Twitter API - 获取具有特定 ID 的推文

Question

我有一个推文 ID 列表，我想为其下载其文本内容。有什么简单的解决方案可以做到这一点，最好是通过 Python 脚本？我查看了 Tweepy 等其他库，但事情似乎并没有那么简单，手动下载它们是不可能的，因为我的列表很长。

Answer 1

您可以通过 statuses/show/:id API route 的 ID 访问特定的推文。大多数 Python Twitter 库都遵循完全相同的模式，或者为方法提供 'friendly' 名称。

例如，Twython offers several show_* methods, including Twython.show_status() 可让您加载特定推文：

CONSUMER_KEY = "<consumer key>"
CONSUMER_SECRET = "<consumer secret>"
OAUTH_TOKEN = "<application key>"
OAUTH_TOKEN_SECRET = "<application secret"
twitter = Twython(
    CONSUMER_KEY, CONSUMER_SECRET,
    OAUTH_TOKEN, OAUTH_TOKEN_SECRET)

tweet = twitter.show_status(id=id_of_tweet)
print(tweet['text'])

并且返回的字典遵循 API 给出的 Tweet object definition。

tweepy library uses tweepy.get_status():

auth = tweepy.OAuthHandler(CONSUMER_KEY, CONSUMER_SECRET)
auth.set_access_token(OAUTH_TOKEN, OAUTH_TOKEN_SECRET)
api = tweepy.API(auth)

tweet = api.get_status(id_of_tweet)
print(tweet.text)

它 returns 是一个稍微丰富的对象，但它的属性再次反映了已发布的 API。

Answer 2

您可以使用 status/lookup 端点批量访问推文（一次最多 100 条）：https://dev.twitter.com/rest/reference/get/statuses/lookup

Answer 3

分享我的工作，之前的回答大大加速了我的工作（谢谢）。此 Python 2.7 脚本获取存储在文件中的推文 ID 的文本。为您的输入数据格式调整 get_tweet_id()；原始配置用于 https://github.com/mdredze/twitter_sandy

处的数据

2018 年 4 月更新： 对@someone 错误报告的回复较晚（谢谢）。此脚本不再丢弃每 100 个推文 ID（这是我的错误）。请注意，如果某条推文因任何原因不可用，批量提取会自动跳过它。如果响应大小与请求大小不同，脚本现在会发出警告。

'''
Gets text content for tweet IDs
'''

# standard
from __future__ import print_function
import getopt
import logging
import os
import sys
# import traceback
# third-party: `pip install tweepy`
import tweepy

# global logger level is configured in main()
Logger = None

# Generate your own at https://apps.twitter.com/app
CONSUMER_KEY = 'Consumer Key (API key)'
CONSUMER_SECRET = 'Consumer Secret (API Secret)'
OAUTH_TOKEN = 'Access Token'
OAUTH_TOKEN_SECRET = 'Access Token Secret'

# batch size depends on Twitter limit, 100 at this time
batch_size=100

def get_tweet_id(line):
    '''
    Extracts and returns tweet ID from a line in the input.
    '''
    (tagid,_timestamp,_sandyflag) = line.split('\t')
    (_tag, _search, tweet_id) = tagid.split(':')
    return tweet_id

def get_tweets_single(twapi, idfilepath):
    '''
    Fetches content for tweet IDs in a file one at a time,
    which means a ton of HTTPS requests, so NOT recommended.

