根据用户ID爬取Twitter数据

我需要爬取的用户ID存放在一个.csv文件下，然后从官网注册到一个APP，并获得你的key和secret，写入下边的代码，就可以爬取tweets了。

每个ID会输出相应的tweet并且s会放在一个.csv文件里，而这个.csv文件就在你运行这段代码的文件夹下。

#!/usr/bin/env python

# encoding: utf-8

import tweepy

import csv

consumer_key = ""

consumer_secret = ""

access_key = ""

access_secret = ""

def get_all_tweets(user_id):

    auth = tweepy.OAuthHandler(consumer_key, consumer_secret)

    auth.set_access_token(access_key, access_secret)

    api = tweepy.API(auth)

    # 初始化一个数字来存储所有的tweets

    alltweets = []

    new_tweets = api.user_timeline(user_id=user_id, 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(user_id=user_id, 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")] for tweet in alltweets]

    # write the csv

    with open('%s_tweets.csv' % user_id, 'wb') as f:

        writer = csv.writer(f)

        writer.writerow(["tweet_id", "created_at", "text"])

        writer.writerows(outtweets)

    pass

if __name__ == '__main__':

    with open(这里写你的文件的位置，例如：'e:/file/userID.csv', 'rb') as f:

        ID = csv.reader(f)

        for row in ID:

# 这里运用了错误查询机制，遇到用户ID出现问题时，可以跳过

            try:

                get_all_tweets(row[0])

            except tweepy.TweepError, e:

                print 'Failed to run the command on that user, Skipping...'

            except IndexError, e:

                print 'List index out of range, Skipping...'

                continue