|
|
# -*- coding: utf-8 -*-
|
|
|
import re
|
|
|
import os
|
|
|
import logging
|
|
|
import pandas as pd
|
|
|
from docx.oxml.ns import qn
|
|
|
from fastapi import HTTPException
|
|
|
from fastapi.responses import JSONResponse
|
|
|
from docx import Document
|
|
|
from pathlib import Path
|
|
|
from datetime import datetime
|
|
|
from docx.shared import Inches, Pt
|
|
|
from app.tools.deal_excels import deal_excel, top5_dod_analysis, transform_data, deal_excel_over_load
|
|
|
from app.tools.get_time import get_time
|
|
|
from app.tools.replace_text import replace_text_in_docx
|
|
|
from app.tools.replace_table import copy_table, copy_sta_table
|
|
|
from app.tools.style import table_style
|
|
|
from app.tools.effective_date import get_next_day
|
|
|
from app.tools.find_before_word import extract_overload_info_from_previous_day
|
|
|
from app.tools.count_data import count_change_outage, count_outage_sentiment
|
|
|
from app.tools.draw_picture import plot_electricity_comparison
|
|
|
|
|
|
# 获取日志记录器
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
|
|
|
def deal_docx(folder_path, save_path=None, time_type=0):
|
|
|
"""
|
|
|
:param folder_path: 文件上传后保存的路径
|
|
|
:param save_path: 最终生成的日报/简报的保存路径
|
|
|
:param time_type: 判断时间的统计方式，0代表前一天17点之后到当天17点之前，1代表当天00:00:00到当天23:59:59
|
|
|
:return: 返回生成日报的存储路径，保存到mysql
|
|
|
"""
|
|
|
|
|
|
# 拿到文件夹下所有文件名
|
|
|
# folder_path = 'E:/work_data/work/三工单日报/20250308/源数据/源数据'
|
|
|
# folder_path = 'E:/work_data/work/三工单日报/20250309/20250309'
|
|
|
# folder_path = 'E:/work_data/work/三工单日报/20250310/20250310'
|
|
|
|
|
|
try:
|
|
|
logger.info("进入日报生成方法")
|
|
|
files = os.listdir(folder_path)
|
|
|
|
|
|
file_path_dict = {}
|
|
|
|
|
|
# 拿到需要分析的三个文档
|
|
|
for file in files:
|
|
|
# 停电word
|
|
|
if file.endswith(".docx") and "投诉服务" in file:
|
|
|
file_path_dict["power_off_doc"] = folder_path + "/" + file
|
|
|
continue
|
|
|
|
|
|
# 舆情word
|
|
|
if file.endswith(".docx") and "抢修投诉舆情" in file:
|
|
|
file_path_dict["sentiment_doc"] = folder_path + "/" + file
|
|
|
print(f"舆情文件路径{file_path_dict['sentiment_doc']}")
|
|
|
continue
|
|
|
|
|
|
# 投诉excel
|
|
|
if file.endswith(".xlsx") and "投诉统计表" in file:
|
|
|
file_path_dict["power_off_excel"] = folder_path + "/" + file
|
|
|
continue
|
|
|
|
|
|
if file.endswith(".xlsx") and "停电报表配变明细" in file:
|
|
|
file_path_dict["over_load_excel"] = folder_path + "/" + file
|
|
|
continue
|
|
|
|
|
|
# 如果传入的文件不对，抛出异常
|
|
|
if len(file_path_dict) != 4:
|
|
|
logger.exception("文件格式错误")
|
|
|
raise HTTPException(
|
|
|
status_code=400,
|
|
|
detail="文档无法正确解析，请确认上传的生成日报的资料是否完整",
|
|
|
)
|
|
|
|
|
|
# ————————————————————————处理word文档—————————————————————————
|
|
|
# 读取停电word文件信息
|
|
|
doc_poweroff = Document(file_path_dict["power_off_doc"])
|
|
|
# 读取舆情word文件
|
|
|
doc_sentiment = Document(file_path_dict["sentiment_doc"])
|
|
|
|
|
|
# 日报拼接数据字典
|
|
|
doc_dict = {}
|
|
|
|
|
|
if time_type == 0:
|
|
|
# 旧版正则
|
|
|
# update:2025-07-04 格式维06和7的匹配
|
|
|
time_re = re.compile(r"^(\d+年)?\d+月\d+日\d+时至.{7,15}期间[,，]")
|
|
|
elif time_type == 1:
|
|
|
# 20250429过滤时间正则
|
|
|
time_re = re.compile(
|
|
|
r"^(\d+年)?\d+月\d+日[^,，。\.;；“”\']{0,10}至[^,，。\.;；“”\']{0,15}期间[,，]"
|
|
|
)
|
|
|
|
|
|
# 避免拿错段落，则进行遍历
|
|
|
paragraphs_poweroff = doc_poweroff.paragraphs
|
|
|
for para in paragraphs_poweroff:
|
|
|
# 第一点内容
|
|
|
if re.match(r".*全网累计停电.*", para.text):
|
|
|
# print(para.text)
|
|
|
