Pandas:访问 .json 文件中的值

Question

我正在尝试创建一个循环，让我访问.json文件(谷歌位置文件(中的值。我上周刚开始学习 Python，所以和我一起吧，非常感谢所有的帮助！

首先我的导入列表：

import pandas as pd
import requests
import json

比我打开.json文件：

with open('data_may.json', 'r') as fh:
raw = json.loads(fh.read())
data = raw['timelineObjects']
data

最后，我尝试创建一个循环来打印出纬度E7的值：

for locations in data[0:5]:
print(locations['placeVisit']['location']['latitudeE7'])

这是我收到的错误消息：

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-99-a8c46eea2476> in <module>
1 for locations in data[0:5]:
----> 2     print(locations['placeVisit']['location']['latitudeE7'])
KeyError: 'placeVisit'

我的.json文件是这样构造的：

{
"timelineObjects" : [ {
"activitySegment" : {
"startLocation" : {
"latitudeE7" : 520950336,
"longitudeE7" : 51250455,
"sourceInfo" : {
"deviceTag" : -1547871288
}
},
"endLocation" : {
"latitudeE7" : 520969498,
"longitudeE7" : 51162451,
"sourceInfo" : {
"deviceTag" : -1547871288
}
},
"duration" : {
"startTimestampMs" : "1556693508999",
"endTimestampMs" : "1556693710203"
},
"distance" : 652,
"activityType" : "CYCLING",
"confidence" : "HIGH",
"activities" : [ {
"activityType" : "CYCLING",
"probability" : 99.11152749237161
}, {
"activityType" : "WALKING",
"probability" : 0.6369730834565008
}, {
"activityType" : "RUNNING",
"probability" : 0.10388160016829592
} ],
"waypointPath" : {
"waypoints" : [ {
"latE7" : 520950508,
"lngE7" : 51250495
}, {
"latE7" : 520971412,
"lngE7" : 51164069
} ]
}
}
}, {
"placeVisit" : {
"location" : {
"latitudeE7" : 520967891,
"longitudeE7" : 51159244,
"placeId" : "ChIJOYpLXEFvxkcRtSdOEoh1Lns",
"address" : "Bemuurde Weerd Oostzijde 1n3514 AN UtrechtnNederland",
"name" : "LSR Landelijk Studenten Rechtsbureau",
"sourceInfo" : {
"deviceTag" : -1547871288
},
"locationConfidence" : 37.736637
},
"duration" : {
"startTimestampMs" : "1556693710203",
"endTimestampMs" : "1556713681618"
},
"placeConfidence" : "MEDIUM_CONFIDENCE",
"centerLatE7" : 520969163,
"centerLngE7" : 51162406,
"visitConfidence" : 93,
"otherCandidateLocations" : [ {
"latitudeE7" : 520967890,
"longitudeE7" : 51159240,
"placeId" : "ChIJOYpLXEFvxkcRV2Hp03ASVuI",
"locationConfidence" : 33.198143
}, {
"latitudeE7" : 520968971,
"longitudeE7" : 51161709,
"placeId" : "ChIJbeiKCEFvxkcRgiZQno9hikQ",
"semanticType" : "TYPE_WORK",
"locationConfidence" : 23.059763
}, {
"latitudeE7" : 520968160,
"longitudeE7" : 51158805,
"placeId" : "ChIJ-SXmBkVvxkcRtpNT_vTdQEE",
"locationConfidence" : 1.7593758
}, {
"latitudeE7" : 520971045,
"longitudeE7" : 51162728,
"placeId" : "ChIJd66UREFvxkcRZJCaM9z3baw",
"semanticType" : "TYPE_SEARCHED_ADDRESS",
"locationConfidence" : 0.6827666
} ],
"editConfirmationStatus" : "NOT_CONFIRMED"
}
}, {
"activitySegment" : {
"startLocation" : {
"latitudeE7" : 520967891,
"longitudeE7" : 51159244,
"sourceInfo" : {
"deviceTag" : -1547871288
}
},
"endLocation" : {
"latitudeE7" : 520942097,
"longitudeE7" : 51258010,
"sourceInfo" : {
"deviceTag" : -1547871288
}
},
"duration" : {
"startTimestampMs" : "1556713681618",
"endTimestampMs" : "1556713939630"
},
"distance" : 816,
"activityType" : "CYCLING",
"confidence" : "HIGH",
"activities" : [ {
"activityType" : "CYCLING",
"probability" : 99.41448992772163
}, {
"activityType" : "WALKING",
"probability" : 0.43749986739765867
}, {
"activityType" : "IN_PASSENGER_VEHICLE",
"probability" : 0.08513907766062832
} ],
"waypointPath" : {
"waypoints" : [ {
"latE7" : 520967674,
"lngE7" : 51158652
}, {
"latE7" : 520942306,
"lngE7" : 51260013
} ]
}
}
}, {
"placeVisit" : {
"location" : {
"latitudeE7" : 520941602,
"longitudeE7" : 51258926,
"placeId" : "ChIJ46vtEE9vxkcRyu8VVfUro2Q",
"address" : "Lucasbolwerk 18n3512 EH UtrechtnNederland",
"name" : "Lucasbolwerk 18",
"semanticType" : "TYPE_HOME",
"sourceInfo" : {
"deviceTag" : -1547871288
},
"locationConfidence" : 62.083218
},
"duration" : {
"startTimestampMs" : "1556713939630",
"endTimestampMs" : "1556731681066"
},
"placeConfidence" : "HIGH_CONFIDENCE",
"centerLatE7" : 520942021,
"centerLngE7" : 51257989,
"visitConfidence" : 95,
"otherCandidateLocations" : [ {
"latitudeE7" : 520940870,
"longitudeE7" : 51259290,
"placeId" : "ChIJu8CAEE9vxkcRRXzQvpFYiIk",
"locationConfidence" : 28.85588
}, {
"latitudeE7" : 520940508,
"longitudeE7" : 51258612,
"placeId" : "ChIJFXCOGk9vxkcRvLD0dAfMEwE",
"locationConfidence" : 0.79878336
}, {
"latitudeE7" : 520943848,
"longitudeE7" : 51258475,
"placeId" : "ChIJC9dtF09vxkcR9zOEsPmnHcQ",
"locationConfidence" : 0.35787553
}, {
"latitudeE7" : 520940508,
"longitudeE7" : 51258612,
"placeId" : "ChIJx2ucGk9vxkcRF_deiIhd7_k",
"locationConfidence" : 0.25281402
} ],
"editConfirmationStatus" : "NOT_CONFIRMED"
}
}, {

