20240411

文件管理1.ipynb

@@ -638,24 +638,23 @@
     "for i, table in enumerate(doc.tables):\n",
     "        print(f\"Table {i}:\")\n",
     "        for row in table.rows:\n",
-    "            print(type(row))\n",
+    "            #print(type(row))\n",
     "            for cell in row.cells:\n",
-    "                if cell.text =='序号':\n",
-    "                    print(cell.text, end=\" | \")\n",
+    "                print(cell.text, end=\" | \")\n",
     "            print()  # 每一行结束后换行\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
-   "id": "c3ccfa25-f31c-46d4-bfd0-903832cc620d",
+   "execution_count": 36,
+   "id": "fe615899-447e-489a-9f0d-90a239031e7c",
    "metadata": {
     "execution": {
-     "iopub.execute_input": "2024-04-10T11:08:13.063231Z",
-     "iopub.status.busy": "2024-04-10T11:08:13.063012Z",
-     "iopub.status.idle": "2024-04-10T11:08:25.173599Z",
-     "shell.execute_reply": "2024-04-10T11:08:25.173048Z",
-     "shell.execute_reply.started": "2024-04-10T11:08:13.063213Z"
+     "iopub.execute_input": "2024-04-11T03:04:05.540001Z",
+     "iopub.status.busy": "2024-04-11T03:04:05.539789Z",
+     "iopub.status.idle": "2024-04-11T03:04:19.212186Z",
+     "shell.execute_reply": "2024-04-11T03:04:19.211594Z",
+     "shell.execute_reply.started": "2024-04-11T03:04:05.539987Z"
     },
     "tags": []
    },
@@ -675,14 +674,52 @@
     "doc = docx.Document(r\"data/中国石化北海炼化有限责任公司2023年职业体检团体报告.docx\")\n",
     "list2 = []\n",
     "for i, table in enumerate(doc.tables):\n",
+    "    list1= []\n",
+    "    for row in table.rows:\n",
+    "        list3 = []\n",
+    "        for cell in row.cells:\n",
+    "            if cell.text.strip()!='':\n",
+    "                list3.append(cell.text)\n",
+    "        list1.append(list3)\n",
+    "    if list1[0][0] =='序号':\n",
+    "        for n in range(1,len(list1)):\n",
+    "            list2.append(list1[n])\n",
+    "filename = '北海职业体测报告情况表2024.xlsx'\n",
+    "wb = openpyxl.Workbook()\n",
+    "sheet = wb.active\n",
+    "\n",
+    "for row in list2:\n",
+    "    sheet.append(row)\n",
     "    \n",
-    "    if table.cell(0, 0).text == '序号':\n",
+    "wb.save(filename)\n",
+    "print('ok!')\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c3ccfa25-f31c-46d4-bfd0-903832cc620d",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import docx\n",
+    "import json\n",
+    "import openpyxl\n",
+    "doc = docx.Document(r\"data/中国石化北海炼化有限责任公司2023年健康体检团体报告.docx\")\n",
+    "list2 = []\n",
+    "for i, table in enumerate(doc.tables):\n",
+    "    \n",
+    "    if table.cell(0, 0).text == '序号' or table.cell(0, 1).text == '序号':\n",
     "        #print(f\"Table {i}:\")\n",
     "        \n",
     "        for row in table.rows:\n",
     "            list1= []\n",
     "            for cell in row.cells:\n",
-    "                list1.append(cell.text)\n",
+    "                if cell.text.strip()!='':\n",
+    "                    list1.append(cell.text)\n",
     "            if list1[0] !='序号':\n",
     "                list2.append(list1)\n",
     "filename = '北海体测报告情况表2024.xlsx'\n",