doc_dict["first_point_para1"] = re.sub(time_re, "", para.text)
|
|
|
continue
|
|
|
|
|
|
if re.match(r".*全网故障抢修工单.*", para.text):
|
|
|
# print(para.text)
|
|
|
doc_dict["first_point_para2"] = re.sub(
|
|
|
r"[，,]整体抢修工作态势正常。+$", "", para.text
|
|
|
)
|
|
|
continue
|
|
|
|
|
|
if "first_point_para2" not in doc_dict:
|
|
|
if re.match(r".*抢修工单.*", para.text):
|
|
|
# print(para.text)
|
|
|
doc_dict["first_point_para2"] = re.sub(
|
|
|
r"[，,]整体抢修工作态势正常。+$", "", para.text
|
|
|
)
|
|
|
continue
|
|
|
|
|
|
# 第二点过载台数
|
|
|
if re.search(r"过载(\d+)(?:[条台]|\s*)?", para.text):
|
|
|
doc_dict["over_load"] = (
|
|
|
re.search(r"过载(\d+)(?:[条台]|\s*)?", para.text).group().replace("过载", "")
|
|
|
).replace("条", "").replace("台", "")
|
|
|
# print(doc_dict['over_load'])
|
|
|
continue
|
|
|
"""
|
|
|
if re.search(r"过载\d+台", para.text):
|
|
|
doc_dict["over_load"] = (
|
|
|
re.search(r"过载\d+台", para.text).group().replace("过载", "")
|
|
|
).replace("台", "")
|
|
|
# print(doc_dict['over_load'])
|
|
|
continue
|
|
|
"""
|
|
|
|
|
|
# 拿到舆情的段落
|
|
|
paragraphs_sentiment = doc_sentiment.paragraphs
|
|
|
for para in paragraphs_sentiment:
|
|
|
if re.match(r".*舆情风险信息\d+条.*", para.text):
|
|
|
text_temp = re.sub(time_re, "", para.text)
|
|
|
doc_dict["sentiment_trend"] = re.search(
|
|
|
r"[^,\\.。]*[,，]舆情态势[^,\\.。]*[\\.。]$", text_temp
|
|
|
).group()
|
|
|
doc_dict["sentiment_para"] = re.sub(
|
|
|
r"[^,\\.。，]*[,，]舆情态势[^,\\.。]*[\\.。]$", "", text_temp
|
|
|
)
|
|
|
continue
|
|
|
|
|
|
# 获取所有表格
|
|
|
print("获取投诉服务的表格")
|
|
|
tables = doc_poweroff.tables
|
|
|
|
|
|
# 舆情直接取第一个表格
|
|
|
print("舆情的表格")
|
|
|
table_sentiment = doc_sentiment.tables[0]
|
|
|
|
|
|
# 表1 “抢修、投诉、舆情”三工单监测汇总表
|
|
|
table1 = tables[0]
|
|
|
|
|
|
|
|
|
# 表2配变过载监测汇总表——配变过载集成到了一张表table1
|
|
|
#table2 = tables[1]
|
|
|
|
|
|
# 表3停电用户前五供电局——停电前五移动到了第二张表
|
|
|
table3 = tables[1]
|
|
|
#table3 = tables[2]
|
|
|
|
|
|
# 新增表4 95598供电类投诉前五供电局统计表
|
|
|
# table4 = doc_poweroff.add_table(6, 5)
|
|
|
|
|
|
# ————————————————————————处理word文档—————————————————————————
|
|
|
|
|
|
# -----------------------------------------------------------------------------------------
|
|
|
|
|
|
# ————————————————————————表格环比统计——————————————————————————
|
|
|
|
|
|
# 首先拿到分析时间，明确要分析哪天的数据
|
|
|
(
|
|
|
start_time,
|
|
|
end_time,
|
|
|
before_start_time,
|
|
|
year,
|
|
|
month,
|
|
|
day,
|
|
|
day_before,
|
|
|
month_before,
|
|
|
) = get_time(files, time_type)
|
|
|
|
|
|
# 获取后一天的时间
|
|
|
year_now, month_now, day_now = get_next_day(int(year), int(month), int(day))
|
|
|
|
|
|
# 通过上述时间,统计停电excel的情况
|
|
|
# 当天情况
|
|
|
province_statistics, district_statistics = deal_excel(
|
|
|
start_time, end_time, file_path_dict["power_off_excel"]
|
|
|
)
|
|
|
print(f"省份统计{province_statistics}")
|
|
|
print(f"地市统计{district_statistics}")
|
|
|
province_statistics_list = list(province_statistics.values())
|
|
|
|
|
|
# 当天省份总投诉
|
|
|
province_statistics_total = sum(province_statistics.values())
|
|
|
print(f"省份总投诉{province_statistics_total}")
|
|
|
|
|
|
# 昨天情况
|
|
|
province_stat_before, district_stat_before = deal_excel(
|
|
|
before_start_time, start_time, file_path_dict["power_off_excel"]
|
|
|
)
|
|
|
print(f"省份昨日情况{province_stat_before}")
|
|
|
|
|
|
# 昨天省份总投诉
|
|
|
province_stat_be_total = sum(province_stat_before.values())
|
|
|
print(f"省份昨日总投诉{province_stat_be_total}")
|
|
|
|
|
|
# 省份环比
|
|
|
province_dod = {
|
|
|
k: province_statistics[k] - province_stat_before[k]
