Update app.py
Browse files
app.py
CHANGED
@@ -41,98 +41,164 @@ def searcht():
|
|
41 |
return jsonify(first_song)
|
42 |
|
43 |
|
44 |
-
# Function to extract track ID from Amazon Music URL
|
45 |
def extract_amazon_track_id(url: str):
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
return None
|
58 |
-
|
59 |
|
60 |
-
|
61 |
def get_song_link_info(url: str):
|
62 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
if "music.amazon.com" in url:
|
64 |
track_id = extract_amazon_track_id(url)
|
65 |
if track_id:
|
66 |
-
|
67 |
-
|
|
|
68 |
else:
|
69 |
-
|
70 |
-
api_url = f"https://api.song.link/v1-alpha.1/links?url={url}&userCountry=US"
|
71 |
else:
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
|
77 |
-
|
78 |
return response.json()
|
79 |
-
|
|
|
80 |
return None
|
81 |
|
82 |
-
# Function to extract Tidal or YouTube URL
|
83 |
def extract_url(links_by_platform: dict, platform: str):
|
84 |
-
|
|
|
|
|
|
|
|
|
85 |
return links_by_platform[platform]["url"]
|
|
|
86 |
return None
|
87 |
|
88 |
-
|
89 |
-
# Function to extract track title and artist from entities
|
90 |
-
def extract_track_info(entities_by_unique_id: dict, platform: str):
|
91 |
-
for entity in entities_by_unique_id.values():
|
92 |
-
if entity["apiProvider"] == platform:
|
93 |
-
return entity["title"], entity["artistName"]
|
94 |
-
return None, None
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
@app.route('/match', methods=['POST'])
|
99 |
-
|
100 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
101 |
track_url = data.get('url')
|
|
|
|
|
|
|
|
|
102 |
|
103 |
-
|
104 |
-
raise HTTPException(status_code=400, detail="No URL provided")
|
105 |
|
106 |
track_info = get_song_link_info(track_url)
|
107 |
if not track_info:
|
108 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
109 |
|
110 |
-
youtube_url = extract_url(track_info["linksByPlatform"], "youtube")
|
111 |
-
entityUniqueId = track_info["entityUniqueId"]
|
112 |
-
logger.info(f"songlink info: {entityUniqueId}")
|
113 |
-
title = track_info["entitiesByUniqueId"][entityUniqueId]["title"]
|
114 |
-
artist = track_info["entitiesByUniqueId"][entityUniqueId]["artistName"]
|
115 |
if youtube_url:
|
116 |
-
video_id =
|
117 |
-
|
118 |
-
|
119 |
-
|
120 |
-
|
121 |
-
|
|
|
|
|
|
|
|
|
|
|
122 |
else:
|
123 |
-
|
124 |
-
|
|
|
|
|
|
|
|
|
|
|
125 |
search_results = ytmusic.search(search_query, filter="songs")
|
126 |
-
|
127 |
-
if
|
128 |
-
videoId
|
129 |
-
|
130 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
131 |
else:
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
raise HTTPException
|
136 |
|
137 |
|
138 |
|
|
|
41 |
return jsonify(first_song)
|
42 |
|
43 |
|
|
|
44 |
def extract_amazon_track_id(url: str):
|
45 |
+
"""
|
46 |
+
Extracts track ID from various Amazon Music URL formats.
|
47 |
+
"""
|
48 |
+
if "music.amazon.com" not in url: # MODIFIED: Slight logic inversion for early exit compared to original, same effective outcome.
|
49 |
+
return None
|
50 |
+
|
51 |
+
parsed_url = urlparse(url)
|
52 |
+
query_params = parse_qs(parsed_url.query)
|
53 |
+
|
54 |
+
if "trackAsin" in query_params:
|
55 |
+
return query_params["trackAsin"][0]
|
56 |
+
|
57 |
+
path_parts = parsed_url.path.split('/') # MODIFIED: Changed from simple `url.split` to more robust path parsing for Case 2.
|
58 |
+
if "tracks" in path_parts:
|
59 |
+
try:
|
60 |
+
track_id_index = path_parts.index("tracks") + 1
|
61 |
+
if track_id_index < len(path_parts):
|
62 |
+
return path_parts[track_id_index] # MODIFIED: Accessing specific part after "tracks".
|
63 |
+
except (ValueError, IndexError):
|
64 |
+
pass
|
65 |
+
|
66 |
+
logger.warning(f"Could not extract Amazon track ID from URL: {url}") # ADDED: Logging for when no ID is found.
|
67 |
return None
|
|
|
68 |
|
69 |
+
|
70 |
def get_song_link_info(url: str):
|
71 |
+
"""
|
72 |
+
Fetches track information from the Song.link API.
|
73 |
+
Uses requests.get() which is a blocking call.
|
74 |
+
"""
|
75 |
+
api_base_url = "https://api.song.link/v1-alpha.1/links" # ADDED: Defined base URL for clarity.
|
76 |
+
params = {"userCountry": "US"} # MODIFIED: Using a params dictionary for requests.get().
|
77 |
+
|
78 |
if "music.amazon.com" in url:
|
79 |
track_id = extract_amazon_track_id(url)
|
80 |
if track_id:
|
81 |
+
params["platform"] = "amazonMusic" # MODIFIED: Populating params dict.
|
82 |
+
params["id"] = track_id
|
83 |
+
params["type"] = "song"
|
84 |
else:
|
85 |
+
params["url"] = url # MODIFIED: Populating params dict.
|
|
|
86 |
else:
|
87 |
+
params["url"] = url # MODIFIED: Populating params dict.
|
88 |
+
|
89 |
+
try: # ADDED: try-except block for robust error handling during API call.
|
90 |
+
logger.info(f"Querying Song.link API with params: {params}") # ADDED: Logging the API query.
|
91 |
+
response = requests.get(api_base_url, params=params, timeout=10) # MODIFIED: Call uses base_url and params. ADDED: timeout.
|
92 |
+
response.raise_for_status() # ADDED: Checks for HTTP errors (4xx or 5xx responses).
|
93 |
return response.json()
|
94 |
+
except requests.exceptions.RequestException as e: # ADDED: Catching network/request related exceptions.
|
95 |
+
logger.error(f"Error fetching from Song.link API: {e}") # ADDED: Logging the specific error.
|
96 |
return None
|
97 |
|
|
|
98 |
def extract_url(links_by_platform: dict, platform: str):
|
99 |
+
"""
|
100 |
+
Extracts a specific platform URL from Song.link API response.
|
101 |
+
"""
|
102 |
+
# MODIFIED: Added .get("url") for safer access to prevent KeyError if "url" key is missing.
|
103 |
+
if platform in links_by_platform and links_by_platform[platform].get("url"):
|
104 |
return links_by_platform[platform]["url"]
|
105 |
+
logger.warning(f"No URL found for platform '{platform}' in links: {links_by_platform.keys()}") # ADDED: Logging if platform URL not found.
|
106 |
return None
|
107 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
108 |
@app.route('/match', methods=['POST'])
|
109 |
+
def match(): # MODIFIED: Changed from `async def` to `def` for synchronous Flask.
|
110 |
+
"""
|
111 |
+
Matches a given music track URL to a YouTube Music URL.
|
112 |
+
Expects a JSON body with "url".
|
113 |
+
"""
|
114 |
+
data = request.get_json()
|
115 |
+
if not data: # ADDED: Check for empty JSON payload.
|
116 |
+
logger.error("Match endpoint: No JSON payload received.") # ADDED: Logging.
|
117 |
+
return jsonify({"detail": "No JSON payload received."}), 400 # MODIFIED: Flask-style JSON error response.
|
118 |
+
|
119 |
track_url = data.get('url')
|
120 |
+
# MODIFIED: Added more specific validation for track_url presence and type.
|
121 |
+
if not track_url or not isinstance(track_url, str):
|
122 |
+
logger.error(f"Match endpoint: Invalid or missing URL: {track_url}") # ADDED: Logging.
|
123 |
+
return jsonify({"detail": "Valid 'url' string is required in request body."}), 400 # MODIFIED: Flask-style JSON error response.
|
124 |
|
125 |
+
logger.info(f"Match endpoint: Processing URL: {track_url}") # ADDED: Logging.
|
|
|
126 |
|
127 |
track_info = get_song_link_info(track_url)
|
128 |
if not track_info:
|
129 |
+
logger.error(f"Match endpoint: Could not fetch track info for URL: {track_url}") # ADDED: Logging.
|
130 |
+
# MODIFIED: Flask-style JSON error response instead of HTTPException.
|
131 |
+
return jsonify({"detail": "Could not fetch track info from Song.link API."}), 404
|
132 |
+
|
133 |
+
entity_unique_id = track_info.get("entityUniqueId") # MODIFIED: Used .get() for safer access.
|
134 |
+
title = None
|
135 |
+
artist = None
|
136 |
+
|
137 |
+
# MODIFIED: More robust extraction of title and artist with checks and logging.
|
138 |
+
if entity_unique_id and entity_unique_id in track_info.get("entitiesByUniqueId", {}):
|
139 |
+
main_entity = track_info["entitiesByUniqueId"][entity_unique_id]
|
140 |
+
title = main_entity.get("title")
|
141 |
+
artist = main_entity.get("artistName")
|
142 |
+
logger.info(f"Match endpoint: Found main entity - Title: '{title}', Artist: '{artist}'") # ADDED: Logging.
|
143 |
+
else:
|
144 |
+
logger.warning(f"Match endpoint: Could not find main entity details for {track_url} using entityUniqueId: {entity_unique_id}") # ADDED: Logging.
|
145 |
+
# ADDED: Fallback logic to find title/artist from other entities if main one fails.
|
146 |
+
for entity_id, entity_data in track_info.get("entitiesByUniqueId", {}).items():
|
147 |
+
if entity_data.get("title") and entity_data.get("artistName"):
|
148 |
+
title = entity_data.get("title")
|
149 |
+
artist = entity_data.get("artistName")
|
150 |
+
logger.info(f"Match endpoint: Using fallback entity - Title: '{title}', Artist: '{artist}' from entity ID {entity_id}") # ADDED: Logging.
|
151 |
+
break
|
152 |
+
if not title or not artist: # ADDED: Check if title/artist still not found after fallback.
|
153 |
+
logger.error(f"Match endpoint: Could not determine title and artist for URL: {track_url}") # ADDED: Logging.
|
154 |
+
return jsonify({"detail": "Could not determine title and artist from Song.link info."}), 404 # MODIFIED: Flask-style JSON error.
|
155 |
+
|
156 |
+
|
157 |
+
youtube_url = extract_url(track_info.get("linksByPlatform", {}), "youtube") # MODIFIED: Used .get() for safer access.
|
158 |
|
|
|
|
|
|
|
|
|
|
|
159 |
if youtube_url:
|
160 |
+
video_id = None
|
161 |
+
# MODIFIED: Improved video_id extraction from youtube_url, handles direct watch links and youtu.be, and strips extra params.
|
162 |
+
if "v=" in youtube_url:
|
163 |
+
video_id = youtube_url.split("v=")[1].split("&")[0]
|
164 |
+
elif "youtu.be/" in youtube_url: # MODIFIED: Handling for youtu.be links if present in song.link
|
165 |
+
video_id = youtube_url.split("youtu.be/")[1].split("?")[0]
|
166 |
+
|
167 |
+
filename = f"{title} - {artist}" if title and artist else "Unknown Track - Unknown Artist"
|
168 |
+
logger.info(f"Match endpoint: Found direct YouTube URL: {youtube_url}, Video ID: {video_id}") # ADDED: Logging.
|
169 |
+
# MODIFIED: Flask-style JSON response instead of returning dict directly.
|
170 |
+
return jsonify({"url": youtube_url, "filename": filename, "track_id": video_id}), 200
|
171 |
else:
|
172 |
+
logger.info(f"Match endpoint: No direct YouTube URL. Searching YTMusic with: '{title} - {artist}'") # ADDED: Logging.
|
173 |
+
# ADDED: Explicit check if title or artist is missing before searching.
|
174 |
+
if not title or not artist:
|
175 |
+
logger.error("Match endpoint: Cannot search YTMusic without title and artist.") # ADDED: Logging.
|
176 |
+
return jsonify({"detail": "Cannot search on YouTube Music without title and artist information."}), 400 # MODIFIED: Flask-style JSON error.
|
177 |
+
|
178 |
+
search_query = f'{title} {artist}' # MODIFIED: Changed from '+' to space for a more natural search query.
|
179 |
search_results = ytmusic.search(search_query, filter="songs")
|
180 |
+
|
181 |
+
if search_results:
|
182 |
+
# MODIFIED: Improved logic to pick the first song with a videoId using next() and .get().
|
183 |
+
first_song = next((song for song in search_results if song.get('videoId')), None)
|
184 |
+
if first_song and first_song.get('videoId'):
|
185 |
+
video_id = first_song["videoId"]
|
186 |
+
# MODIFIED: Changed ym_url to a standard YouTube watch URL format.
|
187 |
+
ym_url = f'https://music.youtube.com/watch?v={video_id}'
|
188 |
+
# MODIFIED: More robust filename generation using .get() and providing fallbacks.
|
189 |
+
filename = f"{first_song.get('title', title)} - {first_song.get('artists', [{'name': artist}])[0]['name']}"
|
190 |
+
logger.info(f"Match endpoint: Found YTMusic search result - URL: {ym_url}, Video ID: {video_id}") # ADDED: Logging.
|
191 |
+
# MODIFIED: Flask-style JSON response.
|
192 |
+
return jsonify({"filename": filename, "url": ym_url, "track_id": video_id}), 200
|
193 |
+
else:
|
194 |
+
logger.error(f"Match endpoint: YTMusic search for '{search_query}' yielded no results with a videoId.") # ADDED: Logging.
|
195 |
+
# MODIFIED: Flask-style JSON error response.
|
196 |
+
return jsonify({"detail": "No matching video ID found on YouTube Music after search."}), 404
|
197 |
else:
|
198 |
+
logger.error(f"Match endpoint: YTMusic search for '{search_query}' yielded no results.") # ADDED: Logging.
|
199 |
+
# MODIFIED: Flask-style JSON error response.
|
200 |
+
return jsonify({"detail": "No results found on YouTube Music for the track."}), 404
|
201 |
+
# REMOVED: The final `raise HTTPException` was determined to be unreachable and removed.
|
202 |
|
203 |
|
204 |
|