def find_matching_tweets(num_tweets=100,
fname="matching_tweets.csv",
shownum=50):
"""Given the number of tweets to retrieve, queries that number of tweets with
the keyword "Trump" and saves the tweet id and text as a csv file "fname". Prints
out the shownum amount of tweets using panda. Does not remove retweets."""
oauth = credsfromfile()
# create and register a streamer
client = Streamer(**oauth)
writer = TweetWriter(limit=num_tweets)
client.register(writer)
# get the name of the newly-created json file
input_file = writer.timestamped_file()
client.filter(track="trump") # case-insensitive
client.sample()
with open(input_file) as fp:
# these two fields for now
json2csv(fp, fname, [
'id',
'text',
])
# pretty print using pandas
tweets = pd.read_csv(fname, encoding="utf8")
return tweets.head(shownum)
def senti_score_realtime(keyword,
client,
classifier,
twt_num,
step,
step_num,
verb=0):
score_all = np.zeros((twt_num, step_num))
for i in range(step_num):
origin = datetime.datetime.today()
end_t = origin + datetime.timedelta(minutes=step)
# don't store files in this case
client.register(TweetWriter(limit=twt_num))
tweets_gen = client.filter(track=keyword)
tweets = []
for t in tweets_gen:
tweets.append(t['text'])
score = classifier.test(tweets)
score_all[0:len(score[:, 0]), i] = score[:, 0]
if verb == 1:
print keyword + ' : ' + str(origin) + ' to ' + str(
end_t) + ' score=' + str(np.mean(score_all[:, i], axis=0))
time.sleep((end_t - origin).seconds)
return score_all
def streamtofile_demo(limit=20):
"""
Write 20 tweets sampled from the public Streaming API to a file.
"""
oauth = credsfromfile()
client = Streamer(**oauth)
client.register(TweetWriter(limit=limit, repeat=False))
client.statuses.sample()
def tweets_by_user_demo(user="******", count=200):
"""
Use the REST API to search for past tweets by a given user.
"""
oauth = credsfromfile()
client = Query(**oauth)
client.register(TweetWriter())
client.user_tweets(user, count)
def limit_by_time_demo(limit=20):
"""
Sample from the Streaming API and send output to terminal.
"""
oauth = credsfromfile()
client = Streamer(**oauth)
client.register(TweetWriter(limit=limit, date_limit=DATE))
client.sample()
from nltk.twitter.common import json2csv
from nltk.twitter.common import json2csv_entities
from nltk.corpus import twitter_samples
from nltk.twitter import Query, Streamer, Twitter, TweetViewer, TweetWriter, credsfromfile
import pandas as pd
oauth = credsfromfile()
n = 10 # 設定拿取 tweets 資料則數
username = '******'
# Query
client = Query(**oauth) # 歷史資料
client.register(TweetWriter()) # 寫入
client.user_tweets(username, n) # 拿取 tweets 資料(n則)
'''
使用 json2csv 存取 tweets 資料 (text欄位)
input_file 的 abspath 需參考上述 Query 寫入資料的路徑做修改
'''
input_file = twitter_samples.abspath('/Users/youngmihuang/twitter-files/tweets.20180726-155316.json')
with open(input_file) as fp:
json2csv(fp, 'tweets_text.csv', ['text'])
# 讀取
data = pd.read_csv('tweets_text.csv')
for line in data.text:
print('Trump tweets content: ')
print(line)
# 斷詞
def save_tweetes_file(self):
client = Streamer(**oauth)
client.register(TweetWriter(limit=100, subdir='twitter_samples_files'))
client.statuses.sample()
def __init__(self, lim=100):
TweetWriter.__init__(self, limit=lim, subdir="Tweets")