|
|
|
for k in province_statistics.keys()
|
|
|
}
|
|
|
|
|
|
# 最终省份环比结果
|
|
|
for key, value in province_dod.items():
|
|
|
if int(value) > 0:
|
|
|
province_dod[key] = "+" + str(value)
|
|
|
|
|
|
elif int(value) == 0:
|
|
|
province_dod[key] = "持平"
|
|
|
|
|
|
print(f"省份环比{province_dod}")
|
|
|
|
|
|
province_dod_list = list(province_dod.values())
|
|
|
|
|
|
# 表1中剩余的省份统计数据及舆情的统计数据、环比情况
|
|
|
table1_extra_data = transform_data(
|
|
|
[province_statistics_list, province_dod_list]
|
|
|
)
|
|
|
logger.info(
|
|
|
f"表1中剩余的省份统计数据及舆情的统计数据、环比情况：{table1_extra_data}"
|
|
|
)
|
|
|
|
|
|
|
|
|
# 将昨天的地市统计转成字典
|
|
|
district_stat_before = dict(district_stat_before)
|
|
|
# 查看今天的前五在昨天的情况
|
|
|
"""
|
|
|
情况1：今天的数据大于5，则可以直接用现有逻辑
|
|
|
情况2：今天的数据小于5，值判断小于5的这几条，比如只有1条，就判断这一条的情况
|
|
|
"""
|
|
|
top_dod_dict = {}
|
|
|
|
|
|
# 需要判断地市停电的有没有5个，分小于5或者大于等于5
|
|
|
top5_name_list = []
|
|
|
top5_poweroff_list = []
|
|
|
|
|
|
# update:2025-07-04 修改供电类投诉前五供电局统计表的同排行
|
|
|
need_district_statistics = (
|
|
|
district_statistics[0:5]
|
|
|
if len(district_statistics) > 5
|
|
|
else district_statistics
|
|
|
)
|
|
|
other_district_statistic = (
|
|
|
district_statistics[5:] if len(district_statistics) > 5 else []
|
|
|
)
|
|
|
other_count = 0
|
|
|
if (
|
|
|
len(other_district_statistic) > 0
|
|
|
and district_statistics[4][1] == district_statistics[5][1]
|
|
|
):
|
|
|
for i in range(len(other_district_statistic)):
|
|
|
if other_district_statistic[i][1] == district_statistics[4][1]:
|
|
|
other_count += 1
|
|
|
poweroff_value = need_district_statistics[len(need_district_statistics) - 1][1]
|
|
|
count = 0
|
|
|
for i in range(len(need_district_statistics)):
|
|
|
current_poweroff_value = need_district_statistics[i][1]
|
|
|
if current_poweroff_value == poweroff_value:
|
|
|
count += 1
|
|
|
else:
|
|
|
top5_name_list.append(need_district_statistics[i][0])
|
|
|
top5_poweroff_list.append(need_district_statistics[i][1])
|
|
|
top_dod_dict[need_district_statistics[i][0]] = top5_dod_analysis(
|
|
|
need_district_statistics[i], district_stat_before
|
|
|
)
|
|
|
if count == 1 and other_count==0:
|
|
|
top5_name_list.append(
|
|
|
need_district_statistics[len(need_district_statistics) - 1][0]
|
|
|
)
|
|
|
top5_poweroff_list.append(
|
|
|
need_district_statistics[len(need_district_statistics) - 1][1]
|
|
|
)
|
|
|
top_dod_dict[
|
|
|
need_district_statistics[len(need_district_statistics) - 1][0]
|
|
|
] = top5_dod_analysis(
|
|
|
need_district_statistics[len(need_district_statistics) - 1],
|
|
|
district_stat_before,
|
|
|
)
|
|
|
else:
|
|
|
top5_name_list.append(f"其他{count + other_count}家单位")
|
|
|
top5_poweroff_list.append(poweroff_value)
|
|
|
top_dod_dict["其他单位"] = "—"
|
|
|
|
|
|
# old_version
|
|
|
"""
|
|
|
if len(district_statistics) >= 5:
|
|
|
|
|
|
# 地市前五统计
|
|
|
# print(district_statistics)
|
|
|
top1 = district_statistics[0]
|
|
|
top2 = district_statistics[1]
|
|
|
top3 = district_statistics[2]
|
|
|
top4 = district_statistics[3]
|
|
|
top5 = district_statistics[4]
|
|
|
|
|
|
|
|
|
print(f'地市前五{top1}{top2}{top3}{top4}{top5}')
|
|
|
|
|
|
top5_name_list = [top1[0], top2[0], top3[0], top4[0], top5[0]]
|
|
|
|
|
|
top5_poweroff_list = [top1[1], top2[1], top3[1], top4[1], top5[1]]
|
|
|
|
|
|
|
|
|
top_dod_dict[top1[0]] = top5_dod_analysis(top1, district_stat_before)
|
|
|
top_dod_dict[top2[0]] = top5_dod_analysis(top2, district_stat_before)
|
|
|
