我正在处理一个有效的Big JSON文件。我正在尝试使用Pandas解析此文件。当我尝试使用常规data = pd.read_json(filename)方法读取此文件时。它读取文件。但是，当我尝试使用参数lines = True data = pd.read_json(filename, lines=True)时，会抛出错误 ValueError：预期的对象或值
我想使用块读取此文件。但是，如果我使用参数chunksize，则会出现相同的错误。
有人可以指出我在这里做错了什么。
filename='data/tinyTwitter.json'
data = pd.read_json(filename, lines=True, chunksize=100)
数据
{
"total_rows":3877777,
"offset":805584,
"rows":[
{
"id":"570379215192727552",
"key":[
"r1r01cdn8nb4",
2015,
2,
25
],
"value":{
"type":"Feature",
"geometry":{
"type":"Point",
"coordinates":[
144.92340088,
-37.95935781
]
},
"properties":{
"created_at":"Wed Feb 25 00:26:16 +0000 2015",
"text":"For the Oscars, Lady Gaga trained with a vocal coach DAILY for 6 months httmelbourne htto/ZSu8FifNUK",
"location":"melbourne"
}
},
"doc":{
"_id":"570379215192727552",
"_rev":"1-fa6a485cb4fe0575781b6c29286af554",
"contributors":null,
"truncated":false,
"text":"For the Oscars, Lady Gaga trained with a vocal coach DAILY for 6 months htDIIS5EtsW9 #melbourne ho/ZSu8FifNUK",
"in_reply_to_status_id":null,
"favorite_count":0,
"source":"",
"retweeted":false,
"coordinates":{
"type":"Point",
"coordinates":[
144.92340088,
-37.95935781
]
},
"entities":{
"symbols":[
],
"user_mentions":[
],
"hashtags":[
{
"indices":[
95,
105
],
"text":"melbourne"
}
],
"urls":[
{
"url":"",
"indices":[
72,
94
],
"expanded_url":"",
"display_url":"j.mp/1ag2Quk"
}
],
"media":[
{
"expanded_url":"",
"display_url":"pir.FifNUK",
"url":"http/ZSu8FifNUK",
"media_url_https":"",
"id_str":"570379215142457344",
"sizes":{
"large":{
"h":380,
"resize":"fit",
"w":380
},
"small":{
"h":340,
"resize":"fit",
"w":340
},
"medium":{
"h":380,
"resize":"fit",
"w":380
},
"thumb":{
"h":150,
"resize":"crop",
"w":150
}
},
"indices":[
106,
128
],
"type":"photo",
"id":570379215142457340,
"media_url":""
}
]
},
"in_reply_to_screen_name":null,
"in_reply_to_user_id":null,
"retweet_count":0,
"id_str":"570379215192727552",
"favorited":false,
"user":{
"follow_request_sent":false,
"profile_use_background_image":true,
"profile_text_color":"333333",
"default_profile_image":false,
"id":2543131938,
"profile_background_image_url_https":"",
"verified":false,
"profile_location":null,
"profile_image_url_https":"",
"profile_sidebar_fill_color":"DDEEF6",
"entities":{
"url":{
"urls":[
{
"url":"",
"indices":[
0,
22
],
"expanded_url":"",
"display_url":"youthsnews.com.au"
}
]
},
"description":{
"urls":[
]
}
},
"followers_count":68313,
"profile_sidebar_border_color":"C0DEED",
"id_str":"2543131938",
"profile_background_color":"C0DEED",
"listed_count":6,
"is_translation_enabled":false,
"utc_offset":36000,
"statuses_count":1390,
"description":"media network",
"friends_count":788,
"location":"pacific, oceania",
"profile_link_color":"042A38",
"profile_image_url":"",
"following":false,
"geo_enabled":true,
"profile_banner_url":"h8",
"profile_background_image_url":"htng",
"name":"ynnmedia™",
"lang":"en",
"profile_background_tile":false,
"favourites_count":765,
"screen_name":"ynnmedianetwork",
"notifications":false,
"url":"htxq",
"created_at":"Tue Jun 03 09:27:23 +0000 2014",
"contributors_enabled":false,
"time_zone":"Yakutsk",
"protected":false,
"default_profile":false,
"is_translator":false
},
"geo":{
"type":"Point",
"coordinates":[
-37.95935781,
144.92340088
]
},
"in_reply_to_user_id_str":null,
"possibly_sensitive":false,
"lang":"en",
"created_at":"Wed Feb 25 00:26:16 +0000 2015",
"in_reply_to_status_id_str":null,
"place":null,
"metadata":{
"iso_language_code":"en",
"result_type":"recent"
},
"location":"melbourne"
}
},
{
"id":"570379220146200576",
"key":[
"r1r01cdn8nb4",
2015,
2,
25
],
"value":{
"type":"Feature",
"geometry":{
