从python中的字典列表的json文件中获取数据帧
我需要从每个内容id，likeCount和displayName的json响应中获取数据框。
除了displayname之外，其他所有工作都很正常。
它出错了：
KeyError: 'author'
我使用的代码：
df=pd.DataFrame([])
for i in json_data['list']:
df=df.append(pd.DataFrame({'Content_id':[i['contentID']],'subject':[i['subject']],'published':[i['published']],'updated':[i['updated']],'viewCount':i['viewCount'],'type':i['type'],'name':[i['author']['displayName']]},index=[0]),ignore_index=True)
print(df.head())
＆＃13;
＆＃13;
＆＃13;
＆＃13;
{
"itemsPerPage": 100,
"links": {
"next": "https:"
},
"list": [
{
"id": "77248",
"resources": {
"entitlements": {
"allowed": [
"GET"
],
"ref": "https:"
},
"outcomeTypes": {
"allowed": [
"GET"
],
"ref": "https:"
},
"childOutcomeTypes": {
"allowed": [
"GET"
],
"ref": "https:"
},
"followingIn": {
"allowed": [
"POST",
"GET"
],
"ref": "https:"
},
"editHTML": {
"allowed": [
"GET"
],
"ref": "https:"
},
"attachments": {
"allowed": [
"POST",
"GET"
],
"ref": "https:"
},
"comments": {
"allowed": [
"POST",
"GET"
],
"ref": "https:"
},
"read": {
"allowed": [
"DELETE",
"POST"
],
"ref": "https:"
},
"followers": {
"allowed": [
"GET"
],
"ref": "https"
},
"versions": {
"allowed": [
"GET"
],
"ref": "https:"
},
"outcomes": {
"allowed": [
"POST",
"GET"
],
"ref": "https"
},
"self": {
"allowed": [
"GET",
"PUT"
],
"ref": "https:"
},
"html": {
"allowed": [
"GET"
],
"ref": "https:"
},
"extprops": {
"allowed": [
"DELETE",
"POST",
"GET"
],
"ref": "https:"
},
"likes": {
"allowed": [
"POST",
"GET"
],
"ref": "https:"
}
},
"followerCount": 1,
"followed": false,
"likeCount": 0,
"published": "2018-03-20T17:44:07.623+0000",
"tags": [],
"updated": "2018-03-20T17:44:07.639+0000",
"iconCss": "jive-icon-document",
"parentPlace": {
"id": "1063",
"html": "https:",
"name": "A's Sa",
"type": "group",
"uri": "https:"
},
"contentID": "1720297",
"author": {
"id": "361666",
"resources": {
"reports": {
"allowed": [
"GET"
],
"ref": "https:"
},
"followingIn": {
"allowed": [
"POST",
"GET"
],
"ref": "https:"
},
"images": {
"allowed": [
"GET"
],
"ref": "https:"
},
"activity": {
"allowed": [
"GET"
],
"ref": "https:"
},
"manager": {
"allowed": [
"GET"
],
"ref": "https:"
},
"social": {
"allowed": [
"GET"
],
"ref": "https:"
},
"recognition": {
"allowed": [
"GET"
],
"ref": "https:"
},
"trendingContent": {
"allowed": [
"GET"
],
"ref": "https:"
},
"trendingPlaces": {
"allowed": [
"GET"
],
"ref": "https:"
},
"avatar": {
"allowed": [
"GET"
],
"ref": "https:"
},
"followers": {
"allowed": [
"GET"
],
"ref": "https:"
},
"colleagues": {
"allowed": [
"GET"
],
"ref": "https"
},
"following": {
"allowed": [
"GET"
],
"ref": "https:"
},
"members": {
"allowed": [
"GET"
],
"ref": "https:"
},
"self": {
"allowed": [
"GET"
],
"ref": "https:"
},
"html": {
"allowed": [
"GET"
],
"ref": "https:"
},
"extprops": {
"allowed": [
"GET"
],
"ref": "https:"
}
},
"displayName": "R S",
"emails": [
{
"jive_label": "Email",
"primary": true,
"type": "work",
"value": "s.r@rjz.com",
"jive_displayOrder": 2,
"jive_showSummaryLabel": false
}
],
"jive": {
"enabled": true,
"level": {
"description": "Level 2",
"imageURI": "https:",
"name": "Novice",
"points": 154
},
"externalContributor": false,
"username": "522164052a",
"visible": true
},
"name": {
"familyName": "S",
"formatted": "R S",
"givenName": "R"
},
"type": "person"
},
"content": {
"text": "<body><!-- [] --><div class=\"jive-rendered-content\"><p>test zebra madagascar</p></div><!-- [] --></body>",
"editable": false,
"type": "text/html"
},
"parent": "https:",
"favoriteCount": 0,
"replyCount": 0,
"status": "published",
"subject": "Zebra",
"viewCount": 2,
"visibleToExternalContributors": false,
