Merge branch 'master' into hn-posts

Author: FirePing32

DIRECTORY.md

@@ -989,6 +989,7 @@
   * [Get Imdb Top 250 Movies Csv](https://github.com/TheAlgorithms/Python/blob/master/web_programming/get_imdb_top_250_movies_csv.py)
   * [Get Imdbtop](https://github.com/TheAlgorithms/Python/blob/master/web_programming/get_imdbtop.py)
   * [Get Top Hn Posts](https://github.com/TheAlgorithms/Python/blob/master/web_programming/get_top_hn_posts.py)
+  * [Get User Tweets](https://github.com/TheAlgorithms/Python/blob/master/web_programming/get_user_tweets.py)
   * [Giphy](https://github.com/TheAlgorithms/Python/blob/master/web_programming/giphy.py)
   * [Instagram Crawler](https://github.com/TheAlgorithms/Python/blob/master/web_programming/instagram_crawler.py)
   * [Instagram Pic](https://github.com/TheAlgorithms/Python/blob/master/web_programming/instagram_pic.py)

requirements.txt

@@ -14,5 +14,6 @@ sklearn
 statsmodels
 sympy
 tensorflow
+tweepy
 types-requests
 xgboost

web_programming/get_user_tweets.py

@@ -0,0 +1,60 @@
+import csv
+
+import tweepy
+
+# Twitter API credentials
+consumer_key = ""
+consumer_secret = ""
+access_key = ""
+access_secret = ""
+
+
+def get_all_tweets(screen_name: str) -> None:
+
+    # authorize twitter, initialize tweepy
+    auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
+    auth.set_access_token(access_key, access_secret)
+    api = tweepy.API(auth)
+
+    # initialize a list to hold all the tweepy Tweets
+    alltweets = []
+
+    # make initial request for most recent tweets (200 is the maximum allowed count)
+    new_tweets = api.user_timeline(screen_name=screen_name, 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(f"getting tweets before {oldest}")
+
+        # all subsiquent requests use the max_id param to prevent duplicates
+        new_tweets = api.user_timeline(
+            screen_name=screen_name, 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(f"...{len(alltweets)} tweets downloaded so far")
+
+    # transform the tweepy tweets into a 2D array that will populate the csv
+    outtweets = [[tweet.id_str, tweet.created_at, tweet.text] for tweet in alltweets]
+
+    # write the csv
+    with open(f"new_{screen_name}_tweets.csv", "w") as f:
+        writer = csv.writer(f)
+        writer.writerow(["id", "created_at", "text"])
+        writer.writerows(outtweets)
+
+
+if __name__ == "__main__":
+    # pass in the username of the account you want to download
+    get_all_tweets("FirePing32")