1 import os,sys
  2 from functools import reduce
  3 import pandas as pd
  4 import json
  5 
  6 ENCODE = "utf8"
  7 CWD_PATH = os.path.dirname(sys.argv[0])
  8 
  9 
 10 def func(i):
 11     m,n = os.path.splitext(i)
 12     if n == ".json":
 13         return i
 14 #加载JSON数据
 15 def read_json(PATH):
 16     lst = os.listdir(PATH)
 17     lstt = list(map(lambda x:os.path.join(PATH, x), lst))
 18     lsf = list(filter(lambda x:os.path.isfile(x), lstt))
 19     lsj = list(filter(func,lsf))
 20     print(lsj)
 21     if len(lsj) == 1:
 22         for f in lsj:
 23             with open(f,‘r‘,encoding=ENCODE) as jsonfile:
 24                 DL = json.load(jsonfile)
 25             jsonfile.close()
 26     else:
 27         raise ValueError
 28     return DL
 29 
 30 #加载文件
 31 def get_file(dirpath,file_ls):
 32     slogn = 0
 33     if not os.path.exists(dirpath):  #如果文件不存在，输出错误
 34         print("目录不存在，请确认！！！")
 35         return file_ls, slogn
 36     elif os.path.isfile(dirpath):
 37         file_ls.append(dirpath)
 38         slogn = 1
 39         return file_ls, slogn
 40     else:
 41         file_t_ls = os.listdir(dirpath)
 42         for file_item in file_t_ls:
 43             file_p = dirpath + "\\" + file_item
 44             if os.path.isfile(file_p):
 45                 i,j = os.path.splitext(file_p)
 46                 if j == ".txt"or j == ".TXT":
 47                     file_ls.append(file_p)
 48         print("文件路径已加载完毕...")
 49         return file_ls, slogn
 50 
 51 #转换列名为对应地类名称
 52 def convent_col(dict_1, index_name, DL):
 53     print(‘***文件处理中***‘)
 54     df = pd.DataFrame(dict_1,index=index_name)
 55     map_columns = DL["DLMC"]
 56     df.rename(columns=map_columns, inplace=True)
 57     df[‘合计‘]=df.sum(axis=1, numeric_only=True)
 58     #print(df)
 59     data = df.groupby(‘权属单位‘).agg(‘sum‘)
 60     return data
 61 
 62 #生成表格
 63 def deal_file(file_ls, dir_path):
 64     if len(file_ls) == 0:
 65         print("所选择的路径名为空")
 66         return ‘error‘
 67     else:
 68         print("总共{}个文件".format(len(file_ls)))
 69         for file_item in file_ls:
 70             #将文件名字作为首列索引（index_col）
 71             base_name = os.path.basename(file_item)
 72             #定义一个默认的值为列表的字典可以方便后期转化为DataFream二维表，以便向其中添加数据(地类模板)
 73             DL = read_json(CWD_PATH)
 74             tmp_dict = DL[‘DLBM‘]  #defaultdict(list)
 75             with open(file_item, ‘r‘, encoding=ENCODE) as file:
 76                 for line in file:
 77                     if ‘@‘ in line:
 78                         tmp_ls = line.strip().split(‘,‘)
 79                         area = tmp_ls[1]  #地类面积
 80                         qs = tmp_ls[4]    #地类权属
 81                         dlbm = tmp_ls[3]  #地类编码
 82                         tmp_dict["权属"].append(qs)
 83                         if isinstance(tmp_dict.get(str(dlbm)),list):
 84                             tmp_dict[dlbm.strip()].append(float(area))     #坐标文件中出现的地类编码都会创建一个键值对，键为地类编码，值为面积列表
 85                             count = len(tmp_dict.get("权属"))
 86                             for v in tmp_dict.values():
 87                                 if len(v) == count:
 88                                     continue
 89                                 else:
 90                                     v.append(0.0)
 91                         else:
 92                             print(str(dlbm))
 93             print(tmp_dict)
 94             del_key_ls = []
 95             for key,value in tmp_dict.items():
 96                 sum = reduce(lambda x, y : x + y, value)
 97                 if sum == 0:
 98                     del_key_ls.append(key)
 99             for i in del_key_ls:
100                 tmp_dict.pop(i)
101             index_name = tmp_dict["权属"]
102             data = convent_col(tmp_dict, index_name, DL)
103             #print(data)
104             save_single_data(data, dir_path, base_name)
105 
106  #存储表格   
107 def save_single_data(data, s_path, name):
108     print(‘***文件正在保存***‘)
109     save_path = s_path + ‘\\‘ + name + ‘.xlsx‘
110     data.to_excel(save_path,sheet_name=‘S_FLB‘,float_format=‘%.4f‘)
111     print(‘DataFrame is written successfully to the Excel File.‘)
112 
113 #主程序
114 def main_app(dirpath):
115     file_ls = []
116     f_ls, s = get_file(dirpath,file_ls)
117     if s:
118         dirpath = os.path.dirname(dirpath)            
119     deal_file(f_ls, dirpath)
120     return "生成地类分类报表成功"
121     
122 if __name__ == "__main__":
123     dirpath = input("请输入要处理的文件路径:")
124     main_app(dirpath)