"parentVisible": true,
"parentContentVisible": true,
"lastActivity": 1521567847639,
"authorship": "open",
"categories": [],
"visibility": "place",
"outcomeTypes": [
{
"id": "3",
"name": "pending",
"confirmUnmark": false,
"shareable": true,
"confirmExclusion": false,
"noteRequired": true,
"urlAllowed": false,
"generalNote": false
},
{
"id": "6",
"name": "success",
"communityAudience": "true",
"confirmUnmark": false,
"shareable": false,
"confirmExclusion": false,
"noteRequired": true,
"urlAllowed": false,
"generalNote": true
},
{
"id": "2",
"name": "finalized",
"confirmUnmark": true,
"shareable": false,
"confirmExclusion": true,
"noteRequired": false,
"urlAllowed": false,
"generalNote": false
},
{
"id": "9",
"name": "wip",
"confirmContentEdit": "true",
"confirmUnmark": true,
"shareable": false,
"confirmExclusion": true,
"noteRequired": false,
"urlAllowed": false,
"generalNote": false
},
{
"id": "7",
"name": "outdated",
"confirmUnmark": false,
"shareable": false,
"confirmExclusion": false,
"noteRequired": false,
"urlAllowed": true,
"generalNote": false
}
],
"attachments": [],
"restrictComments": false,
"type": "document",
"lastActivityDate": "2018-03-20T17:44:07.639+0000"
}
],
"startIndex":0
我想要的输出是，
2 个答案:
答案 0 :(得分：0)
KeyError: 'anything'通常表示未找到您的词典密钥。
我建议改为使用get;
import pandas as pd
for i in json_data.get('list',[]):
dfDICT = {'Content_id':[i.get('contentID',None)],
'subject':[i.get('subject',None)],
'published':[i.get('published',None)],
'updated':[i.get('updated',None)],
'likeCount':i.get('likeCount',None)
}
if i.get('author',None): # Test if your key exists
dfDICT['name'] = i.get('author').get('displayName',None)
# NOTE: displayname --> displayName
else: # Included for consistency
dfDICT['name'] = None
df=df.append(pd.DataFrame(dfDICT,index=[0]),ignore_index=True)
print(df.head())
注意： get如果只传递一个参数，则默认为None。
答案 1 :(得分：0)
我不确定您是否遗漏了您提供的代码或json中的内容，但我没有收到您在问题中提到的错误。
我在这里发布json格式
{
"itemsPerPage": 100,
"links": {
"next": "https:"
},
"list": [
{
"id": "77248",
"resources": {
"entitlements": {
"allowed": [
"GET"
],
"ref": "https:"
},
"outcomeTypes": {
"allowed": [
"GET"
],
"ref": "https:"
},
"childOutcomeTypes": {
"allowed": [
"GET"
],
"ref": "https:"
},
"followingIn": {
"allowed": [
"POST",
"GET"
],
"ref": "https:"
},
"editHTML": {
"allowed": [
"GET"
],
"ref": "https:"
},
"attachments": {
"allowed": [
"POST",
"GET"
],
"ref": "https:"
},
"comments": {
"allowed": [
"POST",
"GET"
],
"ref": "https:"
},
"read": {
"allowed": [
"DELETE",
"POST"
],
"ref": "https:"
},
"followers": {
"allowed": [
"GET"
],
"ref": "https"
},
"versions": {
"allowed": [
"GET"
],
"ref": "https:"
},
"outcomes": {
"allowed": [
"POST",
"GET"
],
"ref": "https"
},
"self": {
"allowed": [
"GET",
"PUT"
],
"ref": "https:"
},
"html": {
"allowed": [
"GET"
],
"ref": "https:"
},
"extprops": {
"allowed": [
"DELETE",
"POST",
"GET"
],
"ref": "https:"
},
"likes": {
"allowed": [
"POST",
"GET"
],
"ref": "https:"
}
},
"followerCount": 1,
"followed": false,
"likeCount": 0,
"published": "2018-03-20T17:44:07.623+0000",
"tags": [],
"updated": "2018-03-20T17:44:07.639+0000",
"iconCss": "jive-icon-document",
"parentPlace": {
"id": "1063",
"html": "https:",
"name": "A's Sa",
"type": "group",
"uri": "https:"
},
"contentID": "1720297",
"author": {
"id": "361666",
"resources": {
"reports": {
"allowed": [
"GET"
],
"ref": "https:"
},
"followingIn": {
"allowed": [
"POST",
"GET"
],
"ref": "https:"
},
"images": {
"allowed": [
"GET"
],
"ref": "https:"
},
"activity": {
"allowed": [
"GET"
],
"ref": "https:"
},
"manager": {
"allowed": [
"GET"
],
"ref": "https:"
},
"social": {