如您所见，目前我只是尝试在 placeVisit 之后访问该值。

提前谢谢你！

Answer 1

placeVisit只是在每timelineObjects项中，您需要检查placeVisit是否存在：

import json
with open('data_may.json', 'r') as fh:
raw = json.loads(fh.read())
data = raw['timelineObjects']

for locations in data[0:5]:
if 'placeVisit' in locations:
print(locations['placeVisit']['location']['latitudeE7'])
else:
print("Found activitySegment instead of placeVisit!")

输出：

Found activitySegment instead of placeVisit!
520967891
Found activitySegment instead of placeVisit!
520941602

Answer 2

让我们从 JSON 中存在多少个上层键开始：

data = <your-json-dictionary>
# print a list of your top-level keys 
print(list(data.keys()))

这表明，

>> ['timelineObjects']

现在让我们看看data['timelineObject']元素的键

for timelineObject in a['timelineObjects']:
print(list(timelineObject.keys()))

>> ['activitySegment']
['placeVisit']
['activitySegment']
['placeVisit']
...

但是，在某些嵌套词典中，键'placeVisit'不存在。当Python遇到这些情况时，它会提高keyError。当字典中找不到键时，您应该使用 python 的dict.get(key, default_when_key_is_missing)方法返回默认值。

for timelineObject in a['timelineObjects']:
print(timelineObject.get('placeVisit', None))

这将返回所需的输出。