first commit

image_test/extract_docx_images.py

@@ -0,0 +1,81 @@
+"""从 docx 提取所有内嵌图片，方便定位实际插入到文档里的图片字节。
+
+用法:
+    python image_test/extract_docx_images.py <signed.docx>
+
+输出:
+    image_test/output/docx_images/<图片名>.png  (按 docx 内顺序编号)
+    每张图打印尺寸 + 紧致度诊断
+"""
+import io
+import sys
+import zipfile
+from pathlib import Path
+from PIL import Image, ImageChops
+
+BASE_DIR = Path(__file__).resolve().parent
+OUT_DIR = BASE_DIR / "output" / "docx_images"
+
+
+def analyze_image(data):
+    img = Image.open(io.BytesIO(data))
+    if img.mode != 'RGBA':
+        img = img.convert('RGBA')
+    r, g, b, a = img.split()
+    luma = Image.merge('RGB', (r, g, b)).convert('L')
+    alpha_mask = a.point(lambda p: 255 if p > 30 else 0)
+    luma_mask = luma.point(lambda p: 255 if p < 210 else 0)
+    combined = ImageChops.darker(alpha_mask, luma_mask)
+    total = img.size[0] * img.size[1] or 1
+    return {
+        'size': img.size,
+        'mode': img.mode,
+        'content_pct': 100.0 * sum(combined.histogram()[1:]) / total,
+        'bbox': combined.getbbox(),
+        'alpha_pct': 100.0 * sum(alpha_mask.histogram()[1:]) / total,
+    }
+
+
+def main():
+    if len(sys.argv) < 2:
+        print("用法: python image_test/extract_docx_images.py <signed.docx>")
+        sys.exit(1)
+
+    docx_path = Path(sys.argv[1])
+    if not docx_path.exists():
+        print(f"文件不存在: {docx_path}")
+        sys.exit(1)
+
+    OUT_DIR.mkdir(parents=True, exist_ok=True)
+
+    with zipfile.ZipFile(docx_path, 'r') as z:
+        media_files = sorted([n for n in z.namelist()
+                              if n.startswith('word/media/')])
+
+        if not media_files:
+            print("docx 内未找到 word/media/ 下的图片")
+            return
+
+        print(f"找到 {len(media_files)} 张图片\n")
+
+        for i, name in enumerate(media_files, 1):
+            data = z.read(name)
+            ext = Path(name).suffix or '.png'
+            out_path = OUT_DIR / f"image_{i:02d}{ext}"
+            with open(out_path, 'wb') as f:
+                f.write(data)
+
+            try:
+                stats = analyze_image(data)
+                print(f"[{i:02d}] {name}")
+                print(f"     尺寸={stats['size']} 模式={stats['mode']} "
+                      f"alpha像素={stats['alpha_pct']:.1f}% "
+                      f"内容={stats['content_pct']:.1f}% bbox={stats['bbox']}")
+                print(f"     已保存: {out_path}")
+            except Exception as e:
+                print(f"[{i:02d}] {name}: 解析失败 {e}")
+            print()
+
+
+if __name__ == '__main__':
+    main()