top_dod_dict[top3[0]] = top5_dod_analysis(top3, district_stat_before)
|
|
|
top_dod_dict[top4[0]] = top5_dod_analysis(top4, district_stat_before)
|
|
|
top_dod_dict[top5[0]] = top5_dod_analysis(top5, district_stat_before)
|
|
|
|
|
|
elif 0 < len(district_statistics) < 5:
|
|
|
for i in range(len(district_statistics)):
|
|
|
top5_name_list.append(district_statistics[i][0])
|
|
|
top5_poweroff_list.append(district_statistics[i][1])
|
|
|
top_dod_dict[district_statistics[i][0]] = top5_dod_analysis(district_statistics[i], district_stat_before)
|
|
|
|
|
|
print(f"地市前五名称{top5_name_list}")
|
|
|
print(f"地市前五数据{top5_poweroff_list}")
|
|
|
# top_dod_dict[top1[0]] = top5_dod_analysis(top1, district_stat_before)
|
|
|
# top_dod_dict[top2[0]] = top5_dod_analysis(top2, district_stat_before)
|
|
|
# top_dod_dict[top3[0]] = top5_dod_analysis(top3, district_stat_before)
|
|
|
# top_dod_dict[top4[0]] = top5_dod_analysis(top4, district_stat_before)
|
|
|
# top_dod_dict[top5[0]] = top5_dod_analysis(top5, district_stat_before)
|
|
|
"""
|
|
|
print(f"地市环比{top_dod_dict}")
|
|
|
top5_stat_list = list(top_dod_dict.values())
|
|
|
|
|
|
# 地市前5的名称、数据、环比放入列表并转至，方便写入表格4
|
|
|
top5_list = transform_data([top5_name_list, top5_poweroff_list, top5_stat_list])
|
|
|
|
|
|
# 省总的投诉情况及环比
|
|
|
complain_dod = int(province_statistics_total) - int(province_stat_be_total)
|
|
|
|
|
|
logger.info(f"省份总量环比{complain_dod}")
|
|
|
|
|
|
# 计算省份总量环比
|
|
|
if complain_dod > 0:
|
|
|
# 使用 f-string 进行格式化
|
|
|
complain_dod = f"增加{complain_dod / province_stat_be_total * 100:.2f}%"
|
|
|
elif complain_dod < 0:
|
|
|
# 使用 f-string 进行格式化
|
|
|
complain_dod = f"减少{-complain_dod / province_stat_be_total * 100:.2f}%"
|
|
|
else:
|
|
|
complain_dod = "持平"
|
|
|
|
|
|
# 异常处置情况
|
|
|
electricity_exception = "停电、投诉、舆情整体平稳，无异常情况。"
|
|
|
|
|
|
standardize_date = None
|
|
|
|
|
|
if time_type == 0:
|
|
|
# ！！！旧版 前面已经过滤掉了时间信息，此处对时间进行单独赋值操作
|
|
|
standardize_date = (
|
|
|
f"{month_before}月{day_before}日17时至{month}月{day}日17时期间，"
|
|
|
)
|
|
|
elif time_type == 1:
|
|
|
# -------------------------20250429更新，修改开始和结束时间---------------------------------
|
|
|
#standardize_date = f"{year}年{month}月{day}日0时至24时期间，"
|
|
|
standardize_date = f"{month}月{day}日0时至24时期间，"
|
|
|
# standardize_date = ''
|
|
|
# -------------------------20250429更新，修改开始和结束时间---------------------------------
|
|
|
|
|
|
# ————————————————————————表格环比统计——————————————————————————
|
|
|
|
|
|
# 获取当前文件夹路径
|
|
|
current_path = Path(__file__).parent
|
|
|
|
|
|
templates_path = str(os.path.join(current_path.parent, "templates")).replace(
|
|
|
"\\", "/"
|
|
|
)
|
|
|
|
|
|
# 默认标题
|
|
|
# 注意，标题会根据不同时期进行调整
|
|
|
report_title = r"南方电网公司“停电抢修、投诉服务、舆情管控”三工单联动监测日报"
|
|
|
|
|
|
# ————————————————————————组装完整简报——————————————————————————
|
|
|
if time_type == 0:
|
|
|
# 旧版正则
|
|
|
sample_first_para = (
|
|
|
f"{month_before}月{day_before}日17时至{month}月{day}日17时"
|
|
|
)
|
|
|
elif time_type == 1:
|
|
|
# 20250429过滤时间正则
|
|
|
sample_first_para = f"{year}年{month}月{day}日0时至24时"
|
|
|
|
|
|
# 简报舆情信息
|
|
|
doc_dict["sentiment_para_simple"] = doc_dict["sentiment_para"].replace(
|
|
|
"全网监测到", ""
|
|
|
)
|
|
|
|
|
|
if re.search(r"重要用户停电[^0]户", doc_dict["first_point_para1"]):
|
|
|
doc_dict["have_important"] = re.sub(
|
|
|
"[,，]用户停电情况总体平稳",
|
|
|
"",
|
|
|
re.sub("其中[,，]", "", doc_dict["first_point_para1"]),
|
|
|
)
|
|
|
else:
|
|
|
doc_dict["have_important"] = (
|
|
|
