Big commit

src/database_handler.py

@@ -0,0 +1,87 @@
+import sqlite3
+from enum import Enum
+
+
+class Table(Enum):
+    TRACK_INFORMATION = "track_information"
+    ARTIST_INFORMATION = "artist_information"
+    ALBUM_INFORMATION = "album_information"
+    TRACK_ATTRIBUTES = "track_attributes"
+    RECENTLY_PLAYED = "recently_played"
+
+
+class Database:
+    """
+    A class to handle the database connection and operations
+    """
+
+    def __init__(self, db_name):
+        """Initialize the connection to the database"""
+        self.db_name = db_name
+        self.conn = sqlite3.connect(db_name)
+        self.cursor = self.conn.cursor()
+        self.create_tables()
+
+    def create_tables(self):
+        """Create the tables in the database"""
+
+        self.cursor.execute(f'''
+        CREATE TABLE IF NOT EXISTS {Table.TRACK_INFORMATION.value} (
+            track_id TEXT PRIMARY KEY,
+            title TEXT
+        );
+        ''')
+
+        self.cursor.execute(f'''
+        CREATE TABLE IF NOT EXISTS {Table.ARTIST_INFORMATION.value} (
+            artist_id TEXT PRIMARY KEY,
+            artist_name TEXT
+        );
+        ''')
+
+        self.cursor.execute(f'''
+        CREATE TABLE IF NOT EXISTS {Table.ALBUM_INFORMATION.value} (
+            album_id TEXT PRIMARY KEY,
+            album_name TEXT
+        );
+        ''')
+
+        self.cursor.execute(f'''
+        CREATE TABLE IF NOT EXISTS {Table.TRACK_ATTRIBUTES.value} (
+            track_id TEXT PRIMARY KEY,
+            attribute_name TEXT,
+            attribute_value TEXT
+        );
+        ''')
+
+        self.cursor.execute(f'''
+        CREATE TABLE IF NOT EXISTS {Table.RECENTLY_PLAYED.value} (
+            played_at TIMESTAMP PRIMARY KEY,
+            track_id TEXT,
+            artist_id TEXT,
+            album_id TEXT,
+            FOREIGN KEY (track_id) REFERENCES {Table.TRACK_INFORMATION.value}(track_id),
+            FOREIGN KEY (artist_id) REFERENCES {Table.ARTIST_INFORMATION.value}(artist_id),
+            FOREIGN KEY (album_id) REFERENCES {Table.ALBUM_INFORMATION.value}(album_id)
+        );
+        ''')
+
+        # Commit the changes
+        self.conn.commit()
+
+    def add_row(self, table: Table, values):
+        """Add a new row into the specified table"""
+        placeholders = ', '.join(['?'] * len(values))
+        query = f"INSERT INTO {table.value} VALUES ({placeholders})"
+        self.cursor.execute(query, values)
+        self.conn.commit()
+
+    def read_all_rows(self, table: Table, column: str = "*"):
+        """Read all rows from the specified table"""
+        self.cursor.execute(f"SELECT {column} FROM {table.value}")
+        rows = self.cursor.fetchall()
+        return rows
+
+    def close(self):
+        """Close the database connection"""
+        self.conn.close()

src/scraper.py

@@ -1,19 +1,49 @@
 import requests
 
 from auth import authenticate
+from database_handler import Database, Table
+
+db = Database('spotify_scraped.db')
 
 
 def main():
     """
     This function is the main function that will be executed when the script is run
     """
+    global db
+
     scope = "user-read-recently-played"
     bearer_token = authenticate(scope)
+
+    # Once each 30 mins
+    _read_recently_played_page_and_add_to_db(bearer_token=bearer_token)
+
+    # Once a day
+    all_track_ids = db.read_all_rows(Table.RECENTLY_PLAYED, 'track_id')
+    for track_id in all_track_ids:
+        response = _get_track_information(track_id=track_id, bearer_token=bearer_token)
+        print(response)
+
+    # Close the database connection
+    db.close()
+
+
+def _read_recently_played_page_and_add_to_db(bearer_token: str):
+    """
+    """
+    global db
+
     last_played_track = _get_last_played_track(bearer_token=bearer_token)
-    print(last_played_track)
+
+    for track in last_played_track['items']:
+        track_id = track['track']['id']
+        played_at = track['played_at']
+        album_id = track['track']['album']['id']
+        artist_id = track['track']['artists'][0]['id']
+        db.add_row(Table.RECENTLY_PLAYED, (played_at, track_id, artist_id, album_id))
 
 
-def _get_last_played_track(limit: str = "1", bearer_token: str = "") -> dict:
+def _get_last_played_track(url: str = "https://api.spotify.com/v1/me/player/recently-played?limit=50", bearer_token: str = "") -> dict:
     """
     This function returns the last played track based on the limit size
 
@@ -26,7 +56,26 @@ def _get_last_played_track(limit: str = "1", bearer_token: str = "") -> dict:
         'Authorization': f'Bearer {bearer_token}'
     }
 
-    response = requests.get(f'https://api.spotify.com/v1/me/player/recently-played?limit={limit}', headers=header)
+    response = requests.get(url, headers=header)
+    response_json = response.json()
+    return response_json
+
+
+def _get_track_information(track_id: str, bearer_token: str) -> dict:
+    """
+    This function returns the track information based on the track id
+
+    :param track_id: str
+    :param bearer_token: str
+    :return: dict
+    """
+
+    url = f"https://api.spotify.com/v1/tracks/{track_id}"
+    header = {
+        'Authorization': f'Bearer {bearer_token}'
+    }
+
+    response = requests.get(url, headers=header)
     response_json = response.json()
     return response_json