pptx-notes-editor

PPTX Notes Editor 工作流 Decision Tree User 请求 ├── Modify Notes → 1,2,3,4,5,6 ├── 导出 to MD Only → 1,2 → 7 ├── Pack Existing Content Only → 5 (optional 验证 → 6) └── Unpack and View Only → 1

• Unpack PPTX

# Unpack to specified directory mkdir -p pptx-unpacked && unzip your-presentation.pptx -d pptx-unpacked

File Structure:

pptx-unpacked/ ├── ppt/ │ ├── slides/ # Slides │ │ ├── slide1.xml │ │ ├── slide2.xml │ │ └── _rels/ # Slide relationships │ │ ├── slide1.xml.rels │ │ └── slide2.xml.rels │ ├── notesSlides/ # Notes files │ │ ├── notesSlide1.xml │ │ └── notesSlide2.xml │ └── _rels/ │ └── presentation.xml.rels └── [Content_Types].xml

• Confirm Slide-to-Notes M应用ing

导入ant: The numbering of notesSlideN.xml does NOT necessarily cor响应 to PPT page numbers! You MUST confirm via the relationship files.

Method 1: 检查 Precise M应用ing (Recommended) # 检查 which notes file cor响应s to slide N cat pptx-unpacked/ppt/slides/_rels/slideN.xml.rels | grep -i "notesSlide"

# Example 输出: # # This means slideN.xml cor响应s to notesSlide2.xml

Method 2: Quick View All M应用ings # 列出 all slide-to-notes cor响应ences for f in pptx-unpacked/ppt/slides/_rels/slide.xml.rels; do slide=$(basename "$f" .xml.rels) notes=$(grep -o 'notesSlide[0-9]\.xml' "$f" | head -1) if [ -n "$notes" ]; then echo "$slide -> $notes" fi done

Edge Cases Slide has no notes: grep returns no 输出, this slide has no notes Notes file exists but no cor响应ing slide: may be orphaned notes, can be ignored

• Read Notes Content

XML Namespace Reference

PPTX XML uses these namespace prefixes:

a: - DrawingML namespace (text, shapes) p: - PresentationML namespace (slide structure) r: - Relationships namespace

Notes text is inside tags.

Method 1: Read Page by Page # 列出 all notes files ls pptx-unpacked/ppt/notesSlides/

# Use file reading 工具 to read individual notes file # Notes text is in tags

Method 2: Batch 提取 All Notes Text # 提取 text from all notes files (macOS compatible) grep -oh '[^<]' pptx-unpacked/ppt/notesSlides/.xml | sed 's/\([^<]\)<\/a:t>/\1/g' | head -50

Method 3: 提取 Single Page Notes by File # 提取 all text from notesSlide2.xml (macOS compatible) grep -oh '[^<]' pptx-unpacked/ppt/notesSlides/notesSlide2.xml | sed 's/\([^<]\)<\/a:t>/\1/g'

Handling XML Escaped Characters

Notes text may contAIn these escape sequences:

< → < > → > & → & " → "

Decode with sed:

sed 's/<//g; s/&/\&/g; s/"/"/g'

• Rewrite in Narrative Style

Narrative Style 图形界面delines Tell a story with beginning, development, turning point, and conclusion Conversational and natural transitions Specific examples and scenarios as support 创建 empathy and engagement with the audience 导入ant Notes MUST confirm before modifying: After generating notes draft, show it to the user and 获取 explicit confirmation before executing any XML modification. Do NOT modify any notes without user confirmation If the original PPT notes are dry bullet-point 列出s, you need to completely rewrite them in narrative style If the original notes are already in narrative style, you can refine and improve them Do NOT assume "keep the original style" - determine the style based on the tar获取 presentation 上下文 Modification Process Step 0: Ask user to select page range and notes style

Present the user with the following choices before 启动ing:

Page Range Selection:

All pages Only pages without notes Only pages with existing notes Custom range (user 输入s e.g. "1-5,8,10-12")

Notes Style Selection:

Narrative style (storytelling, conversational, with beginning/development/命令行工具max/conclusion) Concise bullet points (distill key in格式化ion, brief and powerful) Verbatim script (complete spoken script that can be read aloud directly) Custom style (user describes desired style)

Language Selection (optional):

Keep original language Chinese English Step 1: Read through entire PPT content (build global 上下文)

Before modifying page by page, you MUST read through all slides to build global 上下文:

# Batch 提取 text summary from all slides (macOS compatible) for f in pptx-unpacked/ppt/slides/slide.xml; do slide=$(basename "$f" .xml) echo "=== $slide ===" grep -oh '[^<]' "$f" | sed 's/\([^<]\)<\/a:t>/\1/g' echo "" done

After reading, present a global overview to the user:

[PPT Global Overview] Total: X pages, Theme: xxx Page 1: Opening - xxx Page 2: Background - xxx Page 3: Core argument - xxx ... Page X: Summary - xxx

Narrative arc: xxx → xxx → xxx

Purpose of reading through:

Understand the overall narrative arc and 记录ical structure Know each page's 角色 (设置up, core argument