re.sub(
|
|
|
r"[,，]其中.{0,3}重要用户停电0户.{0,5}停电情况总体平稳[\\.。]",
|
|
|
"",
|
|
|
doc_dict["first_point_para1"],
|
|
|
)
|
|
|
+ "，无重要用户停电。"
|
|
|
)
|
|
|
|
|
|
# 获取停电数字信息
|
|
|
(
|
|
|
total_outage,
|
|
|
short_term_outage,
|
|
|
change_outage,
|
|
|
percentage,
|
|
|
short_precentage,
|
|
|
important_stop_outage,
|
|
|
type,
|
|
|
) = count_change_outage(doc_dict["have_important"])
|
|
|
# 获取舆情数字信息
|
|
|
today_sentiment, type_sentiment, yesterday_sentiment, result_sentiment = (
|
|
|
count_outage_sentiment(doc_dict["sentiment_para_simple"])
|
|
|
)
|
|
|
# 简报的舆情信息只要总数和环比
|
|
|
complain_simple = (
|
|
|
f"95598供电类投诉{province_statistics_total}条，环比{complain_dod}"
|
|
|
)
|
|
|
|
|
|
print(doc_dict["have_important"])
|
|
|
|
|
|
print(doc_dict["sentiment_para_simple"])
|
|
|
|
|
|
current_doc_name = f"南方电网公司停电抢修投诉服务舆情管控三工单联动监测日报{year}{int(month):02d}{int(day):02d}.docx"
|
|
|
|
|
|
if "over_load" not in doc_dict:
|
|
|
raise Exception("过载数据不符合标准未解析，请查看文档")
|
|
|
doc_dict_over_load = doc_dict["over_load"]
|
|
|
over_load_before = extract_overload_info_from_previous_day(
|
|
|
current_word=current_doc_name
|
|
|
)
|
|
|
|
|
|
if over_load_before:
|
|
|
# 将字符串转换为浮点数
|
|
|
over_load_before = float(over_load_before)
|
|
|
doc_dict_over_load = float(doc_dict_over_load)
|
|
|
if over_load_before > doc_dict_over_load:
|
|
|
over_load_percent = (
|
|
|
(over_load_before - doc_dict_over_load) / over_load_before * 100
|
|
|
)
|
|
|
over_load_percent = f"{over_load_percent:.2f}%"
|
|
|
over_load_type = "减少"
|
|
|
elif over_load_before < doc_dict_over_load:
|
|
|
over_load_percent = (
|
|
|
(doc_dict_over_load - over_load_before) / over_load_before * 100
|
|
|
)
|
|
|
over_load_percent = f"{over_load_percent:.2f}%"
|
|
|
over_load_type = "增加"
|
|
|
else:
|
|
|
over_load_percent = ""
|
|
|
over_load_type = "持平"
|
|
|
else:
|
|
|
over_load_before = ""
|
|
|
over_load_percent = "，缺少上一天数据"
|
|
|
over_load_type = "无法估计"
|
|
|
|
|
|
# 组装替换的文本
|
|
|
replacements_simple = {
|
|
|
"{{standardize_date}}": standardize_date,
|
|
|
"{{total_outage}}": str(total_outage),
|
|
|
"{{short_term_outage}}": str(short_term_outage),
|
|
|
"{{change_outage}}": str(change_outage),
|
|
|
"{{percentage}}": str(percentage),
|
|
|
"{{short_precentage}}": str(short_precentage),
|
|
|
"{{important_stop_outage}}": str(important_stop_outage),
|
|
|
"{{type}}": type,
|
|
|
"{{have_important}}": doc_dict["have_important"],
|
|
|
"{{over_load}}": doc_dict["over_load"],
|
|
|
"{{over_load_percent}}": str(over_load_percent),
|
|
|
"{{over_load_type}}": over_load_type,
|
|
|
"{{complain}}": complain_simple,
|
|
|
"{{sample_first_para}}": sample_first_para,
|
|
|
"{{today_sentiment}}": str(today_sentiment),
|
|
|
"{{type_sentiment}}": type_sentiment,
|
|
|
"{{yesterday_sentiment}}": str(yesterday_sentiment),
|
|
|
"{{result_sentiment}}": str(result_sentiment) if result_sentiment!="" else "",
|
|
|
"{{year}}": year,
|
|
|
"{{month}}": month,
|
|
|
"{{day}}": day,
|
|
|
}
|
|
|
|
|
|
# 组装简报
|
|
|
electricity_daily_simple = Document(f"{templates_path}/简报模板.docx")
|
|
|
|
|
|
# 替换模板字符串
|
|
|
replace_text_in_docx(electricity_daily_simple, replacements_simple)
|
|
|
|
|
|
datas = {
|
|
|
"停电用户\n（万户）": {
|
|
|
"昨天": total_outage + change_outage,
|
|
|
"今天": total_outage,
|
|
|
},
|
|
|
"过载配变\n（台）": {"昨天": over_load_before, "今天": doc_dict_over_load},
|
|
|
"95598供电类\n投诉（条）": {
|
|
|
"昨天": province_stat_be_total,
|
