Skip to content

musixmatch

MusixMatch lyrics provider.

MusixMatch() ¤

Bases: LyricsProvider

MusixMatch lyrics provider class.

Source code in spotdl/providers/lyrics/base.py 
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
def __init__(self):
    """
    Init the lyrics provider searchand set headers.
    """

    self.headers = {
        "Connection": "keep-alive",
        "Pragma": "no-cache",
        "Cache-Control": "no-cache",
        "sec-ch-ua": '"Chromium";v="104", " Not A;Brand";v="99", "Google Chrome";v="104"',
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 "
        "(KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36",
        "Accept": "*/*",
        "Sec-Fetch-Site": "same-origin",
        "Sec-Fetch-Mode": "cors",
        "Sec-Fetch-Dest": "empty",
        "Accept-Language": "en-US;q=0.8,en;q=0.7",
    }

extract_lyrics(url, **_) ¤

Extracts the lyrics from the given url.

Arguments¤
  • url: The url to extract the lyrics from.
  • kwargs: Additional arguments.
Returns¤
  • The lyrics of the song or None if no lyrics were found.
Source code in spotdl/providers/lyrics/musixmatch.py 
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
def extract_lyrics(self, url: str, **_) -> Optional[str]:
    """
    Extracts the lyrics from the given url.

    ### Arguments
    - url: The url to extract the lyrics from.
    - kwargs: Additional arguments.

    ### Returns
    - The lyrics of the song or None if no lyrics were found.
    """

    lyrics_resp = requests.get(
        url,
        headers=self.headers,
        timeout=10,
        proxies=GlobalConfig.get_parameter("proxies"),
    )

    lyrics_soup = BeautifulSoup(lyrics_resp.text, "html.parser")
    lyrics_paragraphs = lyrics_soup.select("p.mxm-lyrics__content")
    lyrics = "\n".join(i.get_text() for i in lyrics_paragraphs)

    return lyrics

get_results(name, artists, **kwargs) ¤

Returns the results for the given song.

Arguments¤
  • name: The name of the song.
  • artists: The artists of the song.
  • kwargs: Additional arguments.
Returns¤
  • A dictionary with the results. (The key is the title and the value is the url.)
Source code in spotdl/providers/lyrics/musixmatch.py 
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
def get_results(self, name: str, artists: List[str], **kwargs) -> Dict[str, str]:
    """
    Returns the results for the given song.

    ### Arguments
    - name: The name of the song.
    - artists: The artists of the song.
    - kwargs: Additional arguments.

    ### Returns
    - A dictionary with the results. (The key is the title and the value is the url.)
    """

    track_search = kwargs.get("track_search", False)
    artists_str = ", ".join(
        artist for artist in artists if artist.lower() not in name.lower()
    )

    # quote the query so that it's safe to use in a url
    # e.g "Au/Ra" -> "Au%2FRa"
    query = quote(f"{name} - {artists_str}", safe="")

    # search the `tracks page` if track_search is True
    if track_search:
        query += "/tracks"

    search_url = f"https://www.musixmatch.com/search/{query}"
    search_resp = requests.get(
        search_url,
        headers=self.headers,
        timeout=10,
        proxies=GlobalConfig.get_parameter("proxies"),
    )
    search_soup = BeautifulSoup(search_resp.text, "html.parser")
    song_url_tag = search_soup.select("a[href^='/lyrics/']")

    if not song_url_tag:
        # song_url_tag being None means no results were found on the
        # All Results page, therefore, we use `track_search` to
        # search the tracks page.

        # track_serach being True means we are already searching the tracks page.
        if track_search:
            return {}

        return self.get_results(name, artists, track_search=True)

    results: Dict[str, str] = {}
    for tag in song_url_tag:
        results[tag.get_text()] = "https://www.musixmatch.com" + str(
            tag.get("href", "")
        )

    return results