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",

百度OCR.ipynb

@@ -49,7 +49,6 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "\n",
     "import os,sys\n",
     "from aip import AipOcr\n",
     "\n",
@@ -92,6 +91,72 @@
     "        print('\\n')"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 将指定目录下图片文件进行文字识别保存为json文件"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import os,sys\n",
+    "from aip import AipOcr\n",
+    "import json\n",
+    "\n",
+    "def get_access_token():\n",
+    "    client_id = 'IMC1ss3Tyo3vEAdVH6jgcdv2'\n",
+    "    client_secret = 'Iua6KdhuDtz159rjzGeFGpqgjhnoU0zZ'   \n",
+    "     # client_id 为官网获取的AK， client_secret 为官网获取的SK\n",
+    "    host = 'https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id={}&client_secret={}'.format(\n",
+    "        client_id, client_secret)\n",
+    "    response = requests.get(host).text\n",
+    "    data = json.loads(response)\n",
+    "    access_token = data['access_token']\n",
+    "    return access_token\n",
+    "\n",
+    "\"\"\" 你的 APPID AK SK \"\"\"\n",
+    "APP_ID = '17553946'\n",
+    "API_KEY = 'IMC1ss3Tyo3vEAdVH6jgcdv2'\n",
+    "SECRET_KEY = 'Iua6KdhuDtz159rjzGeFGpqgjhnoU0zZ'\n",
+    "\n",
+    "client = AipOcr(APP_ID, API_KEY, SECRET_KEY)\n",
+    "def get_file_content(filePath):\n",
+    "    with open(filePath, 'rb') as fp:\n",
+    "        return fp.read()\n",
+    "\n",
+    "options = {}\n",
+    "options[\"language_type\"] = \"CHN_ENG\"\n",
+    "options[\"detect_direction\"] = \"true\"\n",
+    "options[\"detect_language\"] = \"true\"\n",
+    "options[\"probability\"] = \"true\"\n",
+    "dict1 = {}\n",
+    "fi_path = os.getcwd()+'/pic'\n",
+    "fl = os.listdir(fi_path)\n",
+    "fl.sort()\n",
+    "i = 1\n",
+    "for fl1 in fl:\n",
+    "    file_name = fi_path+'/' + fl1\n",
+    "    image = get_file_content(file_name)\n",
+    "    result= client.basicGeneral(image, options)\n",
+    "    if 'words_result' in result:\n",
+    "        text = ''.join([w['words'] for w in result['words_result']])\n",
+    "        \n",
+    "        dict1[i] = text\n",
+    "        i+=1\n",
+    "        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",
+    "    json.dump(dict1,fl2,ensure_ascii=False)    "
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -101,26 +166,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2020-11-26T08:59:12.967127Z",
-     "iopub.status.busy": "2020-11-26T08:59:12.966172Z",
-     "iopub.status.idle": "2020-11-26T08:59:28.010488Z",
-     "shell.execute_reply": "2020-11-26T08:59:28.006947Z",
-     "shell.execute_reply.started": "2020-11-26T08:59:12.967019Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "22917135_2274033\n",
-      "已完成\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "import requests\n",
     "import json\n",
@@ -175,26 +223,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {
-    "execution": {
-     "iopub.execute_input": "2023-01-03T00:39:37.591809Z",
-     "iopub.status.busy": "2023-01-03T00:39:37.591257Z",
-     "iopub.status.idle": "2023-01-03T00:39:37.763387Z",
-     "shell.execute_reply": "2023-01-03T00:39:37.761195Z",
-     "shell.execute_reply.started": "2023-01-03T00:39:37.591761Z"
-    },
     "tags": []
