我试图使用以下代码提取推文,我刚刚意识到我只获得前140个字符。我在这方面有点新意,现在我需要将tweet_mode = extended和full_text放在某处,所以如果有人能指出我非常感激的地方。谢谢!
#!/usr/bin/env python
导入tweepy#https://github.com/tweepy/tweepy import csv
#Twitter API credentials
consumer_key = "5f55VEYRnHuBvVESy11OrBayI"
consumer_secret = "r0PcvNast4FLYD1HNQiJIsIDGtk72hhVFPzR3BfrIWfuSn2SWD"
access_key = "949748064985722880-Wpc3hErpGEeDC75MBfcDoo07X9WVcAo"
access_secret = "w02RdHMg1izgaFlKUJH3C5s9cDNue2h8XJv87E3TE0Whm"
def get_all_tweets(screen_name):
#Twitter only allows access to a users most recent 3240 tweets with
this method
#authorize twitter, initialize tweepy
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_key, access_secret)
api = tweepy.API(auth)
#initialize a list to hold all the tweepy Tweets
alltweets = []
#make initial request for most recent tweets (200 is the maximum
allowed count)
new_tweets = api.user_timeline(screen_name = screen_name,count=200,)
#save most recent tweets
alltweets.extend(new_tweets)
#save the id of the oldest tweet less one
oldest = alltweets[-1].id - 1
#keep grabbing tweets until there are no tweets left to grab
while len(new_tweets) > 0:
print "getting tweets before %s" % (oldest)
#all subsiquent requests use the max_id param to prevent duplicates
new_tweets = api.user_timeline(screen_name =
screen_name,count=200,max_id=oldest)
#save most recent tweets
alltweets.extend(new_tweets)
#update the id of the oldest tweet less one
oldest = alltweets[-1].id - 1
print "...%s tweets downloaded so far" % (len(alltweets))
#transform the tweepy tweets into a 2D array that will populate the csv
outtweets = [[tweet.id_str, tweet.created_at, tweet.text.encode("utf-
8"),tweet.retweet_count,tweet.favorite_count] for tweet in alltweets]
#write the csv
with open('%s_tweets.csv' % screen_name, 'wb') as f:
writer = csv.writer(f)
writer.writerow(["id","created_at","full_text","retweet_count","favorite_count"])
writer.writerows(outtweets)
pass
if __name__ == '__main__':
#pass in the username of the account you want to download
get_all_tweets("realdonaldtrump")
答案 0 :(得分:3)
将“tweet_mode = extended”放在此处:
new_tweets = api.user_timeline(screen_name = screen_name,
count=200,
tweet_mode=extended)
在这里:
while len(new_tweets) > 0:
new_tweets = api.user_timeline(screen_name = screen_name,
count=200,
max_id=oldest,
tweet_mode=extended)
将“full_tweet”放在此处:
outtweets = [[tweet.id_str,
tweet.created_at,
tweet.full_tweet.encode("utf-8"),
tweet.retweet_count,
tweet.favorite_count] for tweet in alltweets]