20230105

文件管理1.ipynb

@@ -411,9 +411,60 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "88d84849-5b98-48cb-86b1-e96757a8615f",
-   "metadata": {},
+   "id": "99fff4b6-73ea-4d53-96bc-41b6b664e00a",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
+   "source": [
+    "import fitz\n",
+    "import os\n",
+    "\n",
+    "sor = \"中华药膳全书学做药膳不生病.pdf\"              # 需要压缩的PDF文件\n",
+    "\n",
+    "doc = fitz.open(sor) \n",
+    "totaling = doc.pageCount\n",
+    "\n",
+    "zoom = 300                     # 清晰度调节，缩放比率\n",
+    "if os.path.exists('pdf_cp'):       # 临时文件，需为空\n",
+    "     os.removedirs('pdf_cp')\n",
+    "os.mkdir('pdf_cp')\n",
+    "for pg in range(6,totaling):\n",
+    "    page = doc[pg]\n",
+    "    zoom = int(zoom)            #值越大，分辨率越高，文件越清晰\n",
+    "    rotate = int(0)\n",
+    "    print(page)\n",
+    "    trans = fitz.Matrix(zoom / 100.0, zoom / 100.0).preRotate(rotate)\n",
+    "    pm = page.getPixmap(matrix=trans, alpha=False)\n",
+    "\n",
+    "    lurl='pdf_cp/%s.jpg' % str(pg+1).rjust(3,\"0\")\n",
+    "    pm.writePNG(lurl)\n",
+    "doc.close()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "88d84849-5b98-48cb-86b1-e96757a8615f",
+   "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-01-05T05:09:41.478369Z",
+     "iopub.status.busy": "2023-01-05T05:09:41.477814Z",
+     "iopub.status.idle": "2023-01-05T05:11:07.156560Z",
+     "shell.execute_reply": "2023-01-05T05:11:07.155155Z",
+     "shell.execute_reply.started": "2023-01-05T05:09:41.478316Z"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "/tmp/tmp0tguht7x\n"
+     ]
+    }
+   ],
    "source": [
     "from pdf2image import convert_from_path, convert_from_bytes\n",
     "import os,sys\n",
@@ -425,7 +476,7 @@
     ")\n",
     "#images = convert_from_path('1.pdf',dpi=200,fmt='jpg', output_folder='./sample_data')\n",
     "with tempfile.TemporaryDirectory() as path:\n",
-    "    images_from_path = convert_from_path('5.pdf', dpi=100,fmt='jpg', output_folder='./pic')\n",
+    "    images_from_path = convert_from_path('中华药膳全书学做药膳不生病.pdf', dpi=300,fmt='jpg', output_folder='./pic')\n",
     "print(path)"
    ]
   },
@@ -650,16 +701,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": null,
    "id": "9957a90c-7735-4224-b5b5-4a4b1b7688c9",
    "metadata": {
-    "execution": {
-     "iopub.execute_input": "2022-12-12T14:12:26.428992Z",
-     "iopub.status.busy": "2022-12-12T14:12:26.428458Z",
-     "iopub.status.idle": "2022-12-12T14:12:26.536571Z",
-     "shell.execute_reply": "2022-12-12T14:12:26.535612Z",
-     "shell.execute_reply.started": "2022-12-12T14:12:26.428944Z"
-    },
     "tags": []
    },
    "outputs": [],
@@ -683,27 +727,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": null,
    "id": "42122edc-eb77-4cfc-bcd8-3f844ffcca58",
    "metadata": {
-    "execution": {
-     "iopub.execute_input": "2022-12-07T07:30:29.738226Z",
-     "iopub.status.busy": "2022-12-07T07:30:29.737684Z",
-     "iopub.status.idle": "2022-12-07T07:30:30.656573Z",
-     "shell.execute_reply": "2022-12-07T07:30:30.655231Z",
-     "shell.execute_reply.started": "2022-12-07T07:30:29.738176Z"
-    },
     "tags": []
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "转换完成\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from subprocess import Popen\n",
     "\n",