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "{'refresh_token': '25.e1167a22bcc63f2e736768f11eb893f9.315360000.1988066377.282335-17553946', 'expires_in': 2592000, 'session_key': '9mzdWr+jeUXdQXD/259SQnM94l/zWgp0GyY6hh17Kt+kjRLgEQG9OYATKN1tjVBrQIdg8DnKb0OBJpbiVsQ/7ixzXqxduw==', 'access_token': '24.acdee0098fe862a7c598f62121a2baac.2592000.1675298377.282335-17553946', 'scope': 'brain_ocr_meter brain_doc_analysis brain_ocr_webimage_loc vis-ocr_机动车购车发票识别 brain_ocr_vehicle_invoice brain_formula vis-ocr_行程单识别 brain_ocr_air_ticket public vis-ocr_ocr brain_ocr_scope brain_ocr_general brain_ocr_general_basic vis-ocr_business_license brain_ocr_webimage brain_all_scope brain_ocr_idcard brain_ocr_driving_license brain_ocr_vehicle_license vis-ocr_plate_number brain_solution brain_ocr_plate_number brain_ocr_accurate brain_ocr_accurate_basic brain_ocr_receipt brain_ocr_business_license brain_solution_iocr brain_qrcode brain_ocr_handwriting brain_ocr_passport brain_ocr_vat_invoice brain_numbers brain_ocr_business_card brain_ocr_train_ticket brain_ocr_taxi_receipt vis-ocr_household_register vis-ocr_vis-classify_birth_certificate vis-ocr_台湾通行证 vis-ocr_港澳通行证 vis-ocr_机动车检验合格证识别 vis-ocr_车辆vin码识别 vis-ocr_定额发票识别 vis-ocr_保单识别 brain_ocr_vin brain_ocr_quota_invoice brain_ocr_birth_certificate brain_ocr_household_register brain_ocr_HK_Macau_pass brain_ocr_taiwan_pass brain_ocr_vehicle_certificate brain_ocr_insurance_doc wise_adapt lebo_resource_base lightservice_public hetu_basic lightcms_map_poi kaidian_kaidian ApsMisTest_Test权限 vis-classify_flower lpq_开放 cop_helloScope ApsMis_fangdi_permission smartapp_snsapi_base smartapp_mapp_dev_manage iop_autocar oauth_tp_app smartapp_smart_game_openapi oauth_sessionkey smartapp_swanid_verify smartapp_opensource_openapi smartapp_opensource_recapi fake_face_detect_开放Scope vis-ocr_虚拟人物助理 idl-video_虚拟人物助理 smartapp_component smartapp_search_plugin avatar_video_test b2b_tp_openapi b2b_tp_openapi_online smartapp_gov_aladin_to_xcx', 'session_secret': '20a3564eae255945e2a4a45ecc57c608'}\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import requests \n",
     "\n",
@@ -207,25 +240,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2020-11-03T03:24:08.412670Z",
-     "iopub.status.busy": "2020-11-03T03:24:08.411768Z",
-     "iopub.status.idle": "2020-11-03T03:24:08.813580Z",
-     "shell.execute_reply": "2020-11-03T03:24:08.810985Z",
-     "shell.execute_reply.started": "2020-11-03T03:24:08.412567Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "已完成\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "import requests\n",
     "import json\n",
@@ -251,28 +268,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 80,
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2020-11-03T08:43:37.180693Z",
-     "iopub.status.busy": "2020-11-03T08:43:37.179800Z",
-     "iopub.status.idle": "2020-11-03T08:43:37.656055Z",
-     "shell.execute_reply": "2020-11-03T08:43:37.653668Z",
-     "shell.execute_reply.started": "2020-11-03T08:43:37.180589Z"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "list"
-      ]
-     },
-     "execution_count": 80,
+   "execution_count": null,
    "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "import requests\n",
     "import json\n",
@@ -313,25 +311,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 81,
-   "metadata": {
-    "execution": {
-     "iopub.execute_input": "2020-11-03T08:48:26.082167Z",
-     "iopub.status.busy": "2020-11-03T08:48:26.081266Z",
-     "iopub.status.idle": "2020-11-03T08:48:26.430039Z",
-     "shell.execute_reply": "2020-11-03T08:48:26.428236Z",
-     "shell.execute_reply.started": "2020-11-03T08:48:26.082060Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "已完成\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "import requests\n",
     "import json\n",