|
|
"今天": province_statistics_total,
|
|
|
},
|
|
|
"涉电力供应类舆情\n风险信息（条）": {
|
|
|
"昨天": yesterday_sentiment,
|
|
|
"今天": today_sentiment,
|
|
|
},
|
|
|
}
|
|
|
|
|
|
# 将数据转换为DataFrame
|
|
|
df = pd.DataFrame(datas)
|
|
|
# 遍历 datas 中的每个值，将 None 或 空字符串替换为 0
|
|
|
for key, value in datas.items():
|
|
|
for sub_key, sub_value in value.items():
|
|
|
if sub_value is None or sub_value == "":
|
|
|
datas[key][sub_key] = None # 将不存在或为空的值设置为 0
|
|
|
else:
|
|
|
datas[key][sub_key] = int(sub_value) # 确保值是整数
|
|
|
|
|
|
# 生成柱状图
|
|
|
img_path = plot_electricity_comparison(year, month, day, datas)
|
|
|
|
|
|
# 查找插入图片的位置（假设模板中有"{{IMG_PLACEHOLDER}}"作为占位符）
|
|
|
img_placeholder = "{{IMG_PLACEHOLDER}}"
|
|
|
img_inserted = False
|
|
|
|
|
|
for paragraph in electricity_daily_simple.paragraphs:
|
|
|
if img_placeholder in paragraph.text:
|
|
|
# 删除占位符文本
|
|
|
paragraph.text = paragraph.text.replace(img_placeholder, "")
|
|
|
# 插入图片
|
|
|
run = paragraph.add_run()
|
|
|
run.add_picture(img_path, width=Inches(6.0))
|
|
|
img_inserted = True
|
|
|
break
|
|
|
|
|
|
if not img_inserted:
|
|
|
# 如果未找到占位符，则在文档末尾添加图片
|
|
|
p = electricity_daily_simple.add_paragraph()
|
|
|
run = p.add_run()
|
|
|
run.add_picture(img_path, width=Inches(6.0))
|
|
|
|
|
|
# 将表格写入简报
|
|
|
# 设置全局样式
|
|
|
style = electricity_daily_simple.styles["Normal"]
|
|
|
style.font.name = "Times New Roman"
|
|
|
|
|
|
# 按照月份分门别类的文件夹
|
|
|
save_folder = f"{year}{str(month).zfill(2)}"
|
|
|
|
|
|
# 创建子文件夹
|
|
|
if not os.path.exists(f"{save_path}/{save_folder}"):
|
|
|
os.makedirs(f"{save_path}/{save_folder}", exist_ok=True)
|
|
|
|
|
|
final_file = None
|
|
|
final_sim_file = None
|
|
|
# 最终保存文件的路径情况
|
|
|
if time_type == 0:
|
|
|
final_file = f"{save_path}/{save_folder}/{report_title}-{year}{str(month).zfill(2)}{str(day).zfill(2)}.docx"
|
|
|
final_sim_file = f"{save_path}/{save_folder}/【简版】{report_title}-{year}{str(month).zfill(2)}{str(day).zfill(2)}.docx"
|
|
|
|
|
|
elif time_type == 1:
|
|
|
final_file = f"{save_path}/{save_folder}/{report_title}-{year_now}{str(month_now).zfill(2)}{str(day_now).zfill(2)}.docx"
|
|
|
final_sim_file = f"{save_path}/{save_folder}/【简版】{report_title}-{year_now}{str(month_now).zfill(2)}{str(day_now).zfill(2)}.docx"
|
|
|
|
|
|
# 删除旧文件，方便文件更新
|
|
|
delete_old_file(final_file)
|
|
|
delete_old_file(final_sim_file)
|
|
|
|
|
|
# 生成简报
|
|
|
# 接口保存路径地址
|
|
|
# 保存为Excel文件
|
|
|
path = f"{save_path}/{save_folder}/{year}{str(month).zfill(2)}{str(day).zfill(2)}电力统计数据.xlsx"
|
|
|
df.to_excel(path, index=True)
|
|
|
electricity_daily_simple.save(final_sim_file)
|
|
|
# 测试保存路径
|
|
|
# electricity_daily_simple.save(f'【简版】公司全国“两会”保供电期间配网设备运行及三工单监测日报-{year}{str(month).zfill(2)}{str(day).zfill(2)}.docx')
|
|
|
|
|
|
# # ————————————————————————组装完整简报——————————————————————————
|
|
|
|
|
|
# -----------------------------------------------------------------------------------------
|
|
|
|
|
|
# ————————————————————————组装完整日报——————————————————————————
|
|
|
|
|
|
# 将数据组装相关的时间内容
|
|
|
doc_dict["first_point_para1"] = standardize_date + doc_dict["first_point_para1"]
|
|
|
#doc_dict["sentiment_para"] = standardize_date + doc_dict["sentiment_para"]
|
|
|
doc_dict["sentiment_para"] = doc_dict["sentiment_para"]
|
|
|
|
|
|
# {{standardize_date}}全网收到{{complain_num}}条供电类投诉，环比{{complain_dod}}条；
|
|
|
complain_text = (
|
|
|
standardize_date
|
|
|
+ f"全网收到{str(province_statistics_total)}条供电类投诉，环比{complain_dod}"
