Skip to main content
 首页 » 编程设计

python之如何使用 tweepy 获取关注者数量

2025年05月04日9xiaohuochai

我正在尝试获取公司的关注者数量并随着时间的推移对其进行跟踪。我有超过 200,000 家公司,所以我目前拥有的代码实际上需要数年才能在当前的 api 限制下运行。

c = tweepy.Cursor(api.followers_ids, id = a) 
ids = [] 
for id in c.items(): 
   time.sleep(0.01) 
   ids.append(id) ' 

在这段代码中,它为每个关注者提供了一个 API。我想知道是否有一个函数可以将关注者计数作为数字给出?还有什么是 twitter api 限制?

请您参考如下方法:

每个 API 请求一次最多返回 5000 个关注者 ID,以检索 200,000 个公司的所有关注者,这是来自 Matthew A 的挖掘社交网络一书中的一个非常有用的脚本. Russell 解决twitter api限制

为了发出强大的 Twitter 请求和访问 Twitter 的 API Matthew 定义了这些方法:

import sys 
import time 
from urllib2 import URLError 
from httplib import BadStatusLine 
import json 
import twitter 
 
def oauth_login(): 
    CONSUMER_KEY = '' 
    CONSUMER_SECRET = '' 
    OAUTH_TOKEN = '' 
    OAUTH_TOKEN_SECRET = '' 
    auth = twitter.oauth.OAuth(OAUTH_TOKEN, OAUTH_TOKEN_SECRET, 
                               CONSUMER_KEY, CONSUMER_SECRET) 
    twitter_api = twitter.Twitter(auth=auth) 
    return twitter_api 
 
def make_twitter_request(twitter_api_func, max_errors=10, *args, **kw): 
# A nested helper function that handles common HTTPErrors. Return an updated 
# value for wait_period if the problem is a 500 level error. Block until the 
# rate limit is reset if it's a rate limiting issue (429 error). Returns None 
# for 401 and 404 errors, which requires special handling by the caller. 
    def handle_twitter_http_error(e, wait_period=2, sleep_when_rate_limited=True): 
        if wait_period > 3600: # Seconds 
            print >> sys.stderr, 'Too many retries. Quitting.' 
            raise e 
# See https://dev.twitter.com/docs/error-codes-responses for common codes 
        if e.e.code == 401: 
 
            print >> sys.stderr, 'Encountered 401 Error (Not Authorized)' 
            return None 
        elif e.e.code == 404: 
            print >> sys.stderr, 'Encountered 404 Error (Not Found)' 
            return None 
        elif e.e.code == 429: 
            print >> sys.stderr, 'Encountered 429 Error (Rate Limit Exceeded)' 
            if sleep_when_rate_limited: 
                print >> sys.stderr, "Retrying in 15 minutes...ZzZ..." 
                sys.stderr.flush() 
                time.sleep(60*15 + 5) 
                print >> sys.stderr, '...ZzZ...Awake now and trying again.' 
                return 2 
            else: 
                raise e # Caller must handle the rate limiting issue 
        elif e.e.code in (500, 502, 503, 504): 
            print >> sys.stderr, 'Encountered %iError. Retrying in %iseconds' %\ 
            (e.e.code, wait_period) 
            time.sleep(wait_period) 
            wait_period *= 1.5 
            return wait_period 
        else: 
            raise e 
# End of nested helper function 
    wait_period = 2 
    error_count = 0 
    while True: 
        try: 
            return twitter_api_func(*args, **kw) 
        except twitter.api.TwitterHTTPError, e: 
            error_count = 0 
            wait_period = handle_twitter_http_error(e, wait_period) 
            if wait_period is None: 
                return 
        except URLError, e: 
            error_count += 1 
            print >> sys.stderr, "URLError encountered. Continuing." 
            if error_count > max_errors: 
                print >> sys.stderr, "Too many consecutive errors...bailing out." 
                raise 
        except BadStatusLine, e: 
            error_count += 1 
            print >> sys.stderr, "BadStatusLine encountered. Continuing." 
            if error_count > max_errors: 
                print >> sys.stderr, "Too many consecutive errors...bailing out." 
                raise 

这里是获取好友和关注者的方法:

from functools import partial 
from sys import maxint 
 
def get_friends_followers_ids(twitter_api, screen_name=None, user_id=None, 
friends_limit=maxint, followers_limit=maxint): 
    # Must have either screen_name or user_id (logical xor) 
    assert (screen_name != None) != (user_id != None),\ 
    "Must have screen_name or user_id, but not both" 
    # See https://dev.twitter.com/docs/api/1.1/get/friends/ids and 
    # https://dev.twitter.com/docs/api/1.1/get/followers/ids for details 
    # on API parameters 
    get_friends_ids = partial(make_twitter_request, twitter_api.friends.ids, 
                             count=5000) 
    get_followers_ids = partial(make_twitter_request,twitter_api.followers.ids, 
                               count=5000) 
    friends_ids, followers_ids = [], [] 
    for twitter_api_func, limit, ids, label in [ 
                    [get_friends_ids, friends_limit, friends_ids, "friends"], 
                    [get_followers_ids, followers_limit, followers_ids, "followers"] 
                ]: 
        if limit == 0: continue 
        cursor = -1 
        while cursor != 0: 
 
            # Use make_twitter_request via the partially bound callable... 
            if screen_name: 
                response = twitter_api_func(screen_name=screen_name, cursor=cursor) 
            else: # user_id 
                response = twitter_api_func(user_id=user_id, cursor=cursor) 
            if response is not None: 
                ids += response['ids'] 
                cursor = response['next_cursor'] 
            print >> sys.stderr, 'Fetched {0} total {1} ids for{2}'.format(len(ids), 
                                                    label, (user_id or screen_name)) 
            # XXX: You may want to store data during each iteration to provide   
            # an additional layer of protection from exceptional circumstances 
            if len(ids) >= limit or response is None: 
                break 
    # Do something useful with the IDs, like store them to disk... 
    return friends_ids[:friends_limit], followers_ids[:followers_limit] 
 
# Sample usage 
twitter_api = oauth_login() 
friends_ids, followers_ids =get_friends_followers_ids(twitter_api, 
                                                      screen_name="SocialWebMining", 
                                                      friends_limit=10, 
                                                      followers_limit=10) 
print friends_ids 
print followers_ids