}}}link', f'{{{R_NS}}}embed'): rid = el.get(attr) if not rid or rid not in mapping: continue target, rel_type = mapping[rid] if tag == 'media' and not rel_type.endswith('/media'): continue if target is None: if tag == 'videoFile' or rel_type.endswith('/media'): external.add(index) elif target in names and Path(target).suffix.lower() in VIDEO_EXTS: uses[target].add(index) return videos, uses, external def size_fmt(n): for unit in ('B', 'KiB', 'MiB', 'GiB', 'TiB'): if n < 1024 or unit == 'TiB': return f'{n:.0f} {unit}' if unit == 'B' else f'{n:.2f} {unit}' n /= 1024 def time_fmt(seconds): if seconds is None: return 'Unknown' millis = round(seconds * 1000) h, rem = divmod(millis, 3600000) m, rem = divmod(rem, 60000) s, ms = divmod(rem, 1000) return f'{h:02}:{m:02}:{s:02}.{ms:03}' def probe(path): try: p = subprocess.run(['ffprobe', '-v', 'error', '-show_entries', 'format=duration:stream=codec_type,width,height,codec_name', '-of', 'json', str(path)], capture_output=True, text=True, check=True) data = json.loads(p.stdout) duration = data.get('format', {}).get('duration') duration = float(duration) if duration not in (None, 'N/A') else None streams = data.get('streams', []) video = next((s for s in streams if s.get('codec_type') == 'video'), {}) resolution = f"{video['width']}×{video['height']}" if video.get('width') and video.get('height') else 'Unknown' return duration, resolution, video.get('codec_name', 'Unknown') except (subprocess.CalledProcessError, OSError, ValueError, json.JSONDecodeError): return None, 'Unknown', 'Unknown' def esc(s): return str(s).replace('|', '\\|').replace('\n', ' ') def aligned_table(cells, markdown=True): headers = HEADERS widths = [max(3, *(len(row[i]) for row in [headers, *cells])) for i in range(len(headers))] right_aligned = {1, 3} def render(row): return '| ' + ' | '.join( value.rjust(widths[i]) if i in right_aligned else value.ljust(widths[i]) for i, value in enumerate(row) ) + ' |' separators = [ '-' * (width - 1) + ':' if markdown and i in right_aligned else '-' * width for i, width in enumerate(widths) ] return [render(headers), render(separators), *(render(row) for row in cells)] def report_formats(value): formats = [item.strip().lower() for item in value.split(',')] if any(item not in REPORT_FORMATS for item in formats): raise argparse.ArgumentTypeError('Choose comma-separated formats from: ' + ', '.join(REPORT_FORMATS)) return formats def report_data(source, rows, uses, external, out): videos = [] for part, name, size, duration, resolution, codec in sorted( rows, key=lambda row: (min(uses[row[0]], default=float('inf')), row[1])): videos.append({ 'slides': sorted(uses[part]), 'duration_seconds': duration, 'name': name, 'size_bytes': size, 'resolution': resolution, 'codec': codec, 'archive_path': part, 'extracted_file': name if (out / name).is_file() else None, }) return { 'presentation': source.name, 'embedded_videos': len(videos), 'total_size_bytes': sum(v['size_bytes'] for v in videos), 'total_duration_seconds': sum(v['duration_seconds'] for v in videos if v['duration_seconds'] is not None), 'known_durations': sum(v['duration_seconds'] is not None for v in videos), 'videos': videos, 'external_media_slides': sorted(external), 'notes': list(REPORT_NOTES), } def typst_string(value): # Encode as a literal string, never as executable Typst markup. return '"' + ''.join( '\\' + c if c in ('\\', '"') else f'\\u{{{ord(c):x}}}' if ord(c) < 32 else c for c in value ) + '"' def render_report(data, format): title = f'Video timings — {data["presentation"]}' metrics = [ ('Embedded videos', str(data['embedded_videos'])), ('Total duration', time_fmt(data['total_duration_seconds'])), ('Total size', size_fmt(data['total_size_bytes'])), ('Durations available', f'{data["known_durations"]} / {data["embedded_videos"]}'), ] summary = [ f'Embedded videos: {data["embedded_videos"]}', f'Total size: {size_fmt(data["total_size_bytes"])}', f'Total duration: {time_fmt(data["total_duration_seconds"])} ' f'({data["known_durations"]}/{data["embedded_videos"]} successfully probed; each file counted once)', ] notes = list(data['notes']) if data['external_media_slides']: notes.append('Slides with external media links: ' + ', '.join(map(str, data['external_media_slides'])) + ' (not extracted).') cells = [ [', '.join(map(str, v['slides'])) or 'Unreferenced', time_fmt(v['duration_seconds']), v['name'], size_fmt(v['size_bytes']), v['resolution'], v['codec']] for v in data['videos'] ] if format == 'json': return json.dumps(data, ensure_ascii=False, indent=2, allow_nan=False) + '\n' if format in ('md', 'txt'): for row, video in zip(cells, data['videos']): row[:] = [esc(value) if format == 'md' else value.replace('\n', ' ') for value in row] if format == 'md' and video['extracted_file']: row[2] = f'[{row[2]}]({quote(video["extracted_file"])})' lines = [('# ' if format == 'md' else '') + title, ''] lines += ['- ' + line for line in summary] lines += ['', *aligned_table(cells, markdown=format == 'md'), ''] lines += [('> ' if format == 'md' else '') + note for note in notes] return '\n'.join(lines) + '\n' if format == 'html': table_rows = [] for row, video in zip(cells, data['videos']): row = [html.escape(value) for value in row] row[0] = ' '.join(f'' for slide in video['slides']) or 'Unreferenced' duration_class = 'duration' if video['duration_seconds'] is not None else 'warning' row[1] = f'{row[1]}' row[5] = f'{row[5]}' if video['extracted_file']: row[2] = f'{row[2]}' table_rows.append('
{html.escape(data["presentation"])}
| {heading} | ' for heading in HEADERS) + '
|---|