Merge pull request #13 from jjoeldaniel/dev

Update web scraping and refactor classes

example.py

@@ -1,4 +1,4 @@
-from geniusdotpy.genius_builder import GeniusBuilder
+from geniusdotpy.genius import Genius 
 from geniusdotpy.track import Track
 
 
@@ -7,21 +7,28 @@ def main():
     client_access_token = "token"
 
     # Create a GeniusBuilder object
-    genius = GeniusBuilder(client_access_token=client_access_token)
+    genius = Genius(client_access_token=client_access_token)
 
     # Search for a track by ID
-    print(genius.search_track_by_id(378195))
+    track1 = genius.search_track_by_id(378195)
+    print(repr(track1))
 
     # Search artist by ID
-    print(genius.search_artist(16775))
+    artist1 = genius.search_artist(track1.artist.id)
+    print(repr(artist1))
 
     # Search for a track by query
-    print(genius.search("Beat It")[0])
+    track3 = genius.search("Beat It")[0]
+    print(repr(track3))
 
     # Search tracks by artist
     tracks: list[Track] = genius.search_track_by_artist(artist_id=16775)
-    print(tracks[0])
-    print(tracks[0].lyrics)
+    track4 = tracks[0]
+    print(repr(track4))
+
+    # Retrieve lyrics
+    track4.get_lyrics()
+    print(track4.lyrics)
 
 
 if __name__ == "__main__":

geniusdotpy/album.py

@@ -1,12 +1,11 @@
 from geniusdotpy.artist import Artist
+import json
 
 
 class Album:
     """Album class"""
 
     def __init__(self, album_info: dict):
-        self.album_info = album_info
-        """JSON object containing album information."""
 
         self.name: str = album_info["name"]
         """Album name"""
@@ -26,3 +25,19 @@ def __init__(self, album_info: dict):
             self.full_title = album_info["full_title"]
         if "artist" in album_info:
             self.artist = Artist(album_info["artist"])
+
+        self.album_info: dict[str, str] = {
+            "name": self.name,
+            "url": self.url,
+            "full_title": self.full_title,
+            "artist": self.artist.artist_info,
+        }
+        """JSON object containing album information."""
+
+        self.json = json.dumps(self.album_info, indent=2)
+
+    def __str__(self):
+        return f"{self.name} by {self.artist}"    
+
+    def __repr__(self):
+        return self.json

geniusdotpy/artist.py

@@ -1,3 +1,5 @@
+import json
+
 class Artist:
     """Genius.com Artist class.
 
@@ -15,9 +17,6 @@ def __init__(self, artist_info: dict):
             Artist object
         """
 
-        self.artist_info = artist_info
-        """JSON object containing artist information."""
-
         self.api_path: str = artist_info["api_path"]
         """API path of the artist."""
 
@@ -30,5 +29,18 @@ def __init__(self, artist_info: dict):
         self.url: str = artist_info["url"]
         """Genius.com URL of the artist."""
 
+        self.artist_info: dict[str, str] = {
+            "api_path": self.api_path,
+            "id": self.id,
+            "name": self.name,
+            "url": self.url,
+        }
+        """Dictionary containing artist information."""
+
+        self.json = json.dumps(self.artist_info, indent=2)
+
     def __str__(self):
         return self.name
+
+    def __repr__(self):
+        return self.json

geniusdotpy/genius_builder.py → geniusdotpy/genius.py

@@ -2,10 +2,8 @@
 from geniusdotpy.artist import Artist
 from geniusdotpy.track import Track
 from geniusdotpy.utils import SortType
-from geniusdotpy.typing import queryID
 
-
-class GeniusBuilder:
+class Genius:
     endpoint = "https://api.genius.com"
     """Genius API endpoint"""
 
@@ -21,7 +19,7 @@ def __init__(self, client_access_token: str):
 
         self.headers = {"Authorization": f"Bearer {client_access_token}"}
 
-    def search_track_by_id(self, track_id: queryID):
+    def search_track_by_id(self, track_id: str | int):
         """Search for a track by ID.
 
         Keyword arguments:
@@ -38,7 +36,7 @@ def search_track_by_id(self, track_id: queryID):
 
         return Track(track_info=response.json()["response"]["song"])
 
-    def search_artist(self, artist_id: queryID):
+    def search_artist(self, artist_id: str | int):
         """Search for an artist by ID.
 
         Keyword arguments:
@@ -55,7 +53,7 @@ def search_artist(self, artist_id: queryID):
 
         return Artist(artist_info=response.json()["response"]["artist"])
 
-    def search(self, query: queryID) -> list[Track]:
+    def search(self, query: str | int) -> list[Track]:
         """Search for a track by query.
 
         Keyword arguments:
@@ -78,10 +76,10 @@ def search(self, query: queryID) -> list[Track]:
         return tracks
 
     def search_track_by_artist(
-        self, artist_id: queryID, sort=SortType.TITLE, page=1, per_page=20
+        self, artist_id: str | int, sort=SortType.TITLE, page=1, per_page=20
     ) -> list:
         endpoint = f"{self.endpoint}/artists/{artist_id}/songs?sort={sort.value}&per_page={per_page}&page={page}"
-        tracks = list()
+        tracks: list[Track] = list()
 
         response = requests.get(endpoint, headers=self.headers)
         response.raise_for_status()

geniusdotpy/track.py

@@ -2,6 +2,7 @@
 from geniusdotpy import utils
 from geniusdotpy.album import Album
 from geniusdotpy.artist import Artist
+import json
 
 
 class Track:
@@ -12,7 +13,6 @@ def __init__(self, track_info: dict):
             track_info -- JSON object containing track info
         """
 
-        self._track_info = track_info
         """JSON object containing track information."""
 
         self.api_path: str = track_info["api_path"]
@@ -24,7 +24,7 @@ def __init__(self, track_info: dict):
         self.url: str = track_info["url"]
         """Genius.com URL of the track."""
 
-        self.lyrics: str = utils.retrieve_lyrics(self.url)
+        self.lyrics: None | str = None
         """Track lyrics."""
 
         self.title: str = track_info["title"]
@@ -33,7 +33,6 @@ def __init__(self, track_info: dict):
         self.artist: Artist = Artist(track_info["primary_artist"])
         """Track artist."""
 
-        # Possibly null values
         self.release_date: None | datetime.datetime = None
         """Track release date."""
 
@@ -59,12 +58,45 @@ def __init__(self, track_info: dict):
 
         if "media" in track_info:
             for provider in track_info["media"]:
-                if provider["provider"] == "youtube":
-                    self.youtube_url = provider["url"]
-                elif provider["provider"] == "spotify":
-                    self.spotify_url = provider["url"]
-                elif provider["provider"] == "soundcloud":
-                    self.soundcloud_url = provider["url"]
+                match provider["provider"]:
+                    case "youtube":
+                        self.youtube_url = provider["url"]
+                    case "spotify":
+                        self.spotify_url = provider["url"]
+                    case "soundcloud":
+                        self.soundcloud_url = provider["url"]
+
+
+        self.track_info: dict = {
+            "api_path": self.api_path,
+            "id": self.id,
+            "url": self.url,
+            "lyrics": self.lyrics,
+            "title": self.title,
+            "artist": self.artist.artist_info,
+            "release_date": str(self.release_date),
+            "youtube_url": self.youtube_url,
+            "spotify_url": self.spotify_url,
+            "soundcloud_url": self.soundcloud_url,
+        }
+
+        if self.album:
+            self.track_info["album"] = self.album.album_info
+        else:
+            self.track_info["album"] = None
+
+        self.json = json.dumps(self.track_info, indent=2)
+
+    def get_lyrics(self) -> None | str:
+        """Retrieves the lyrics of the track."""
+
+        if not self.lyrics:
+            self.lyrics = utils.retrieve_lyrics(self.url)
+
+        return self.lyrics
 
     def __str__(self):
         return f"{self.title} by {self.artist.name}"
+
+    def __repr__(self):
+        return self.json

geniusdotpy/utils.py

@@ -20,8 +20,9 @@ def retrieve_lyrics(track_url: str):
 
     html = requests.get(track_url).content
     soup = BeautifulSoup(html, "html.parser")
+    res = soup.find("div", class_=lambda x: x and x.startswith("Lyrics__Container"))
 
-    res = soup.find("div", class_="Lyrics__Container-sc-1ynbvzw-5")
-    assert res, "Could not find lyrics (div.Lyrics__Container-sc-1ynbvzw-5))"
-
-    return res.get_text(separator="\n")
+    if res:
+        return res.get_text(separator="\n")
+    else:
+        return None