0.12

Visual album art and --quiet mode

Author: lukafilipxvic

.gitignore

@@ -1,4 +1,5 @@
 # Byte-compiled / optimized / DLL files
+.env
 __pycache__/
 *.py[cod]
 *$py.class

README.md

@@ -15,6 +15,10 @@
 
 Pyzam is a free CLI music recognition tool for audio and mixtapes in Python.
 
+<p align="center">
+  <img src="https://github.com/lukafilipxvic/pyzam/blob/main/images/pyzam-usage.gif" alt="Pyzam usage", width"459">
+</p>
+
 ## Installation
 
 ### Dependencies
@@ -51,7 +55,7 @@ pyzam --url "https://archive.org/download/09-hold-me-in-your-arms/02%20-%20Never
 
 ```bash
 # Loop the recognition continously and save the logs as CSV file
-pyzam --speaker -d 10 --loop
+pyzam --speaker -d 10 --write --loop
 
 # Listen to mixtapes and save the logs as CSV file
 pyzam --input audio_file.mp3 --duration 12 --mixtape
@@ -66,8 +70,9 @@ See `pyzam --help` for more options.
 | --microphone, -m  | Listens to the microphone of your device.
 | --speaker, -s     | Listens to the speaker of your device (default).
 | --url, -u         | Detects from the given URL to an audio file.
-| --help, -h        | Show usage & options and exit.
+| --help, -h        | Show usage, options and exit.
 | --duration, -d    | Length of microphone or speaker recording. Max = 12 seconds.
+| --quiet, -q       | Supresses the operation messages (i.e. Recording speaker for X seconds...). 
 | --loop, -l        | Loop the recognition process indefinitely.
 | --mixtape         | Detects every -d seconds for a given input file, only works with --input. --write is enabled automatically.
 | --json, -j        | Return the whole Shazamio output in JSON.

images/pyzam-usage.gif

@@ -1 +1 @@
-__version__ = "0.11"
+__version__ = "0.12"

pyzam/__init__.py

@@ -1,7 +1,7 @@
 #! /usr/bin/env python3
 
 """
-Pyzam 0.11
+Pyzam 0.12
 A CLI music recognition tool for audio and mixtapes.
 """
 
@@ -47,6 +47,9 @@ def _parser() -> argparse.ArgumentParser:
     parser.add_argument(
         "-d", "--duration", type=int, default=5, help="audio recording duration (s)"
     )
+    parser.add_argument(
+        "-q", "--quiet", action="store_true", help="suppress operation messages"
+    )
     run_group.add_argument(
         "--loop", "-l", action="store_true", help="loop music recognition process"
     )
@@ -75,15 +78,15 @@ def check_ffmpeg():
 def get_input_file(args, temp_dir) -> Path:
     if args.microphone:
         return record.microphone(
-            filename=f"{temp_dir}/pyzam_mic.wav", seconds=args.duration
+            filename=f"{temp_dir}/pyzam_mic.wav", seconds=args.duration, quiet=args.quiet
         )
     elif args.speaker:
         return record.speaker(
-            filename=f"{temp_dir}/pyzam_speaker.wav", seconds=args.duration
+            filename=f"{temp_dir}/pyzam_speaker.wav", seconds=args.duration, quiet=args.quiet
         )
     elif args.url:
-        return record.url(url=args.url,
-            filename=f"{temp_dir}/pyzam_url.wav"
+        return record.url(
+            url=args.url, filename=f"{temp_dir}/pyzam_url.wav", quiet=args.quiet
         )
     else:
         return args.input

pyzam/__main__.py

@@ -1,8 +1,10 @@
 import asyncio
+import climage
 import csv
 from datetime import datetime
-import random
+import requests
 from rich.progress import MofNCompleteColumn, Progress, TimeElapsedColumn
+import pkg_resources
 from shazamio import Shazam
 import soundfile as sf
 import tempfile
@@ -18,10 +20,8 @@ def write_csv(file_name: str, data_rows: list):
     :param data_rows: Includes timestamp, track_title, artist and album_cover.
     """
     header = ["Timestamp", "Track", "Artist", "Album Cover"]
-    csv_file = f"{file_name}.csv"
-    file_exists = os.path.isfile(csv_file)
-
-    with open(csv_file, mode="a", newline="", encoding="utf-8") as file:
+    file_exists = os.path.isfile(f"{file_name}.csv")
+    with open(f"{file_name}.csv", mode="a", newline="", encoding="utf-8") as file:
         writer = csv.writer(file)
         if not file_exists:
             writer.writerow(header)
@@ -36,17 +36,49 @@ def extract_track_info(out):
             out["track"]
             .get("images", {})
             .get("coverart", "")
-            .replace("/400x400cc.jpg", "/1400x1400cc.png")
+            #.replace("/400x400cc.jpg", "/1400x1400cc.png")
         )
     else:
         album_cover_hq = None
     return track_title, artist, album_cover_hq
 
 
 def print_track_info(track_info):
-    print(f"Track: {track_info[0]}")
-    print(f"Artist: {track_info[1]}")
-    print(f"Album Cover: {track_info[2]}")
+    track_name = f"Track: {track_info[0]}"
+    artist_name = f"Artist: {track_info[1]}"
+    
+    default_cover_data = pkg_resources.resource_string(__name__, 'data/default_album_cover.png')
+    with tempfile.NamedTemporaryFile(delete=False, suffix='.png') as temp_file:
+        temp_file.write(default_cover_data)
+        default_cover_path = temp_file.name
+
+    album_cover = climage.convert(default_cover_path, is_unicode=True, width=40)
+
+    if track_info[2]:
+        try:
+            response = requests.get(track_info[2], timeout=5)
+            response.raise_for_status()
+            with tempfile.NamedTemporaryFile(delete=False, suffix='.jpg') as temp_file:
+                temp_file.write(response.content)
+                temp_file_path = temp_file.name
+            album_cover = climage.convert(temp_file_path, is_unicode=True, width=40)
+        except (requests.RequestException, IOError) as e:
+            print(f"Error downloading album cover: {e}")  # Provide feedback on error
+    
+    cover_lines = album_cover.splitlines()
+    max_height = max(len(cover_lines), 2)
+    
+    os.system('cls' if os.name == 'nt' else 'clear')
+    print() # Space on top
+    for i in range(max_height):
+        cover_line = cover_lines[i] if i < len(cover_lines) else ' ' * 25  # Padding for cover lines
+        
+        if i == max_height - 2:
+            print(f"{cover_line}  {track_name}")
+        elif i == max_height - 1:
+            print(f"{cover_line}  {artist_name}")
+        else:
+            print(cover_line)
 
 
 async def identify_audio(
@@ -72,6 +104,7 @@ async def identify_audio(
     out = await shazam.recognize(data=audio_file, proxy=None)
 
     if "track" not in out:
+        os.system('cls' if os.name == 'nt' else 'clear')
         print("No matches found.")
         return
 
@@ -112,14 +145,12 @@ def split_and_identify(audio_file: str, duration: int):
         task = progress.add_task(
             f"[green]Splitting and identifying audio...", total=num_segments
         )
-        # Make each segment an audio file to be used in Shazamio.
         for i in range(num_segments):
             start_idx = i * samples_per_duration
             segment_data = data[start_idx : start_idx + samples_per_duration]
             timestamp = datetime.utcfromtimestamp(start_idx / samplerate).strftime(
                 "%H:%M:%S"
             )
-            # Temporarily saves audio file, shazams, then deletes.
             with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as temp_file:
                 sf.write(temp_file.name, segment_data, samplerate)
                 asyncio.run(

pyzam/data/default_album_cover.png

@@ -3,49 +3,54 @@
 import soundfile as sf
 import io
 
-
-def speaker(filename: str, seconds):
+def speaker(filename: str, seconds, quiet=False):
     """
     Records the device's speaker.
 
     :param filename: Name and directory of the audio file written.
     :param seconds: Duration to record (seconds).
+    :param quiet: If True, suppresses print statements.
     """
-    with sc.get_microphone(
-        id=str(sc.default_speaker().name), include_loopback=True
-    ).recorder(samplerate=44100) as speaker:
-        print(f"Recording speaker for {seconds} seconds...")
+    speaker = sc.get_microphone(id=str(sc.default_speaker().name), include_loopback=True)
+    with speaker.recorder(samplerate=44100) as speaker_recorder:
+        if not quiet:
+            print()
+            print(f"Recording {speaker.name} for {seconds} seconds...")
 
-        data = speaker.record(numframes=44100 * seconds)
+        data = speaker_recorder.record(numframes=44100 * seconds)
         sf.write(file=filename, data=data, samplerate=44100)
     return filename
 
 
-def microphone(filename: str, seconds):
+def microphone(filename: str, seconds, quiet=False):
     """
-    Records the device's device.
+    Records the device's microphone.
 
     :param filename: Name and directory of the audio file written.
     :param seconds: Duration to record (seconds).
+    :param quiet: If True, suppresses recording statements.
     """
-    with sc.get_microphone(
-        id=str(sc.default_microphone().name), include_loopback=True
-    ).recorder(samplerate=44100) as mic:
-        print(f"Recording microphone for {seconds} seconds...")
-        data = mic.record(numframes=44100 * seconds)
+    mic = sc.default_microphone()
+    with mic.recorder(samplerate=44100) as mic_recorder:
+        if not quiet:
+            print()
+            print(f"Recording {mic.name} for {seconds} seconds...")
+
+        data = mic_recorder.record(numframes=44100 * seconds)
         sf.write(file=filename, data=data, samplerate=44100)
     return filename
 
 
-def url(url: str, filename: str):
+def url(url: str, filename: str, quiet=False):
     """
     Downloads audio from the provided URL.
 
     :param url: URL of the audio file.
     :param filename: Name and directory of the audio file written.
-    :param seconds: Duration to record (seconds).
+    :param quiet: If True, suppresses print statements.
     """
-    print(f"Downloading audio from URL...")
+    if not quiet:
+        print(f"Downloading audio from URL...")
     headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36 Edge/12.246'}
 
     try:

pyzam/identify.py

@@ -1,5 +1,7 @@
 asyncio==3.4.3
+climage==0.2.2
 fastapi==0.111.0
+pillow==10.4.0
 requests==2.32.3
 rich==13.8
 soundfile==0.12.1

pyzam/record.py

@@ -5,7 +5,7 @@
 
 setuptools.setup(
     name="pyzam",
-    version="0.11",
+    version="0.12",
     entry_points={"console_scripts": ["pyzam = pyzam.__main__:main"]},
     author="lukafilipxvic",
     description="A CLI music recognition tool for audio and mixtapes.",
@@ -20,6 +20,7 @@
         "SoundCard",
     ],
     packages=setuptools.find_packages(),
+    package_data={"pyzam": ["data/default_album_cover.png"]},
     python_requires=">=3.9",
     license="MIT",
     classifiers=[