Get tweets containing keywords using Python Tweepy

I want to get tweets that include the #Weekend Hackathon keyword when creating a weekend hackathon website. Get it using Python's tweepy module.

Get Consumer API keys and Access token & access token secret

tweepy installation

Tweepy is convenient for operating the Twitter API, so please use it.

$ pip install tweepy

OAuth authentication

OAuth authentication required to operate Twitter API Authenticate using the API KEY obtained from the Developer site.

import tweepy


#Enter the obtained API KEY and TOKEN
API_KEY = ""
API_SECRET_KEY = ""
ACCESS_TOKEN = ""
ACCESS_TOKEN_SECRET = ""


def twitter_api() -> tweepy.API:
    auth = tweepy.OAuthHandler(API_KEY, API_SECRET_KEY)
    auth.set_access_token(ACCESS_TOKEN, ACCESS_TOKEN_SECRET)
    return tweepy.API(auth)

Keyword search

Created get_search method to enable keyword search

** Argument description **

KEY	Contents
api	OAuth authentication
q	Keywords you want to search
start_date	Search start period
end_date	Search end period
count	Number of acquisitions

Since the data is easy to process, I decided to put it in Pandas tweet_created_at is changed to Japan time after +9 hours because it is US time

from datetime import timedelta

import pandas as pd
import tweepy

#Enter the obtained API KEY and TOKEN
API_KEY = ""
API_SECRET_KEY = ""
ACCESS_TOKEN = ""
ACCESS_TOKEN_SECRET = ""


def twitter_api() -> tweepy.API:
    auth = tweepy.OAuthHandler(API_KEY, API_SECRET_KEY)
    auth.set_access_token(ACCESS_TOKEN, ACCESS_TOKEN_SECRET)
    return tweepy.API(auth)


def get_search(
    api: tweepy.API, q: str, start_date: str, end_date: str, count: int = 1000
) -> pd.DataFrame:

    q = f"{q} since:{start_date} until:{end_date} -filter:retweets"

    tweets = api.search(
        q=q,
        count=count,
        tweet_mode="extended",
        locale="ja",
        lang="ja",
        include_entities=False,
    )

    df = pd.DataFrame(
        columns=[
            "user_id",
            "user_name",
            "user_screen_name",
            "user_profile_image_url",
            "tweet_id",
            "tweet_full_text",
            "tweet_favorite_count",
            "tweet_created_at",
        ]
    )

    for tweet in tweets:
        df = df.append(
            {
                "user_id": tweet.user.id,
                "user_name": tweet.user.name,
                "user_screen_name": tweet.user.screen_name,
                "user_profile_image_url": tweet.user.profile_image_url.replace(
                    "_normal", ""
                ),
                "tweet_id": tweet.id,
                "tweet_full_text": tweet.full_text,
                "tweet_favorite_count": tweet.favorite_count,
                "tweet_created_at": tweet.created_at + timedelta(hours=+9),
            },
            ignore_index=True,
        )
    return df

How to use

Simple OAuth authentication and search, DataFrame so process it and use it

api = twitter_api()
search = get_search(api, "#Weekend hackathon", "2021-01-15", "2021-01-18")

idxmax = search.groupby("user_id").tweet_created_at.idxmax()
tweets = search.iloc[idxmax]