处理100个句子记5500个单词的程序（将excel 转为json）

Posted 2020-11-25 zach0812

 

 1 import xlrd,json
 2 
 3 data = xlrd.open_workbook("C:\\Users\\zcb\\Desktop\\data.xlsx")
 4 
 5 sheet1 = data.sheet_by_name("Sheet1")
 6 final_data = []
 7 idx = 1
 8 for i in range(51,59):
 9     row = sheet1.row_values(i)
10     sentence ={}
11     sentence["sentence_id"] = row[0]
12     sentence["sentence"]=row[1].split("|")
13     sentence["语法笔记"]=row[2]
14     temp = row[3].split("|")[:-1]
15     temp_list = []
16     for i in range(0,len(temp),8):
17         temp_dict = {}
18         temp_dict["word_id"]=idx
19         temp_dict["word"] = temp[i].strip(" 
")
20         temp_dict["pron"] = temp[i + 1].strip(" 
")
21         temp_dict["词性"] = temp[i + 2].strip(" 
")
22         if ‘$‘ in temp_dict["词性"]:
23             temp_dict["词性"] = [l.strip(" ") for l in temp_dict["词性"].split("$")]
24         temp_dict["记忆"] = temp[i + 3].strip(" 
")
25         if ‘$‘ in temp_dict["记忆"]:
26             temp_dict["记忆"] = [l.strip(" ") for l in temp_dict["记忆"].split("$")]
27         temp_dict["搭配"] = temp[i + 4].strip(" 
")
28         if ‘$‘ in temp_dict["搭配"]:
29             temp_dict["搭配"] = [l.strip(" ") for l in temp_dict["搭配"].split("$")]
30         temp_dict["同义"] = temp[i + 5].strip(" 
")
31         if ‘$‘ in temp_dict["同义"]:
32             temp_dict["同义"] = [l.strip(" ") for l in temp_dict["同义"].split("$")]
33         temp_dict["反义"] = temp[i + 6].strip(" 
")
34         if ‘$‘ in temp_dict["反义"]:
35             temp_dict["反义"] = [l.strip(" ") for l in temp_dict["反义"].split("$")]
36         temp_dict["同根"] = temp[i + 7].strip(" 
")
37         if ‘$‘ in temp_dict["同根"]:
38             temp_dict["同根"] = [l.strip(" ") for l in temp_dict["同根"].split("$")]
39         temp_list.append(temp_dict)
40         idx +=1
41     sentence["核心词表"] = temp_list
42     temp = row[4].split("|")[:-1]
43     temp_list = []
44     for i in range(0,len(temp),8):
45         if "的词" in temp[i]:
46             topic = temp[i].split("的词")[0].strip(" 
")+"的词"
47 
48         temp_dict = {}
49         temp_dict["主题"] = topic
50         temp_dict["word_id"] = idx
51         temp_dict["word"] = temp[i].split("的词")[-1].strip("： 
")
52         temp_dict["pron"] = temp[i + 1].strip(" 
")
53         temp_dict["词性"] = temp[i + 2].strip(" 
")
54         if ‘$‘ in temp_dict["词性"]:
55             temp_dict["词性"] = [ l.strip(" ") for l in temp_dict["词性"].split("$") ]
56         temp_dict["记忆"] = temp[i + 3].strip(" 
")
57         if ‘$‘ in temp_dict["记忆"]:
58             temp_dict["记忆"] = [ l.strip(" ") for l in temp_dict["记忆"].split("$")  ]
59         temp_dict["搭配"] = temp[i + 4].strip(" 
")
60         if ‘$‘ in temp_dict["搭配"]:
61             temp_dict["搭配"] = [ l.strip(" ") for l in temp_dict["搭配"].split("$")  ]
62         temp_dict["同义"] = temp[i + 5].strip(" 
")
63         if ‘$‘ in temp_dict["同义"]:
64             temp_dict["同义"] = [ l.strip(" ") for l in temp_dict["同义"].split("$")  ]
65         temp_dict["反义"] = temp[i + 6].strip(" 
")
66         if ‘$‘ in temp_dict["反义"]:
67             temp_dict["反义"] = [ l.strip(" ") for l in temp_dict["反义"].split("$")  ]
68         temp_dict["同根"] = temp[i + 7].strip(" 
")
69         if ‘$‘ in temp_dict["同根"]:
70             temp_dict["同根"] =  [ l.strip(" ") for l in temp_dict["同根"].split("$")  ]
71         idx+=1
72         temp_list.append(temp_dict)
73     sentence["主题归纳"] = temp_list
74 
75     final_data.append(sentence)
76 with open("final_data.json","w",encoding="utf8") as f:
77     json.dump(final_data,f,ensure_ascii=False)

View Code

data.zip ：https://files.cnblogs.com/files/zach0812/data.zip