修改wps逻辑

work/001_文件处理/wps_word_to_image_pdf.py

@@ -1,19 +1,24 @@
-'''
-将word转换成pdf，通过wps实现，下面是需要的安装包
-pip install pymupdf pywin32 pillow
-'''
+"""
+自动处理：
+1. Word -> PDF -> 图片版PDF
+2. PDF -> 图片版PDF
+
+依赖：
+pip install pymupdf pywin32
+"""
+
 import os
 import sys
 import time
+import shutil
 import fitz
 import win32com.client
-from PIL import Image
-import fitz
-import shutil
 
-def word_to_temp_pdf_by_wps(word_path, temp_pdf_path):
-    word_path = os.path.abspath(word_path)
-    temp_pdf_path = os.path.abspath(temp_pdf_path)
+
+def word_to_pdf_by_wps(word_path, pdf_path):
+    """
+    WPS 转 PDF
+    """
 
     try:
         wps = win32com.client.Dispatch("KWPS.Application")
@@ -22,43 +27,65 @@ def word_to_temp_pdf_by_wps(word_path, temp_pdf_path):
 
     wps.Visible = False
 
-    doc = wps.Documents.Open(word_path)
+    doc = wps.Documents.Open(os.path.abspath(word_path))
+
     time.sleep(1)
 
     # 17 = PDF
-    doc.ExportAsFixedFormat(temp_pdf_path, 17)
+    doc.ExportAsFixedFormat(os.path.abspath(pdf_path), 17)
 
     doc.Close(False)
     wps.Quit()
 
+    print(f"[OK] Word 转 PDF 完成: {pdf_path}")
+
+
+def pdf_to_images(pdf_path, image_dir, zoom=2):
+    """
+    PDF 每页转图片
+    """
 
-def pdf_to_images(temp_pdf_path, image_dir, zoom=2):
     os.makedirs(image_dir, exist_ok=True)
 
-    doc = fitz.open(temp_pdf_path)
+    doc = fitz.open(pdf_path)
+
     image_paths = []
 
     for i in range(len(doc)):
         page = doc.load_page(i)
-        pix = page.get_pixmap(matrix=fitz.Matrix(zoom, zoom), alpha=False)
 
-        img_path = os.path.join(image_dir, f"page_{i + 1}.png")
+        pix = page.get_pixmap(
+            matrix=fitz.Matrix(zoom, zoom),
+            alpha=False
+        )
+
+        img_path = os.path.join(
+            image_dir,
+            f"page_{i + 1}.png"
+        )
+
         pix.save(img_path)
 
         image_paths.append(img_path)
+
         print(f"[OK] 截图完成: {img_path}")
 
     doc.close()
+
     return image_paths
 
 
 def images_to_pdf(image_paths, output_pdf_path):
+    """
+    图片重新合成 PDF
+    """
+
     pdf = fitz.open()
 
     for img_path in image_paths:
-        img_doc = fitz.open(img_path)
+        img = fitz.open(img_path)
 
-        rect = img_doc[0].rect
+        rect = img[0].rect
 
         page = pdf.new_page(
             width=rect.width,
@@ -67,99 +94,154 @@ def images_to_pdf(image_paths, output_pdf_path):
 
         page.insert_image(rect, filename=img_path)
 
-        img_doc.close()
+        img.close()
 
-    pdf.save(output_pdf_path)
+    pdf.save(output_pdf_path, deflate=True)
     pdf.close()
 
-    print(f"[OK] 新 PDF 已生成: {output_pdf_path}")
+    print(f"[OK] 图片版 PDF 已生成: {output_pdf_path}")
+
 
-'''
-def safe_delete(path):
-    if os.path.exists(path):
-        try:
-            os.remove(path)
-            print(f"[OK] 已删除临时 PDF: {path}")
-        except Exception as e:
-            print(f"[警告] 删除失败: {path}，原因: {e}")
-'''
 def safe_delete(path):
     """
     自动删除：
-    1. 文件
-    2. 空文件夹
-    3. 非空文件夹
+    - 文件
+    - 空目录
+    - 非空目录
     """
 
     if not os.path.exists(path):
-        print(f"[跳过] 路径不存在: {path}")
         return
 
     try:
-        # 文件
+
         if os.path.isfile(path):
             os.remove(path)
             print(f"[OK] 文件已删除: {path}")
 
-        # 文件夹
         elif os.path.isdir(path):
-
-            # 递归删除（包括非空目录）
             shutil.rmtree(path)
-
             print(f"[OK] 文件夹已删除: {path}")
 
-        else:
-            print(f"[警告] 未知类型: {path}")
-
     except Exception as e:
-        print(f"[失败] 删除失败: {path}")
+        print(f"[警告] 删除失败: {path}")
         print(f"原因: {e}")
 
 
 def main():
+
     if len(sys.argv) < 2:
         print("用法:")
-        print("python wps_word_to_image_pdf.py test.docx")
+        print("python auto_pdf_image.py 文件")
         return
 
-    word_path = sys.argv[1]
+    input_path = os.path.abspath(sys.argv[1])
 
-    if not os.path.exists(word_path):
-        print("文件不存在:", word_path)
+    if not os.path.exists(input_path):
+        print("文件不存在:", input_path)
         return
 
-    base_dir = os.path.dirname(os.path.abspath(word_path))
-    base_name = os.path.splitext(os.path.basename(word_path))[0]
+    ext = os.path.splitext(input_path)[1].lower()
 
-    temp_pdf_path = os.path.join(base_dir, base_name + "_temp.pdf")
-    image_dir = os.path.join(base_dir, base_name + "_images")
-    output_pdf_path = os.path.join(base_dir, base_name + "_图片版.pdf")
+    base_dir = os.path.dirname(input_path)
+    base_name = os.path.splitext(os.path.basename(input_path))[0]
+
+    image_dir = os.path.join(
+        base_dir,
+        base_name + "_images"
+    )
+
+    output_pdf_path = os.path.join(
+        base_dir,
+        base_name + "_图片版.pdf"
+    )
+
+    temp_pdf_path = os.path.join(
+        base_dir,
+        base_name + "_temp.pdf"
+    )
+
+    generated_temp_pdf = False
 
     try:
-        print("[1] WPS 正在导出临时 PDF...")
-        word_to_temp_pdf_by_wps(word_path, temp_pdf_path)
 
+        # =========================
+        # Word 文档
+        # =========================
+        if ext in [".doc", ".docx"]:
+
+            print("[1] 检测到 Word 文档")
+
+            word_to_pdf_by_wps(
+                input_path,
+                temp_pdf_path
+            )
+
+            pdf_path = temp_pdf_path
+
+            generated_temp_pdf = True
+
+        # =========================
+        # PDF 文件
+        # =========================
+        elif ext == ".pdf":
+
+            print("[1] 检测到 PDF 文件")
+
+            pdf_path = input_path
+
+        else:
+            print("仅支持:")
+            print(".doc")
+            print(".docx")
+            print(".pdf")
+            return
+
+        # =========================
+        # PDF -> 图片
+        # =========================
         print("[2] 正在按页截图...")
-        image_paths = pdf_to_images(temp_pdf_path, image_dir, zoom=2)
 
-        print("[3] 正在重新合成图片 PDF...")
-        images_to_pdf(image_paths, output_pdf_path)
+        image_paths = pdf_to_images(
+            pdf_path,
+            image_dir,
+            zoom=2
+        )
+
+        # =========================
+        # 图片 -> PDF
+        # =========================
+        print("[3] 正在生成图片版 PDF...")
+
+        images_to_pdf(
+            image_paths,
+            output_pdf_path
+        )
+
+        # =========================
+        # 删除临时文件
+        # =========================
+        print("[4] 清理临时文件...")
+
+        time.sleep(1)
 
-        print("[4] 删除临时 PDF...")
-        safe_delete(temp_pdf_path)
         safe_delete(image_dir)
 
+        # 删除临时 PDF
+        if generated_temp_pdf:
+            safe_delete(temp_pdf_path)
+
         print()
         print("[完成]")
-        print("最终 PDF:", output_pdf_path)
+        print("最终文件:", output_pdf_path)
 
     except Exception as e:
         print("[失败]", e)
+        print()
         print("请确认：")
         print("1. WPS 已安装")
-        print("2. 文档能用 WPS 正常打开")
-        print("3. CMD 可以用管理员权限运行")
+        print("2. 文档能正常打开")
+        print("3. 文件未被占用")
 
 
 if __name__ == "__main__":