我从json提取数据时遇到问题，我尝试了n种不同的方法。我能够提取ID本身，很遗憾，我无法显示该字段的详细信息。
以下是我的json
{
"params": {
"cid": "15482782896",
"datemax": "20190831",
"datemin": "20190601",
"domains": [
"url.com"
],
},
"results": {
"59107": {
"url.com": {
"1946592": {
"data": {
"2019-06-01": {
"ENGINE": {
"DEVICE": {
"": {
"position": 21,
"url": "url3.com"
}
}
}
},
"2019-07-01": {
"ENGINE": {
"DEVICE": {
"": {
"position": 4,
"url": "url3.com"
}
}
}
},
"2019-08-01": {
"ENGINE": {
"DEVICE": {
"": {
"position": 2,
"url": "url3.com"
}
}
}
}
},
"keyword": {
"title": "python_1",
"volume": 10
}
},
"1946602": {
"data": {
"2019-06-01": {
"ENGINE": {
"DEVICE": {
"": {
"position": 5,
"url": "url1.com"
}
}
}
},
"2019-07-01": {
"ENGINE": {
"DEVICE": {
"": {
"position": 12,
"url": "url1.com"
}
}
}
},
"2019-08-01": {
"ENGINE": {
"DEVICE": {
"": {
"position": 10.25,
"url": "url1.com"
}
}
}
}
},
"keyword": {
"title": "python_2",
"volume": 20
}
}
}
}
}
}
我尝试了以下代码，但以id本身的形式得到了结果
import json
import csv
def get_leaves(item, key=None):
if isinstance(item, dict):
leaves = {}
for i in item.keys():
leaves.update(get_leaves(item[i], i))
return leaves
elif isinstance(item, list):
leaves = {}
for i in item:
leaves.update(get_leaves(i, key))
return leaves
else:
return {key : item}
with open('me_filename') as f_input:
json_data = json.load(f_input)
fieldnames = set()
for entry in json_data:
fieldnames.update(get_leaves(entry).keys())
with open('output.csv', 'w', newline='') as f_output:
csv_output = csv.DictWriter(f_output, fieldnames=sorted(fieldnames))
csv_output.writeheader()
csv_output.writerows(get_leaves(entry) for entry in json_data)
我也尝试使用熊猫但也无法正确解析
import io
import json
import pandas as pd
with open('me_filename', encoding='utf-8') as f_input:
df = pd.read_json(f_input , orient='None')
df.to_csv('output.csv', encoding='utf-8')
结果我需要得到它：
ID Name page volume url 2019-06-01 2019-07-01 2019-08-01 2019-09-01
1946592 python_1 url.com 10 url3.com 21 4 2 null
1946602 python_2 url.com 20 url1.com 5 12 10,25 null
我该怎么办？
嗯，这是一个复杂的解决方案，看起来非常混乱，不再像提供的代码一样，但是我相信它将解决您的问题。
首先，我对提供的Json遇到了问题（由于在第8行的末尾加上了'，'），但是设法生成了：
ID,Name,Page,Volume,Url,2019-08-01,2019-07-01,2019-06-01,
1946592,python_1,url.com,10,url3.com,2,4,21,
1946602,python_2,url.com,20,url1.com,10.25,12,5,
使用以下内容：
import json
dates: set = set()
# Collect the data
def get_breakdown(json):
collected_data = []
for result in json['results']:
for page in json['results'][result]:
for _id in json['results'][result][page]:
data_struct = {
'ID': _id,
'Name': json['results'][result][page][_id]['keyword']['title'],
'Page': page,
'Volume': json['results'][result][page][_id]['keyword']['volume'],
'Dates': {}
}
for date in dates:
if date in json['results'][result][page][_id]['data']:
data_struct['URL'] = json['results'][result][page][_id]['data'][date]['ENGINE']['DEVICE']['']['url']
data_struct['Dates'][date] = {'Position' : json['results'][result][page][_id]['data'][date]['ENGINE']['DEVICE']['']['position']}
else:
data_struct['Dates'][date] = {'Position' : 'null'}
collected_data.append(data_struct)
return collected_data
# Collect all dates across the whole data
# structure and save them to a set
def get_dates(json):
for result in json['results']:
for page in json['results'][result]:
for _id in json['results'][result][page]:
for date in json['results'][result][page][_id]['data']:
dates.add(date)
# Write to .csv file
def write_csv(collected_data, file_path):
f = open(file_path, "w")
# CSV Title
date_string = ''
for date in dates:
date_string = '{0}{1},'.format(date_string, date)
f.write('ID,Name,Page,Volume,Url,{0}\n'.format(date_string))
# Data
for data in collected_data:
position_string = ''
for date in dates:
position_string = '{0}{1},'.format(position_string, data['Dates'][date]['Position'])
f.write('{0},{1},{2},{3},{4},{5}\n'.format(
data['ID'],
data['Name'],
data['Page'],
data['Volume'],
data['URL'],
position_string
))
# Code Body
with open('me_filename.json') as f_input:
json_data = json.load(f_input)
get_dates(json_data)
write_csv(get_breakdown(json_data), "output.csv")
希望您可以遵循该代码，并且可以完成预期的工作。我确信它可以变得更加可靠-但是，如前所述，我无法使其与您提供的基本代码一起使用。
本文收集自互联网，转载请注明来源。
如有侵权，请联系 [email protected] 删除。
我来说两句