.env.example

@@ -0,0 +1,9 @@
+# Copy to `.env` and fill in, then `source .env` before running.
+# Get these from https://developer.spotify.com/dashboard (your app's settings).
+# Register `http://127.0.0.1:8888` as a Redirect URI in that app.
+export SPOTIFY_CLIENT_ID=your_client_id_here
+export SPOTIFY_CLIENT_SECRET=your_client_secret_here
+
+# Optional overrides:
+# export MUSIC_LIBRARY_PATH=~/Music
+# export WORK_DIR=./work_dir/new

.gitignore

@@ -2,6 +2,8 @@ prefetched*
 __pycache__
 .idea
 secret
+.env
+.venv
 work_dir
 old
 tmp

Env.py

@@ -1,7 +1,13 @@
+import os
 from pathlib import Path
 
-local_library_path = Path("/home/auser/Music/")
+# Local config. Paths can be overridden via environment variables.
-work_dir = Path("./work_dir/new")
+local_library_path = Path(os.environ.get("MUSIC_LIBRARY_PATH", "~/Music")).expanduser()
+work_dir = Path(os.environ.get("WORK_DIR", "./work_dir/new"))
 
-client_id = '3b4db45bb66b45e9a2532989c8034332'
+# Spotify app credentials. NEVER hardcode these here — set them in the
-client_secret = "ed03dce79ec049e59b1bf20967aba418"
+# environment (see .env.example) so they don't end up in version control.
+#   export SPOTIFY_CLIENT_ID=...
+#   export SPOTIFY_CLIENT_SECRET=...
+client_id = os.environ.get("SPOTIFY_CLIENT_ID")
+client_secret = os.environ.get("SPOTIFY_CLIENT_SECRET")

Flow.py

@@ -26,7 +26,7 @@ class Flow:
     itunes_library : Library = None
 
     @staticmethod
-    def fetch_spotify(self):
+    def fetch_spotify():
         fetch_all(client_id, client_secret, work_dir)
 
     @staticmethod

README.md

@@ -1,3 +1,100 @@
-# spotifyFetcher
+# MusicIndexer
-loads all data through web api<br>
+
-client secret - 4ced4e4575094b749834a60996680c6c
+Pull your Spotify library and listening stats via the Spotify Web API, index a
+local music library (audio tags + iTunes XML), and match the two so you can see
+which tracks you own, what's missing, and your top artists/tracks/playlists — in
+a Streamlit GUI.
+
+## Features
+
+- **Spotify backend** — OAuth (Authorization Code) login, then fetch the user
+  profile, liked tracks, all playlists and their tracks, long-term top tracks
+  and top artists, and playlist/profile cover art. Resilient paginated fetching
+  (follows `next`, retries dropped connections, honours `429` rate limits) with
+  progress bars.
+- **Local backend** — index a folder of audio files via `mutagen` tags.
+- **iTunes backend** — parse an iTunes Library XML export.
+- **Matching** — map local tracks to Spotify tracks (fuzzy matcher; ISRC/MBID
+  matching planned).
+- **Stats & lyrics** — generate listening stats and fetch lyrics.
+- **GUI** — browse libraries as artist → album → track tables.
+
+## Setup
+
+Requires Python 3.13+.
+
+```bash
+python -m venv .venv
+source .venv/bin/activate
+pip install -r requirements.txt
+```
+
+### Credentials
+
+Create an app at https://developer.spotify.com/dashboard and add
+`http://127.0.0.1:8888` as a **Redirect URI**. Credentials are read from the
+environment — never commit them.
+
+```bash
+cp .env.example .env
+# edit .env with your client id/secret
+source .env
+```
+
+`Env.py` reads `SPOTIFY_CLIENT_ID` / `SPOTIFY_CLIENT_SECRET` (plus optional
+`MUSIC_LIBRARY_PATH` and `WORK_DIR`) from the environment.
+
+## Usage
+
+Edit `main.py` to uncomment the steps you want, then run:
+
+```bash
+python main.py
+```
+
+The flow steps (see `Flow.py`) include:
+
+| Step | What it does |
+|------|--------------|
+| `fetch_spotify()` | OAuth login + download all Spotify data into `work_dir/spotify/` |
+| `fetch_local()` | index local audio files into `work_dir/local/` |
+| `parse_spotify_library()` / `parse_itunes_library()` / `parse_local_library()` | build normalized libraries |
+| `load_libraries()` / `save_libraries()` | (de)serialize libraries to `work_dir` |
+| `map_local_to_spotify()` | match local tracks against the Spotify library |
+| `fetch_and_save_lyrics()` | fetch lyrics for tracks |
+| `log_stats()` | generate stats |
+
+On first `fetch_spotify()` a browser opens for the Spotify login; a local server
+on `127.0.0.1:8888` catches the redirect and exchanges the code for a token.
+
+### GUI
+
+```bash
+./gui.sh        # runs: .venv/bin/streamlit run Gui.py
+```
+
+## Layout
+
+```
+main.py                 entry point (CLI flow)
+Gui.py / gui.sh         Streamlit GUI
+Flow.py                 orchestrates fetch / parse / map / stats
+Env.py                  config (reads credentials from the environment)
+src/
+  Library.py            data model (Library / Artist / Album / Track)
+  LibrarySerializer.py  load/save libraries
+  backends/
+    spotify/            Web API client, OAuth, parser
+    local/              local-file indexer, parser, playlist generator
+    itunes/             iTunes XML parser
+    navidrome/          Navidrome backend
+  mappers/              local↔Spotify matching (fuzzy / search)
+  lyrics/               lyrics fetching
+work_dir/               fetched data and serialized libraries (gitignored)
+```
+
+## Notes
+
+- Data is cached as JSON under `work_dir/` (gitignored); re-running reuses it.
+- The deprecated Spotify endpoints (audio-features, recommendations, etc.) are
+  not used — only currently-supported endpoints.

gui.sh

@@ -1 +1,5 @@
-streamlit run Gui.py
+#!/usr/bin/env bash
+# Run from the script's directory using the project virtualenv,
+# so it works regardless of whether the venv is activated / on PATH.
+cd "$(dirname "$0")"
+exec .venv/bin/streamlit run Gui.py "$@"

main.py

@@ -17,17 +17,17 @@ def test1():
 def main():
     flow = Flow.Flow()
 
-    # flow.fetch_spotify()
+    flow.fetch_spotify()
     # flow.fetch_local()
 
     flow.parse_spotify_library()
-    flow.parse_itunes_library()
+    #flow.parse_itunes_library()
-    flow.parse_local_library()
+    #flow.parse_local_library()
 
-    flow.load_libraries()
+    #flow.load_libraries()
 
-    flow.map_local_to_spotify()
+    #flow.map_local_to_spotify()
-    flow.save_libraries()
+    #flow.save_libraries()
 
     # flow.log_stats()
 

requirements.txt

@@ -0,0 +1,9 @@
+streamlit==1.58.0
+streamlit-aggrid==1.2.1.post2
+pandas==3.0.3
+Pillow==12.2.0
+mutagen==1.47.0
+rapidfuzz==3.14.5
+requests==2.34.2
+tqdm==4.68.2
+xmltodict==1.0.4

src/backends/spotify/SpotifyWebAPI.py

@@ -1,7 +1,10 @@
 import requests
 import urllib.parse
+from requests.adapters import HTTPAdapter
+from urllib3.util.retry import Retry
 from PIL import Image
 from io import BytesIO
+from tqdm import tqdm
 
 from src.backends.spotify.SpotifyAuthenticator import authenticate
 
@@ -9,6 +12,31 @@ from src.helpers import *
 
 FETCH_STEP = 50
 token = ''
+REQUEST_TIMEOUT = 30
+
+
+def _build_session():
+    """Session that retries transient failures (dropped connections, 5xx) and
+    honours Spotify's 429 Retry-After, so a single reset mid-fetch doesn't
+    abort the whole run."""
+    session = requests.Session()
+    retry = Retry(
+        total=6,
+        connect=6,
+        read=6,
+        backoff_factor=1.5,  # sleeps ~0, 1.5, 3, 6, 12, 24s between attempts
+        status_forcelist=(429, 500, 502, 503, 504),
+        allowed_methods=frozenset({"GET", "POST"}),
+        respect_retry_after_header=True,
+        raise_on_status=False,
+    )
+    adapter = HTTPAdapter(max_retries=retry)
+    session.mount("https://", adapter)
+    session.mount("http://", adapter)
+    return session
+
+
+_session = _build_session()
 
 
 def fetch(endpoint, method='GET', body=None):
@@ -17,23 +45,27 @@ def fetch(endpoint, method='GET', body=None):
         'Authorization': f'Bearer {token}',
     }
 
-    response = requests.request(method, url, headers=headers, json=body)
+    response = _session.request(method, url, headers=headers, json=body, timeout=REQUEST_TIMEOUT)
     response.raise_for_status()
     return response.json()
 
 
-def fetch_paginated(endpoint):
+def fetch_paginated(endpoint, desc="Fetching", leave=True):
     """Collect every item of a paging object by following its `next` field,
     which is Spotify's recommended way to page (more robust than tracking
-    offset/total manually)."""
+    offset/total manually). Shows a tqdm progress bar driven by the paging
+    object's `total`."""
     items = []
     page = fetch(endpoint)
-    while True:
+    with tqdm(total=page.get('total'), desc=desc, unit="item", leave=leave) as pbar:
-        items += page.get('items', [])
+        while True:
-        next_url = page.get('next')
+            batch = page.get('items', [])
-        if not next_url:
+            items += batch
-            break
+            pbar.update(len(batch))
-        page = fetch(next_url)
+            next_url = page.get('next')
+            if not next_url:
+                break
+            page = fetch(next_url)
     return items
 
 
@@ -43,31 +75,31 @@ def find_song(song_pattern):
 
 
 def fetch_playlists(user_id):
-    print("Fetching playlists")
+    return fetch_paginated(f"v1/me/playlists?limit={FETCH_STEP}", desc="Fetching playlists")
-    return fetch_paginated(f"v1/me/playlists?limit={FETCH_STEP}")
 
 
 def fetch_playlist_items(playlist_id):
-    return fetch_paginated(f"v1/playlists/{playlist_id}/tracks?limit={FETCH_STEP}")
+    return fetch_paginated(
+        f"v1/playlists/{playlist_id}/tracks?limit={FETCH_STEP}",
+        desc="Fetching playlist tracks",
+        leave=False,
+    )
 
 
 def fetch_tracks(user_id):
-    print("Fetching tracks")
+    tracks = fetch_paginated(f"v1/me/tracks?limit={FETCH_STEP}&market=ES", desc="Fetching liked tracks")
-    tracks = fetch_paginated(f"v1/me/tracks?limit={FETCH_STEP}&market=ES")
     save_data(tracks, "tracks")
     return tracks
 
 
 def fetch_tracks_top():
-    print("Fetching top tracks")
+    tracks = fetch_paginated(f"v1/me/top/tracks?limit={FETCH_STEP}&time_range=long_term", desc="Fetching top tracks")
-    tracks = fetch_paginated(f"v1/me/top/tracks?limit={FETCH_STEP}&time_range=long_term")
     save_data(tracks, "top_tracks")
     return tracks
 
 
 def fetch_artists_top():
-    print("Fetching top artists")
+    artists = fetch_paginated(f"v1/me/top/artists?limit={FETCH_STEP}&time_range=long_term", desc="Fetching top artists")
-    artists = fetch_paginated(f"v1/me/top/artists?limit={FETCH_STEP}&time_range=long_term")
     save_data(artists, "top_artists")
     return artists