"allowed": [
"GET"
],
"ref": "https:"
},
"recognition": {
"allowed": [
"GET"
],
"ref": "https:"
},
"trendingContent": {
"allowed": [
"GET"
],
"ref": "https:"
},
"trendingPlaces": {
"allowed": [
"GET"
],
"ref": "https:"
},
"avatar": {
"allowed": [
"GET"
],
"ref": "https:"
},
"followers": {
"allowed": [
"GET"
],
"ref": "https:"
},
"colleagues": {
"allowed": [
"GET"
],
"ref": "https"
},
"following": {
"allowed": [
"GET"
],
"ref": "https:"
},
"members": {
"allowed": [
"GET"
],
"ref": "https:"
},
"self": {
"allowed": [
"GET"
],
"ref": "https:"
},
"html": {
"allowed": [
"GET"
],
"ref": "https:"
},
"extprops": {
"allowed": [
"GET"
],
"ref": "https:"
}
},
"displayName": "Rahman2 Syd",
"emails": [
{
"jive_label": "Email",
"primary": true,
"type": "work",
"value": "s.r@rjz.com",
"jive_displayOrder": 2,
"jive_showSummaryLabel": false
}
],
"jive": {
"enabled": true,
"level": {
"description": "Level 2",
"imageURI": "https:",
"name": "Novice",
"points": 154
},
"externalContributor": false,
"username": "522164052a",
"visible": true
},
"name": {
"familyName": "S",
"formatted": "R S",
"givenName": "R"
},
"type": "person"
},
"content": {
"text": "<body><!-- [] --><div class=\"jive-rendered-content\"><p>test zebra madagascar<\/p><\/div><!-- [] --><\/body>",
"editable": false,
"type": "text/html"
},
"parent": "https:",
"favoriteCount": 0,
"replyCount": 0,
"status": "published",
"subject": "Zebra",
"viewCount": 2,
"visibleToExternalContributors": false,
"parentVisible": true,
"parentContentVisible": true,
"lastActivity": 1521567847639,
"authorship": "open",
"categories": [],
"visibility": "place",
"outcomeTypes": [
{
"id": "3",
"name": "pending",
"confirmUnmark": false,
"shareable": true,
"confirmExclusion": false,
"noteRequired": true,
"urlAllowed": false,
"generalNote": false
},
{
"id": "6",
"name": "success",
"communityAudience": "true",
"confirmUnmark": false,
"shareable": false,
"confirmExclusion": false,
"noteRequired": true,
"urlAllowed": false,
"generalNote": true
},
{
"id": "2",
"name": "finalized",
"confirmUnmark": true,
"shareable": false,
"confirmExclusion": true,
"noteRequired": false,
"urlAllowed": false,
"generalNote": false
},
{
"id": "9",
"name": "wip",
"confirmContentEdit": "true",
"confirmUnmark": true,
"shareable": false,
"confirmExclusion": true,
"noteRequired": false,
"urlAllowed": false,
"generalNote": false
},
{
"id": "7",
"name": "outdated",
"confirmUnmark": false,
"shareable": false,
"confirmExclusion": false,
"noteRequired": false,
"urlAllowed": true,
"generalNote": false
}
],
"attachments": [],
"restrictComments": false,
"type": "document",
"lastActivityDate": "2018-03-20T17:44:07.639+0000"
}
]
}
您提供的代码是：
for i in json_data['list']:
df=df.append(pd.DataFrame({'Content_id':[i['contentID']],'subject':[i['subject']],'published':[i['published']],'updated':[i['updated']],'likeCount':i['likeCount'],'name':i['author']['displayname']},index=[0]),ignore_index=True)
print(f.head())
运行它们会给你两个错误：
-
KeyError: displayname
密钥真的是displayName而不是displayname
-
f.head()- 更改为df.head()
我也不确定你的初始df是什么。假设它是一个空的DataFrame，打印df会给你
Content_id likeCount name published subject updated
0 1720297 0 Rahman2 Syd 2018-03-20T17:44:07.623+0000 Zebra 2018-03-20T17:44:07.639+0000
我不确定这是否是您正在寻找的输出，但它修复了错误，我让剩下的让您弄明白。
相关问题
最新问题
- 我写了这段代码，但我无法理解我的错误
- 我无法从一个代码实例的列表中删除 None 值，但我可以在另一个实例中。为什么它适用于一个细分市场而不适用于另一个细分市场？
- 是否有可能使 loadstring 不可能等于打印？卢阿
- java中的random.expovariate()
- Appscript 通过会议在 Google 日历中发送电子邮件和创建活动
- 为什么我的 Onclick 箭头功能在 React 中不起作用？
- 在此代码中是否有使用“this”的替代方法？
- 在 SQL Server 和 PostgreSQL 上查询，我如何从第一个表获得第二个表的可视化
- 每千个数字得到
- 更新了城市边界 KML 文件的来源？