python - 计算标签的推文

Question

我想知道是否有任何方法可以使用 hashtags.org 之类的流 API 计算来自 twitter 的主题标签50 条推文/秒。这是代码：

#!/usr/bin/python
import tweetstream
    import sys
    print sys.argv
    twitterUsername = "user"
    twitterPassword = "pass"
    twitterWordFilter = sys.argv[1]

    try:
        with tweetstream.FilterStream(twitterUsername, twitterPassword,track=twitterWordFilter) as stream:
            for tweet in stream:
                print stream.count

    except tweetstream.ConnectionError, e:
        print "Disconnected from twitter. Reason:", e.reason

Answer 1

def get_tweet_count(term):

    total_tweet_count = 0 
    page = 1
    while True:
        url = 'http://search.twitter.com/search.json?q=' 
                + urllib.quote(term) + '&rpp=100&page=' + str(page)

        response = urllib2.urlopen(url)
        json_content = response.read()
        tweets = json.loads(json_content)['results']
        total_tweet_count += len(tweets)

        # Are we at the last page or have we run out of pages?
        if len(tweets) < 100 or page >= 15:
            break

        max_id = tweets[0]['id_str']
        page += 1
        # Wait so twitter doesn't get annoyed with us
        time.sleep(1)

    return total_tweet_count

这个脚本我改编自GitHub 上的代码。