|
|
|
)
|
|
|
# update:2025-07-04 备注,增加过载环比
|
|
|
replacements = {}
|
|
|
if time_type == 0:
|
|
|
# 组装替换的文本
|
|
|
replacements = {
|
|
|
"{{year}}": year,
|
|
|
"{{month}}": month,
|
|
|
"{{day}}": day,
|
|
|
"{{power_off_one}}": doc_dict["first_point_para1"],
|
|
|
"{{power_off_two}}": doc_dict["first_point_para2"],
|
|
|
"{{over_load}}": doc_dict["over_load"],
|
|
|
"{{over_load_percent}}": str(over_load_percent),
|
|
|
"{{over_load_type}}": over_load_type,
|
|
|
"{{complain}}": complain_simple,
|
|
|
"{{sentiment}}": doc_dict["sentiment_para"],
|
|
|
"{{sentiment_trend}}": doc_dict["sentiment_trend"],
|
|
|
"{{exception}}": electricity_exception,
|
|
|
}
|
|
|
|
|
|
elif time_type == 1:
|
|
|
# 组装替换的文本
|
|
|
replacements = {
|
|
|
"{{year}}": str(year_now),
|
|
|
"{{month}}": str(month_now),
|
|
|
"{{day}}": str(day_now),
|
|
|
"{{power_off_one}}": doc_dict["first_point_para1"],
|
|
|
"{{power_off_two}}": doc_dict["first_point_para2"],
|
|
|
"{{over_load}}": doc_dict["over_load"],
|
|
|
"{{over_load_percent}}": str(over_load_percent),
|
|
|
"{{over_load_type}}": over_load_type,
|
|
|
"{{complain}}": complain_simple,
|
|
|
"{{sentiment}}": doc_dict["sentiment_para"],
|
|
|
"{{sentiment_trend}}": doc_dict["sentiment_trend"],
|
|
|
"{{exception}}": electricity_exception,
|
|
|
}
|
|
|
|
|
|
# 组装日报
|
|
|
electricity_daily = Document(f"{templates_path}/日报模板.docx")
|
|
|
|
|
|
#
|
|
|
replace_text_in_docx(electricity_daily, replacements)
|
|
|
|
|
|
# 将表格添加到新的文档里
|
|
|
# 组装表1的数据
|
|
|
# 此处缺少省份统计数据和舆情数据
|
|
|
logger.info("将投诉服务的表格1写入日报的表格1，从2-8行，2-9列写入")
|
|
|
# 定义要查看的区域范围
|
|
|
start_row1 = 2 # 起始行索引（从0开始）
|
|
|
end_row1 = 8 # 结束行索引（不包括）
|
|
|
start_col1 = 2 # 起始列索引（从0开始）
|
|
|
end_col1 = 9 # 结束列索引（不包括）
|
|
|
copy_table(
|
|
|
table1,
|
|
|
electricity_daily.tables[0],
|
|
|
start_row1,
|
|
|
end_row1,
|
|
|
start_col1,
|
|
|
end_col1,
|
|
|
0,
|
|
|
)
|
|
|
|
|
|
|
|
|
# 插入各个省份的投诉数据及环比
|
|
|
logger.info("将投诉数据写入到表1，第二行开始，第11列开始")
|
|
|
# 省份统计的表格数据在表格中的起始位置
|
|
|
start_row_pro_sta = 2
|
|
|
start_col_pro_sta = 11
|
|
|
copy_sta_table(
|
|
|
electricity_daily.tables[0],
|
|
|
table1_extra_data,
|
|
|
start_row_pro_sta,
|
|
|
start_col_pro_sta,
|
|
|
)
|
|
|
|
|
|
# 放入舆情的数据
|
|
|
logger.info("将舆情数据写入到表1，第二行开始，第11列开始")
|
|
|
# 定义要查看的区域范围
|
|
|
start_row1_1 = 2 # 起始行索引（从0开始）
|
|
|
end_row1_1 = 8 # 结束行索引（不包括）
|
|
|
start_col1_1 = 10 # 起始列索引（从0开始）
|
|
|
end_col1_1 = 13 # 结束列索引（不包括）
|
|
|
copy_table(
|
|
|
table_sentiment,
|
|
|
electricity_daily.tables[0],
|
|
|
start_row1_1,
|
|
|
end_row1_1,
|
|
|
start_col1_1,
|
|
|
end_col1_1,
|
|
|
3,
|
|
|
)
|
|
|
|
|
|
# 复制表1的数据
|
|
|
logger.info("将配变过载写入表0，第二行开始，第9列开始")
|
|
|
# 定义要查看的区域范围
|
|
|
start_row2 = 2 # 起始行索引（从0开始）
|
|
|
end_row2 = 8 # 结束行索引（不包括）
|
|
|
start_col2 = 9 # 起始列索引（从0开始）
|
|
|
end_col2 = 11 # 结束列索引（不包括）
|
|
|
#target_row=1
|
|
|
#target_col=7
|
|
|
copy_table(
|
|
|
table1,
|
|
|
electricity_daily.tables[0],
|
|
|
start_row2,
|
|
|
end_row2,
|
|
|
start_col2,
|
|
|
end_col2,
|
|
|
0
|
|
|
)
|
|
|
"""
|
|
|
copy_table(
|
|
|
table2,
|
|
|
electricity_daily.tables[1],
|
|
|
start_row2,
|
|
|
end_row2,
|
|
|
start_col2,
|
|
|
end_col2,
|
|
|
0,
|
|
|
)
|
|
|
"""
|
|
|
|
|
|
# 复制表3的数据
|
|
|
logger.info("将停电前五插入表格2")
|
|
|
# 定义要查看的区域范围
|
|
|
start_row3 = 2 # 起始行索引（从0开始）
|
|
|
end_row3 = 7 # 结束行索引（不包括）
|
|
|
start_col3 = 1 # 起始列索引（从0开始）
|
|
|
end_col3 = 5 # 结束列索引（不包括）
|
|
|
copy_table(
