This commit is contained in:
512song committed 2023-12-03 15:04:51 +08:00
1 parent b33bbbd408
commit de6a5be703
3 files changed
+1026 -71

No files matched your search

+143 -1
View File
@@ -1915,10 +1915,152 @@
" print(k,v['name'])"
]
},
{
"cell_type": "markdown",
"id": "e7e0e29c-0f12-4478-b687-a03486adc85e",
"metadata": {},
"source": [
"## 报告按部门分类"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a362768f-a67f-4c64-a830-b6a745ab35e4",
"id": "3ff8ad3c-7868-4eb2-b879-4e8da19407ff",
"metadata": {},
"outputs": [],
"source": [
"import os,sys,shutil\n",
"import json\n",
"import glob\n",
"from pathlib import Path\n",
"\n",
"fi_path = '/home/songyi/pdf-typescript/134'\n",
"new_path = 'file/134'\n",
"old = []\n",
"dict2 = {}\n",
"\n",
"filename = 'data/天津石化人员名单2023.json'\n",
"with open(filename,'r') as fl:\n",
" dict1 = json.load(fl)\n",
"fls = glob.glob(f'{fi_path}/*.pdf')\n",
"for fn in fls:\n",
" fi_name =Path(fn).stem.split('-')[0]\n",
" code = int(fi_name)\n",
" unit_path = Path(new_path,dict1[str(code)]['unit'])\n",
" unit_path.mkdir(parents = True, exist_ok = True)\n",
" n_name = Path(unit_path,Path(fn).stem+'.pdf')\n",
" if not os.path.exists(n_name):\n",
" shutil.copyfile(fn,n_name)\n",
" #print(n_name)"
]
},
{
"cell_type": "markdown",
"id": "abe43620-c456-43a0-905a-b29aad8b2e3c",
"metadata": {},
"source": [
"## 核对新部门分类人员"
]
},
{
"cell_type": "code",
"execution_count": 140,
"id": "a3f1476d-5f70-45c4-aa04-ebc6558033b8",
"metadata": {
"execution": {
"iopub.execute_input": "2023-12-02T09:58:33.152532Z",
"iopub.status.busy": "2023-12-02T09:58:33.152132Z",
"iopub.status.idle": "2023-12-02T09:58:33.270132Z",
"shell.execute_reply": "2023-12-02T09:58:33.269673Z",
"shell.execute_reply.started": "2023-12-02T09:58:33.152500Z"
},
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"787\n",
"1 吴强\n",
"2 李丹\n",
"3 王勃\n",
"4 史海燕\n",
"5 周美琴\n",
"6 钟丽\n",
"7 徐玉清\n",
"8 苏洪梅\n",
"9 张杰\n",
"10 杨植文\n",
"11 张梦瑶\n",
"12 韩晓舒\n",
"13 栗晓娜\n",
"14 陈继杨\n",
"15 陈雪梅\n",
"16 林宏锟\n",
"17 汝晴\n",
"18 庞珺珊\n",
"19 姚子翔\n",
"20 罗泽伟\n",
"21 吴子巍\n",
"22 史策\n",
"23 赵婷婷\n",
"24 韦州全\n",
"25 代迪\n",
"26 傅志成\n",
"27 刘国旭\n",
"28 宋燕\n",
"29 侯海霞\n",
"30 刘慧\n",
"31 古富兰\n",
"32 范和文\n",
"33 冯鸥\n",
"34 王依然\n",
"35 田长利\n",
"36 杜苹苹\n",
"37 姜涛\n",
"38 王晓松\n",
"39 雷文秀\n",
"40 徐月\n",
"41 李凤燕\n",
"42 尹莎\n"
]
}
],
"source": [
"import json\n",
"import csv\n",
"import openpyxl\n",
"import time\n",
"from datetime import date\n",
"\n",
"filename = 'data/result_北海炼化2023.json'\n",
"with open(filename,'r') as fl:\n",
" dict1 = json.load(fl) \n",
"\n",
"\n",
"wb = openpyxl.load_workbook('data/北海炼化新名单.xlsx')\n",
"sheet = wb.active\n",
"# sheets = wb.sheetnames\n",
"list1 = []\n",
"\n",
"for n in range(5, sheet.max_row+1):\n",
" if sheet.cell(n,2).value is not None:\n",
" list1.append(sheet.cell(n,2).value)\n",
"print(len(list1)) \n",
"i = 1\n",
"for k, v in dict1.items():\n",
" name = v['name']\n",
" if name not in list1:\n",
" print(i,name)\n",
" i+=1"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e30031dc-3597-4594-8c32-693a958ae171",
"metadata": {},
"outputs": [],
"source": []