    `twapi`: Initialized, authorized API object from Tweepy
    `idfilepath`: Path to file containing IDs
    '''
    # process IDs from the file
    with open(idfilepath, 'rb') as idfile:
        for line in idfile:
            tweet_id = get_tweet_id(line)
            Logger.debug('get_tweets_single: fetching tweet for ID %s', tweet_id)
            try:
                tweet = twapi.get_status(tweet_id)
                print('%s,%s' % (tweet_id, tweet.text.encode('UTF-8')))
            except tweepy.TweepError as te:
                Logger.warn('get_tweets_single: failed to get tweet ID %s: %s', tweet_id, te.message)
                # traceback.print_exc(file=sys.stderr)
        # for
    # with

def get_tweet_list(twapi, idlist):
    '''
    Invokes bulk lookup method.
    Raises an exception if rate limit is exceeded.
    '''
    # fetch as little metadata as possible
    tweets = twapi.statuses_lookup(id_=idlist, include_entities=False, trim_user=True)
    if len(idlist) != len(tweets):
        Logger.warn('get_tweet_list: unexpected response size %d, expected %d', len(tweets), len(idlist))
    for tweet in tweets:
        print('%s,%s' % (tweet.id, tweet.text.encode('UTF-8')))

def get_tweets_bulk(twapi, idfilepath):
    '''
    Fetches content for tweet IDs in a file using bulk request method,
    which vastly reduces number of HTTPS requests compared to above;
    however, it does not warn about IDs that yield no tweet.

    `twapi`: Initialized, authorized API object from Tweepy
    `idfilepath`: Path to file containing IDs
    '''    
    # process IDs from the file
    tweet_ids = list()
    with open(idfilepath, 'rb') as idfile:
        for line in idfile:
            tweet_id = get_tweet_id(line)
            Logger.debug('Enqueing tweet ID %s', tweet_id)
            tweet_ids.append(tweet_id)
            # API limits batch size
            if len(tweet_ids) == batch_size:
                Logger.debug('get_tweets_bulk: fetching batch of size %d', batch_size)
                get_tweet_list(twapi, tweet_ids)
                tweet_ids = list()
    # process remainder
    if len(tweet_ids) > 0:
        Logger.debug('get_tweets_bulk: fetching last batch of size %d', len(tweet_ids))
        get_tweet_list(twapi, tweet_ids)

def usage():
    print('Usage: get_tweets_by_id.py [options] file')
    print('    -s (single) makes one HTTPS request per tweet ID')
    print('    -v (verbose) enables detailed logging')
    sys.exit()

def main(args):
    logging.basicConfig(level=logging.WARN)
    global Logger
    Logger = logging.getLogger('get_tweets_by_id')
    bulk = True
    try:
        opts, args = getopt.getopt(args, 'sv')
    except getopt.GetoptError:
        usage()
    for opt, _optarg in opts:
        if opt in ('-s'):
            bulk = False
        elif opt in ('-v'):
            Logger.setLevel(logging.DEBUG)
            Logger.debug("main: verbose mode on")
        else:
            usage()
    if len(args) != 1:
        usage()
    idfile = args[0]
    if not os.path.isfile(idfile):
        print('Not found or not a file: %s' % idfile, file=sys.stderr)
        usage()

    # connect to twitter
    auth = tweepy.OAuthHandler(CONSUMER_KEY, CONSUMER_SECRET)
    auth.set_access_token(OAUTH_TOKEN, OAUTH_TOKEN_SECRET)
    api = tweepy.API(auth)

    # hydrate tweet IDs
    if bulk:
        get_tweets_bulk(api, idfile)
    else:
        get_tweets_single(api, idfile)

if __name__ == '__main__':
    main(sys.argv[1:])

Answer 4

我没有足够的声誉来添加实际评论，很遗憾，这是要走的路：

我在 chrisinmtown 答案中发现了一个 bug 和一个奇怪的东西：

由于错误，每第 100 条推文将被跳过。这是一个简单的解决方案：

        if len(tweet_ids) < 100:
            tweet_ids.append(tweet_id)
        else:
            tweet_ids.append(tweet_id)
            get_tweet_list(twapi, tweet_ids)
            tweet_ids = list()

使用效果更好，因为它甚至可以超过速率限制。

api = tweepy.API(auth_handler=auth, wait_on_rate_limit=True, wait_on_rate_limit_notify=True)

Twitter API - 获取具有特定 ID 的推文

Twitter API - get tweets with specific id

python

twitter