Question

#-*- coding:utf-8 -*-
import tweepy as tp
import datetime
import json
import sys
import time
import numpy as np

consumer_key='ThnJCL5MrFjUrEG...rqd3J'
consumer_secret='6u13y5wzZGUi8pNfvgjh...1strtxXAV8k3zXl9l76GZ5o'
access_token_key='1441391030-O3Sqn....n0aTqrrETtIVAwFzk03mP'
access_token_secret='AKRD....Xtyoj4BZEr4Ytm'
#创建认证对象
auth = tp.OAuthHandler(consumer_key,consumer_secret)
#设置token和密码
auth.set_access_token(access_token_key,access_token_secret)
api=tp.API(auth)
class MyStreamListener(tp.StreamListener):
    #def __init__(self,time_limit=3600):
        #self.start_time = time.time()
    def on_status(self, status):
            print(status.text)
 #reference:https://marcobonzanini.com/2015/03/02/mining-twitter-data-with-python-part-1/
    def on_data(self, data):
        try:
            with open('20181101', '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
myStreamListener = MyStreamListener()
myStream = tp.Stream(auth=api.auth,listener=myStreamListener)
myStream.filter(track = ['glasgow'])

tweet = json.loads(open(20181101).read())
tweet_texts = [tweet['text'] for tweet in tweet]
tweet_source = [tweet['source'] for tweet in tweet]
tweet_geo = [tweet['geo'] for tweet in tweet]
tweet_location = [tweet['location'] for tweet in tweet]
hashtags = [hashtag['text'] for tweet in tweet for hashtag in tweet['entities']['hashtags']]
print(tweet_texts)
print(tweet_geo)
print(tweet_location)
print(hashtags)

每一次，当我想打印tweet_texts时，都会显示错误：

文件“”，第1行，在 tweet = json.loads（open（20181101）.read（））

TypeError：强制转换为Unicode：需要字符串或缓冲区，找到int。这是从tweepy获得来自Twitter的推文的信息流，对此我很陌生。首先谢谢

Python3：TypeError：强制转换为Unicode：需要字符串或缓冲区，发现整数

0 个答案: