20230209

百度OCR.ipynb

@@ -100,11 +100,32 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {
+    "execution": {
+     "iopub.execute_input": "2023-01-31T07:25:58.845092Z",
+     "iopub.status.busy": "2023-01-31T07:25:58.844564Z",
+     "iopub.status.idle": "2023-01-31T07:26:05.074689Z",
+     "shell.execute_reply": "2023-01-31T07:26:05.072976Z",
+     "shell.execute_reply.started": "2023-01-31T07:25:58.845044Z"
+    },
     "tags": []
    },
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2 扫描全能王 2023-01-31 15.17_1.jpg\n",
+      "3 扫描全能王 2023-01-31 15.17_2.jpg\n",
+      "4 扫描全能王 2023-01-31 15.17_3.jpg\n",
+      "5 扫描全能王 2023-01-31 15.17_4.jpg\n",
+      "6 扫描全能王 2023-01-31 15.17_5.jpg\n",
+      "7 扫描全能王 2023-01-31 15.17_6.jpg\n",
+      "8 扫描全能王 2023-01-31 15.17_7.jpg\n"
+     ]
+    }
+   ],
    "source": [
     "import os,sys\n",
     "from aip import AipOcr\n",
@@ -137,7 +158,7 @@
     "options[\"detect_language\"] = \"true\"\n",
     "options[\"probability\"] = \"true\"\n",
     "dict1 = {}\n",
-    "fi_path = os.getcwd()+'/pic'\n",
+    "fi_path = os.getcwd()+'/data/pic'\n",
     "fl = os.listdir(fi_path)\n",
     "fl.sort()\n",
     "i = 1\n",
@@ -153,7 +174,7 @@
     "        print(i,fl1)\n",
     "        #print('\\n'.join([w['words'] for w in result['words_result']]))\n",
     "        #print('\\n')\n",
-    "with open('中华药膳全书学做药膳不生病.json','w') as fl2:\n",
+    "with open('合同.json','w') as fl2:\n",
     "    json.dump(dict1,fl2,ensure_ascii=False)    "
    ]
   },