Question

我正在尝试运行此脚本来收集特定主题标签的实时流式传输，并将其保存在csv文件中。这是我目前的脚本。它打印到控制台并创建一个包含作者，日期，文本行的csv文件。然而，流式推文不会保存到csv。

import sys
import tweepy
import csv

#pass security information to variables
consumer_key = ""
consumer_secret = ""
access_key = ""
access_secret = ""


#use variables to access twitter
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_key, access_secret)
api = tweepy.API(auth)

#create an object called 'customStreamListener'


class CustomStreamListener(tweepy.StreamListener):

def on_status(self, status): 
    print status.author.screen_name, status.created_at, status.text
    with open('file.csv', 'w') as f: 
                f.write('Author,Date,Text')
                writer = csv.writer(f)
                writer.writerow([status.author.screen_name, status.created_at, status.text])


def on_error(self, status_code):
    print >> sys.stderr, 'Encountered error with status code:', status_code
    return True # Don't kill the stream

def on_timeout(self):
    print >> sys.stderr, 'Timeout...'
    return True # Don't kill the stream




streamingAPI = tweepy.streaming.Stream(auth, CustomStreamListener())
streamingAPI.filter(track=['russia'])

Answer 1

您需要在on_status之外使用全局变量编写器。

例如（使用您的代码）

class CustomStreamListener(tweepy.StreamListener):
global writer
        writer = csv.writer(open('file.csv', 'w+'))
        w.writerow(('Author', 'Date', 'Text'))
def on_status(self, status): 
    print status.author.screen_name, status.created_at, status.text
    writer.writerow(status.author.screen_name, status.created_at, status.text)

tweepy收集twitter hashtag流到csv文件

1 个答案: