Initial commit

.gitattributes

@@ -0,0 +1,2 @@
+# Auto detect text files and perform LF normalization
+* text=auto

docx2md/docx2md.py

@@ -0,0 +1,103 @@
+import subprocess
+import os
+import re
+import json
+from pathlib import Path
+
+def convert_compact_mode(docx_file):
+    path_obj = Path(docx_file)
+    base_name = path_obj.stem
+    output_md = f"{base_name}_Compact.md"
+    media_folder = f"{base_name}_images"
+    metadata_file = f"{base_name}_metadata.json"
+    images_list_file = f"{base_name}_images.txt"
+    
+    # 1. 关键修改：使用 gfm 格式，强制生成紧凑表格
+    cmd = ["pandoc", docx_file, "-o", output_md, 
+           "--to=gfm",  # <--- 核心改动：使用 GitHub 风格，拒绝网格表
+           "--standalone", 
+           f"--extract-media={media_folder}", 
+           "--wrap=none", 
+           "--markdown-headings=atx"]
+    
+    try:
+        subprocess.run(cmd, check=True, capture_output=True)
+    except Exception as e:
+        print(f"❌ 转换出错: {e}")
+        return
+
+    with open(output_md, 'r', encoding='utf-8') as f:
+        content = f.read()
+
+    # 2. 紧凑版正则清洗
+    # 因为 gfm 主要是 pipe table，我们只需要匹配 |...| 结构
+    # 并且不仅匹配，还要把里面为了对齐而产生的多余空格给压扁
+    
+    # 这一步将 "|  文本   |" 压缩为 "| 文本 |"
+    def compress_table_row(match):
+        row = match.group(0)
+        # 将连续的空格替换为单个空格，但保留结构
+        return re.sub(r' +', ' ', row)
+
+    # 匹配标准 Markdown 表格行
+    content = re.sub(r'^\|.*\|$', compress_table_row, content, flags=re.MULTILINE)
+
+    # 3. 标记表格 (逻辑简化，因为现在只有一种表格格式了)
+    tbl_count = 0
+    def tag_table(match):
+        nonlocal tbl_count
+        tbl_count += 1
+        return f"\n\n**[表格 {tbl_count}]**\n{match.group(0)}\n"
+
+    # 匹配连续的表格块
+    table_block_regex = r'(\|.*\|[\r\n]+)+(\|[\s\-:|]+\|[\r\n]+)(\|.*\|[\r\n]*)+'
+    content = re.sub(table_block_regex, tag_table, content)
+
+    # 4. 图片处理与清单 (保持不变)
+    img_count = 0
+    img_details = []
+    def img_replacer(m):
+        nonlocal img_count
+        img_count += 1
+        path = m.group(2) or m.group(3) or ""
+        filename = os.path.basename(path)
+        img_details.append(filename)
+        return f"\n\n**[图片 {img_count}: {filename}]**\n{m.group(0)}\n"
+    
+    content = re.sub(r'(!\[.*?\]\((.*?)\)|\[.*?\]:\s*([^\s]+\.(?:png|jpg|jpeg|gif|bmp))(\s*\{.*?\})?)', img_replacer, content)
+
+    # 5. 深度清洗噪声
+    content = re.sub(r'\[(.*?)\]\(\\l\)', r'\1', content)
+    content = re.sub(r'\[(.*?)\]\[\d+\]', r'\1', content)
+    content = re.sub(r'\{width=.*?\}', '', content)
+    content = re.sub(r'\n{3,}', '\n\n', content)
+
+    # 6. 保存元信息与清单
+    with open(images_list_file, 'w', encoding='utf-8') as f:
+        f.write(f"文档 {base_name} 图片清单：\n" + "="*30 + "\n")
+        for i, name in enumerate(img_details, 1):
+            f.write(f"{i}. {name}\n")
+
+    stats = {
+        "filename": base_name,
+        "table_count": tbl_count,
+        "image_count": img_count,
+        "char_count": len(content),
+        # 重新预估 Token，因为去掉了空格，这个值会更准
+        "estimated_tokens": int(len(content) * 0.6) 
+    }
+    with open(metadata_file, 'w', encoding='utf-8') as f:
+        json.dump(stats, f, indent=4, ensure_ascii=False)
+
+    with open(output_md, 'w', encoding='utf-8') as f:
+        f.write(content)
+
+    print(f"\n" + "="*60)
+    print(f"✅ 紧凑版转换完成！已去除冗余空格")
+    print(f"📁 文档: {output_md}")
+    print(f"📊 统计: {img_count} 图片, {tbl_count} 表格")
+    print(f"📉 Token 节省: 预估比原版节省 30% 空间")
+    print("="*60)
+
+if __name__ == "__main__":
+    convert_compact_mode("a2.docx")

pptx2md/pptx2md.py

@@ -0,0 +1,101 @@
+import os
+import re
+from pptx import Presentation
+from pptx.enum.shapes import MSO_SHAPE_TYPE
+
+# --- 新增：文本清洗函数 ---
+def clean_text(text):
+    if not text:
+        return ""
+    # 1. 去除控制字符 (例如 \x00-\x08, \x0b, \x0c, \x0e-\x1f)
+    #    保留 \t (制表符), \n (换行), \r (回车)
+    text = re.sub(r'[\x00-\x08\x0b\x0c\x0e-\x1f\x7f]', '', text)
+    
+    # 2. 如果你想更彻底，可以去除连续的乱码块
+    #    (如果一行文字里非中英文符号占比过高，可能就是二进制垃圾)
+    #    这里暂时只做控制字符清洗，通常足够解决 99% 的问题。
+    
+    return text.strip()
+
+def extract_pptx_fixed(pptx_path, output_md, media_folder):
+    if not os.path.exists(pptx_path):
+        print(f"找不到文件: {pptx_path}")
+        return
+
+    if not os.path.exists(media_folder):
+        os.makedirs(media_folder)
+
+    prs = Presentation(pptx_path)
+    
+    with open(output_md, "w", encoding="utf-8") as f:
+        f.write(f"# PPT 提取报告: {os.path.basename(pptx_path)}\n\n")
+
+        for i, slide in enumerate(prs.slides):
+            f.write(f"## --- 第 {i+1} 页 ---\n\n")
+
+            # 1. 提取备注 (同样需要清洗)
+            if slide.has_notes_slide:
+                notes = slide.notes_slide.notes_text_frame.text
+                cleaned_notes = clean_text(notes)
+                if cleaned_notes:
+                    f.write(f"> **演讲者备注**: {cleaned_notes}\n\n")
+
+            # 2. 排序 (按视觉从上到下)
+            shapes = sorted(slide.shapes, key=lambda x: (x.top, x.left))
+
+            for shape in shapes:
+                # --- A. 提取文本 ---
+                if shape.has_text_frame:
+                    try:
+                        # 逐段提取并清洗
+                        for paragraph in shape.text_frame.paragraphs:
+                            para_text = ""
+                            for run in paragraph.runs:
+                                chunk = clean_text(run.text)
+                                if not chunk: continue
+                                
+                                if run.font.bold:
+                                    chunk = f"**{chunk}**"
+                                para_text += chunk
+                            
+                            if para_text:
+                                # 识别标题
+                                prefix = ""
+                                if shape == slide.shapes.title: 
+                                    prefix = "### "
+                                f.write(f"{prefix}{para_text}\n")
+                        f.write("\n")
+                    except Exception as e:
+                        print(f"跳过第 {i+1} 页的损坏文本框: {e}")
+
+                # --- B. 提取表格 ---
+                if shape.has_table:
+                    f.write("\n| PPT 表格数据 |\n| --- |\n")
+                    for row in shape.table.rows:
+                        # 清洗表格内容
+                        row_data = [clean_text(cell.text_frame.text).replace('\n', '<br>') for cell in row.cells]
+                        f.write("| " + " | ".join(row_data) + " |\n")
+                    f.write("\n")
+
+                # --- C. 提取图片 ---
+                if shape.shape_type == MSO_SHAPE_TYPE.PICTURE:
+                    try:
+                        image = shape.image
+                        ext = image.ext
+                        # 过滤掉 weird 的图片格式，或者统一转为 jpg (可选)
+                        image_name = f"slide_{i+1}_img_{shape.shape_id}.{ext}"
+                        image_path = os.path.join(media_folder, image_name)
+                        
+                        with open(image_path, "wb") as img_f:
+                            img_f.write(image.blob)
+                        
+                        f.write(f"![幻灯片图片]({media_folder}/{image_name})\n\n")
+                    except Exception as e:
+                        print(f"无法保存图片 (可能是损坏的OLE对象): {e}")
+
+    print(f"✅ 修复版提取完成！乱码已被过滤。保存至: {output_md}")
+
+# --- 执行 ---
+if __name__ == "__main__":
+    # 替换成你的文件名
+    extract_pptx_fixed("1.pptx", "output_ppt_fixed.md", "ppt_media_fixed")

xlsx2csv/xlsx2csv.py

@@ -0,0 +1,4 @@
+import pandas as pd
+# 自动处理了中文编码，避免乱码
+df = pd.read_excel("1.xlsx")
+print(df.to_csv(index=False))