"type":"Point",
"coordinates":[
144.92340088,
-37.95935781
]
},
"properties":{
"created_at":"Wed Feb 25 00:26:17 +0000 2015",
"text":"Abuses in AIB Roast were dubbed: Rakhi Sawant Ka",
"location":"melbourne"
}
},
"doc":{
"_id":"570379220146200576",
"_rev":"1-61252163c64f6f548cab2b8eb4cbd045",
"contributors":null,
"truncated":false,
"text":"Abuses in AIB Roast were dubbed: Rakhi Sawant ourne htco/MbglBYEAKa",
"in_reply_to_status_id":null,
"favorite_count":0,
"source":"t</a>",
"retweeted":false,
"coordinates":{
"type":"Point",
"coordinates":[
144.92340088,
-37.95935781
]
},
"entities":{
"symbols":[
],
"user_mentions":[
],
"hashtags":[
{
"indices":[
69,
79
],
"text":"melbourne"
}
],
"urls":[
{
"url":"htKiAELeMO6",
"indices":[
46,
68
],
"expanded_url":"/1ag2Omb",
"display_url":"j.mp/1ag2Omb"
}
],
"media":[
{
"expanded_url":"h79220146200576/photo/1",
"display_url":"pglBYEAKa",
"url":"rr",
"media_url":"pk4O5UIAAI0l",
"id_str":"570379220049731584",
"sizes":{
"large":{
"h":380,
"resize":"fit",
"w":380
},
"small":{
"h":340,
"resize":"fit",
"w":340
},
"medium":{
"h":380,
"resize":"fit",
"w":380
},
"thumb":{
"h":150,
"resize":"crop",
"w":150
}
},
"indices":[
80,
102
],
"type":"photo",
"id":570379220049731600,
"media_urrl":"htpk4O5UIAAI0l1.jpg"
}
]
},
"in_reply_to_screen_name":null,
"in_reply_to_user_id":null,
"retweet_count":0,
"id_str":"570379220146200576",
"favorited":false,
"user":{
"follow_request_sent":false,
"profile_use_background_image":true,
"profile_text_color":"333333",
"default_profile_image":false,
"id":2543131938,
"profile_background_image_url_https":"h/images/themes/theme1/bg.png",
"verified":false,
"profile_location":null,
"profile_image_url_https":"htt/567602629937606657/ZCcCDFzr_normal.jpeg",
"profile_sidebar_fill_color":"DDEEF6",
"entities":{
"url":{
"urls":[
{
"url":"htAxq",
"indices":[
0,
22
],
"expanded_url":"hws.com.au",
"display_url":"youth.au"
}
]
},
"description":{
"urls":[
]
}
},
"followers_count":68313,
"profile_sidebar_border_color":"C0DEED",
"id_str":"2543131938",
"profile_background_color":"C0DEED",
"listed_count":6,
"is_translation_enabled":false,
"utc_offset":36000,
"statuses_count":1390,
"description":"media network",
"friends_count":788,
"location":"pacific, oceania",
"profile_link_color":"042A38",
"profile_image_url":"htes/567602629937606657/ZCcCDFzr_normal.jpeg",
"following":false,
"geo_enabled":true,
"profile_banner_url":"httpanners/2543131938/1424079798",
"profile_background_image_url":"http/themes/theme1/bg.png",
"name":"ynnmedia™",
"lang":"en",
"profile_background_tile":false,
"favourites_count":765,
"screen_name":"ynnmedianetwork",
"notifications":false,
"url":"httgeAxq",
"created_at":"Tue Jun 03 09:27:23 +0000 2014",
"contributors_enabled":false,
"time_zone":"Yakutsk",
"protected":false,
"default_profile":false,
"is_translator":false
},
"geo":{
"type":"Point",
"coordinates":[
-37.95935781,
144.92340088
]
},
"in_reply_to_user_id_str":null,
"possibly_sensitive":false,
"lang":"en",
"created_at":"Wed Feb 25 00:26:17 +0000 2015",
"in_reply_to_status_id_str":null,
"place":null,
"metadata":{
"iso_language_code":"en",
"result_type":"recent"
},
"location":"melbourne"
}
}
]
}
答案 0 :(得分：0)
我在评论中添加了上面的链接。但我相信问题在于twitter响应将多种json格式发送到1个文件中，并且没有将它们分解。有效的解决方案是我将整个文件拿走，然后将它们分成一个列表。然后就分别与每个人一起工作。
import json
filename='data/tinyTwitter.json'
data = []
with open(filename) as json_file:
data_str = json_file.read()
data_str = data_str.split('[',1)[-1]
data_str = data_str.rsplit(']',1)[0]
data_str = data_str.split('][')
for jsonStr in data_str:
jsonStr = '[' + jsonStr + ']'
temp_data = json.loads(jsonStr)
for each in temp_data:
data.append(each)