JSONDecodeError：預期值：第 2 行第 1 列（字符 1）

Question

JSON 文件添加：[JSON 文件][https://drive.google.com/file/d/1JXaalZ4Wu_1bQACrf8eNlIx80zvjopFr/view]

我正在分析帶有特定主題標簽的推文，但我不知道如何處理以下錯誤，感謝您的幫助。 錯誤消息來自行

推文 = json.loads（行）

當我運行代碼時，我在 JSONDecodeError 下方收到錯誤消息：期望值：第 2 行第 1 列（字符 1）

錯誤顯示在此單元格中（tweet = json.loads(line)）[錯誤圖像][2]

我的代碼：

# import tweepy library to access Twitter REST APIs service
import tweepy
#Python code to get twitter access
#Authorize access to Twitter using access keys & tokens from my developer account using tweepy OAuthHandler method
from tweepy import OAuthHandler 
import tweepy as tw
consumer_key=''
consumer_secret=''
access_token=''
access_token_secret=''
#online authuntication 
auth = tweepy.OAuthHandler(consumer_key,consumer_secret)
auth.set_access_token(access_token,access_token_secret)
api = tweepy.API(auth) #The api variable is now our entry point for most of the operations we can perform with Twitter.
api = tweepy.API(auth, wait_on_rate_limit = True, wait_on_rate_limit_notify = True)

#Source: https://marcobonzanini.com/2015/03/02/mining-twitter-data-with-python-part-1/
from tweepy import Stream
from tweepy.streaming import StreamListener
 
class MyListener(StreamListener):
 
    def on_data(self, data):
        try:
            with open('python.json', 'a') as f:
                f.write(data)
                return True
        except BaseException as e:
            print("Error on_data: %s" % str(e))
        return True
 
    def on_error(self, status):
        print(status)
        return True
 
twitter_stream = Stream(auth, MyListener())
twitter_stream.filter(track=['#covid19'])

from google.colab import files
uploaded = files.upload()

#Source: https://marcobonzanini.com/2015/03/02/mining-twitter-data-with-python-part-1/
import json
file='/content/python.json'
with open(file, 'r') as f:
    line = f.readline() # read only the first tweet/line
    tweet = json.loads(line) # load it as Python dict

# https://marcobonzanini.com/2015/03/09/mining-twitter-data-with-python-part-2/
import re
#define a variable to identify emotions
emoticons_str = r"""
    (?:
        [:=;] # Eyes
        [oO\-]? # Nose (optional)
        [D\)\]\(\]/\\OpP] # Mouth
    )"""
#define a list to identify emotions,HTML tags, mentions, hashtags, URLs, numbers, words with - and ', other words and anything else 
regex_str = [
    emoticons_str,
    r'<[^>]+>', # HTML tags
    r'(?:@[\w_]+)', # @-mentions
    r"(?:\#+[\w_]+[\w\'_\-]*[\w_]+)", # hash-tags
    r'http[s]?://(?:[a-z]|[0-9]|[$-_@.&amp;+]|[!*\(\),]|(?:%[0-9a-f][0-9a-f]))+', # URLs
 
    r'(?:(?:\d+,?)+(?:\.?\d+)?)', # numbers
    r"(?:[a-z][a-z'\-_]+[a-z])", # words with - and '
    r'(?:[\w_]+)', # other words
    r'(?:\S)' # anything else
]
#re.VERBOSE, to allow spaces in the regexp to be ignored  
#re.IGNORECASE to catch both upper and lowercases
tokens_re = re.compile(r'('+'|'.join(regex_str)+')', re.VERBOSE | re.IGNORECASE) 
emoticon_re = re.compile(r'^'+emoticons_str+'$', re.VERBOSE | re.IGNORECASE)
#The tokenize() function simply catches all the tokens in a string and returns them as a list 
def tokenize(s):
    return tokens_re.findall(s)
#preprocess(), which is used as a pre-processing chain: in this case we simply add a lowercasing feature for all the tokens that are not emoticons
def preprocess(s, lowercase=False):
    tokens = tokenize(s)
    if lowercase:
        tokens = [token if emoticon_re.search(token) else token.lower() for token in tokens]
    return tokens

#remove stop words
from nltk.corpus import stopwords
import string
import nltk
nltk.download('stopwords')
 
punctuation = list(string.punctuation)
stop = stopwords.words('english') + punctuation + ['rt', 'via']
terms_stop = [term for term in preprocess(tweet['text']) if term not in stop]

import re
import operator
import json
from collections import Counter
from nltk.corpus import stopwords
from nltk import bigrams
import string
from collections import defaultdict
import sys
com = defaultdict(lambda: defaultdict(int))
fname = '/content/python.json'
with open(fname, 'r') as f:
  count_all = Counter()
  for line in f:
    tweet = json.loads(line)
    terms_only = [term for term in preprocess(tweet['text']) if term not in stop and not term.startswith(('@', '#'))]
    count_all.update(terms_only)
  print(count_all.most_common(15))


  [1]: https://drive.google.com/file/d/1JXaalZ4Wu_1bQACrf8eNlIx80zvjopFr/view
  [2]: https://i.stack.imgur.com/XF1zI.png

Answer 1

當您從文件加載 json 時，您應該閱讀所有文件，請參閱文檔的load()鏈接

fname = '/content/python.json'
with open(fname, 'r') as f:
      for line in f.readlines():
        if line.startswith('{'):
            tweet = json.loads(line)

也可以使用此代碼搜索更多錯誤

fname = '/content/python.json'
with open(fname, 'r') as f:
      for line in f.readlines():
        if line.startswith('{'):
            try:
                json.loads(line)
            except json.JSONDecodeError as e:
                print(e.msg, e)
                print(repr(line))