Question

我有一个像这样的json推文的txt文件，每条推文都在[“text”：＆amp; “is_quote_status”：]和日期是在行尾，如何将推文和日期提取到csv文件？

我终于能够用2个代码解决这个问题了。感谢@mark，需要时间来弄明白，但我做到了。

清理json文件。：

fin = open("sim.txt")
fout = open("output.txt", "w+")
delete_list = ['ObjectId(', 'NumberLong(','ISODate(', ')']
for line in fin:
    for word in delete_list:
        line = line.replace(word, "")
    fout.write(line)    
fin.close()
fout.close()

提取推文和日期以将其存储在.csv

中

import json
import csv
infile = open("output1.txt","r")
outfile=open("output4.csv","w")
json_s=infile.read()
writer=csv.writer(outfile)
for data in(json.loads(json_s)):
    x=data['text'].encode("utf-8")
    y=data['created_at_date'].encode("utf-8")
    writer.writerow([x,y])
infile.close()
outfile.close()
print 'DONE'

示例.json字符串我有 -

{
     "_id": "582f4fbd44b65941a0a81213",
     "contributors": null,
     "truncated": false,
     "text": "Tonight at 10 PM ET, 7 PM PT, on @FoxNews, a one hour special on me and my life by @HarveyLevinTMZ. Enjoy!",
     "is_quote_status": false,
     "in_reply_to_status_id": null,
     "id": "799660246788612100",
     "favorite_count": 15765,
     "source": "<a href=\"http://twitter.com\" rel=\"nofollow\">Twitter Web Client</a>",
     "retweeted": false,
     "coordinates": null,
     "entities": {
        "symbols": [],
        "user_mentions": [{
          "id": 1367531,
          "indices": [33, 41],
          "id_str": "1367531",
          "screen_name": "FoxNews",
          "name": "Fox News"
        }, {
          "id": 36098990,
          "indices": [83, 98],
          "id_str": "36098990",
          "screen_name": "HarveyLevinTMZ",
          "name": "Harvey Levin"
        }],
        "hashtags": [],
        "urls": []
      },
      "in_reply_to_screen_name": null,
      "in_reply_to_user_id": null,
      "retweet_count": 5251,
      "id_str": "799660246788612100",
      "favorited": false,
     "user": {
        "id": 25073877,
        "id_str": "25073877"
      },
      "geo": null,
      "in_reply_to_user_id_str": null,
      "lang": "en",
      "created_at": "Fri Nov 18 17:07:14 +0000 2016",
      "in_reply_to_status_id_str": null,
      "place": null,
      "created_at_date": "2016-11-18T17:07:14Z"
    }

Answer 1

请注意json路径，并且文本文件中必须包含有效的json。

<强> /path/to/json/file.json

[{
        "_id": "dummyid1",
        "contributors": null,
        "truncated": false,
        "text": "Dummy tweet 1",
        "is_quote_status": false,
        "in_reply_to_status_id": null,
        "id": "799660246788612100",
        "favorite_count": 15765,
        "source": "<a href=\"http://twitter.com\" rel=\"nofollow\">Twitter Web Client</a>",
        "retweeted": false,
        "coordinates": null,
        "entities": {
            "symbols": [],
            "user_mentions": [{
                "id": 1367531,
                "indices": [33, 41],
                "id_str": "1367531",
                "screen_name": "FoxNews",
                "name": "Fox News"
            }, {
                "id": 36098990,
                "indices": [83, 98],
                "id_str": "36098990",
                "screen_name": "HarveyLevinTMZ",
                "name": "Harvey Levin"
            }],
            "hashtags": [],
            "urls": []
        },
        "in_reply_to_screen_name": null,
        "in_reply_to_user_id": null,
        "retweet_count": 5251,
        "id_str": "799660246788612100",
        "favorited": false,
        "user": {
            "id": 25073877,
            "id_str": "25073877"
        },
        "geo": null,
        "in_reply_to_user_id_str": null,
        "lang": "en",
        "created_at": "Fri Nov 18 17:07:14 +0000 2016",
        "in_reply_to_status_id_str": null,
        "place": null,
        "created_at_date": "2016-11-18T17:07:14Z"
    },
    {
        "_id": "dummyid2",
        "contributors": null,
        "truncated": false,
        "text": "Dummy tweet 2",
        "is_quote_status": false,
        "in_reply_to_status_id": null,
        "id": "799660246788612100",
        "favorite_count": 15765,
        "source": "<a href=\"http://twitter.com\" rel=\"nofollow\">Twitter Web Client</a>",
        "retweeted": false,
        "coordinates": null,
        "entities": {
            "symbols": [],
            "user_mentions": [{
                "id": 1367531,
                "indices": [33, 41],
                "id_str": "1367531",
                "screen_name": "FoxNews",
                "name": "Fox News"
            }, {
                "id": 36098990,
                "indices": [83, 98],
                "id_str": "36098990",
                "screen_name": "HarveyLevinTMZ",
                "name": "Harvey Levin"
            }],
            "hashtags": [],
            "urls": []
        },
        "in_reply_to_screen_name": null,
        "in_reply_to_user_id": null,
        "retweet_count": 5251,
        "id_str": "799660246788612100",
        "favorited": false,
        "user": {
            "id": 25073877,
            "id_str": "25073877"
        },
        "geo": null,
        "in_reply_to_user_id_str": null,
        "lang": "en",
        "created_at": "Fri Nov 18 17:07:14 +0000 2016",
        "in_reply_to_status_id_str": null,
        "place": null,
        "created_at_date": "2016-11-18T17:07:14Z"
    }
]

<强> script.py

import json

with open('/path/to/json/file.json', 'r') as f:
    json_string = f.read()

datas_from_json = json.loads(json_string) # json string now a iterable list

for data in datas_from_json:
    print(data['text'])

# outputs
# Dummy tweet 1
# Dummy tweet 2

Answer 2

使用Pandas。

可以简化此过程

考虑到/path/to/input.json或/path/to/input.txt有一个有效的json文件，只要存在有效的json，文件扩展名就无关紧要。

import pandas as pd

df = pd.read_json("path/to/input.txt")
df[["text", "created_at_date"]].to_csv("output.csv", index=False)

在有效的json中，如何解析.txt并以CSV格式存储推文？

2 个答案: