clean player names in the hashtags

.env.sample

@@ -2,3 +2,4 @@ TWITTER_CONSUMER_KEY=TWITTER_CONSUMER_KEY
 TWITTER_CONSUMER_SECRET=TWITTER_CONSUMER_SECRET
 TWITTER_ACCESS_TOKEN=TWITTER_CONSUMER_SECRET
 TWITTER_ACCESS_TOKEN_SECRET=TWITTER_ACCESS_TOKEN_SECRET
+ENV=local

README.md

@@ -1,6 +1,6 @@
 # 🎾 Got Tennis Bot
 
-A bot to get the best games of the day from [tennisexplorer.com](https://tennisexplorer.com) and tweet.
+A [Twitter bot](https://twitter.com/GotTennisBot) to get the best games of the day from [tennisexplorer.com](https://tennisexplorer.com) and [tweet](https://twitter.com/GotTennisBot/status/1672490118588903425).
 
 Best games: games from players that have rank position <= 100
 

bot.py

@@ -46,7 +46,7 @@ def get_match_data(row):
   # head function is used just in case I want to limit when developing locally
   # get games of the day when both players have ranking position <= relevant_rank
   match_data = games\
-  .head(50)\
+  .head(1000)\
   .parallel_apply(get_match_data, axis=1)\
   .query('status != "complete"')\
   .query(f"player1_ranking <= {relevant_rank} and player2_ranking <= {relevant_rank}")
@@ -83,10 +83,13 @@ def get_player_data(row):
       print(f"failed to get player data for {row}")
       pass
 
+    def hashify(name):
+      return name.replace(" ", "").replace("'", "").replace("-", "")
+
     tour = row['tour'].upper()
-    tournament_hashtag = row['tournament'].replace(" ", "")
-    player1_hashtag = row['player1_name'].replace(" ", "")
-    player2_hashtag = row['player2_name'].replace(" ", "")
+    tournament_hashtag = hashify(row['tournament'])
+    player1_hashtag = hashify(row['player1_name'])
+    player2_hashtag = hashify(row['player2_name'])
 
     row["tweet"] = f"""
     {verbose_player1_name} (rank #{int(row['player1_ranking'])}) vs {verbose_player2_name} (rank #{int(row['player2_ranking'])})\n