|
|
|
table3,
|
|
|
electricity_daily.tables[1],
|
|
|
start_row3,
|
|
|
end_row3,
|
|
|
start_col3,
|
|
|
end_col3,
|
|
|
0,
|
|
|
)
|
|
|
"""
|
|
|
copy_table(
|
|
|
table3,
|
|
|
electricity_daily.tables[2],
|
|
|
start_row3,
|
|
|
end_row3,
|
|
|
start_col3,
|
|
|
end_col3,
|
|
|
0,
|
|
|
)
|
|
|
"""
|
|
|
# 填充表格4
|
|
|
# 需要判断是否前五数据不存在
|
|
|
logger.info("将自行统计的数据插入表格5")
|
|
|
# 表4中的插入位置
|
|
|
start_tb4_row = 2
|
|
|
start_tb4_col = 5
|
|
|
if top5_list:
|
|
|
copy_sta_table(
|
|
|
electricity_daily.tables[1],
|
|
|
top5_list,
|
|
|
start_tb4_row,
|
|
|
start_tb4_col,
|
|
|
is_dynamics=False
|
|
|
)
|
|
|
|
|
|
logger.info("将配变重过载的数据插入表格5")
|
|
|
# 统计配变过载前五的数据
|
|
|
top_5_results = deal_excel_over_load(file_path_dict["over_load_excel"])
|
|
|
# 表4中的插入位置
|
|
|
start_tb4_row = 2
|
|
|
start_tb4_col = 8
|
|
|
if not top_5_results.empty:
|
|
|
data = top_5_results.values
|
|
|
copy_sta_table(
|
|
|
electricity_daily.tables[1],
|
|
|
data,
|
|
|
start_tb4_row,
|
|
|
start_tb4_col,
|
|
|
)
|
|
|
|
|
|
# copy_sta_table(electricity_daily.tables[3], top5_list, start_tb4_row, start_tb4_col)
|
|
|
|
|
|
# 将表格中的字体中文设置成仿宋，英文数字设置成新罗马，均为11号大小
|
|
|
for table in electricity_daily.tables:
|
|
|
table_style(table)
|
|
|
|
|
|
# 设置英文数字样式
|
|
|
# 设置全局样式
|
|
|
# 显式设置每个段落的字体
|
|
|
for paragraph in electricity_daily.paragraphs:
|
|
|
for run in paragraph.runs:
|
|
|
run.font.name = "Times New Roman"
|
|
|
#run.font.name = "仿宋"
|
|
|
#run._element.rPr.rFonts.set(qn('w:eastAsia'), '仿宋')
|
|
|
#run.font.size = Pt(16)
|
|
|
|
|
|
# 接口保存路径
|
|
|
electricity_daily.save(final_file)
|
|
|
|
|
|
# 返回doc、年月日，然后在接口代码里进行分析后，提取表1的数据保存到数据库
|
|
|
# return electricity_daily, year, month, day
|
|
|
# 日报本身的时间
|
|
|
statistics_time = None
|
|
|
|
|
|
if time_type == 0:
|
|
|
statistics_time = datetime(int(year), int(month), int(day))
|
|
|
|
|
|
elif time_type == 1:
|
|
|
statistics_time = datetime(int(year_now), int(month_now), int(day_now))
|
|
|
|
|
|
# 返回值保存到数据库，以二进制保存
|
|
|
if time_type == 0:
|
|
|
return {
|
|
|
"report_title": f"{report_title}-{year}{str(month).zfill(2)}{str(day).zfill(2)}.docx",
|
|
|
"daily_report": final_file,
|
|
|
"daily_repo_simple": final_sim_file,
|
|
|
"statistics_time": statistics_time,
|
|
|
"save_folder": save_folder,
|
|
|
# 'excel':path,
|
|
|
# 'img':img_path
|
|
|
}
|
|
|
elif time_type == 1:
|
|
|
return {
|
|
|
"report_title": f"{report_title}-{year_now}{str(month_now).zfill(2)}{str(day_now).zfill(2)}.docx",
|
|
|
"daily_report": final_file,
|
|
|
"daily_repo_simple": final_sim_file,
|
|
|
"statistics_time": statistics_time,
|
|
|
"save_folder": save_folder,
|
|
|
# 'excel':path,
|
|
|
# 'img':img_path
|
|
|
}
|
|
|
# 测试保存路径
|
|
|
# electricity_daily.save(f'公司全国“两会”保供电期间配网设备运行及三工单监测日报-{year}{str(month).zfill(2)}{str(day).zfill(2)}.docx')
|
|
|
# # ————————————————————————组装完整日报——————————————————————————
|
|
|
|
|
|
except Exception as e:
|
|
|
logger.exception("最终渲染阶段失败")
|
|
|
return JSONResponse(
|
|
|
content={"status_code": 500, "detail": f"word解析异常：{e}"}
|
|
|
)
|
|
|
|
|
|
|
|
|
# 从磁盘删除旧文件方法
|
|
|
def delete_old_file(file):
|
|
|
try:
|
|
|
if os.path.exists(file):
|
|
|
os.remove(file)
|
|
|
logger.info("磁盘里的旧文件删除成功")
|
|
|
|
|
|
except Exception as e:
|
|
|
logger.info(f"删除旧文件失败：{e}")
|
|
|
|
|
|
|
|
|
# if __name__ == '__main__':
|
|
|
# folder_path = 'E:/work_data/work/三工单日报/20250310/20250310'
|
|
|
#
|
|
|
# deal_docx(folder_path)
|