tweepy将推特标签流收集到csv文件
我正在尝试运行这个脚本,目的是实时收集某个特定标签的推文,并把它们保存到一个csv文件里。现在我有的这个脚本可以在控制台上打印信息,并创建一个包含作者、日期和文本的csv文件。不过,流式获取的推文并没有被保存到这个csv文件里。
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'])
1 个回答
0
你需要在 on_status 外面使用一个全局变量 writer。
比如说(用你的代码举个例子)
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)