Merge pull request #26 from deedy5/dev

Migrate from requests to curl_cffi + enable Deezer

README.md

@@ -40,8 +40,8 @@ syncedlyrics.search("...", lang="de")
 - [Lrclib](https://github.com/tranxuanthang/lrcget/issues/2#issuecomment-1326925928)
 - [NetEase](https://music.163.com/)
 - [Megalobiz](https://www.megalobiz.com/)
+- [Deezer](https://deezer.com/)
 - ~~[Lyricsify](https://www.lyricsify.com/)~~ (Broken duo to Cloudflare protection)
-- ~~[Deezer](https://deezer.com/)~~ (Broken)
 
 Feel free to suggest more providers or make PRs to fix the broken ones.
 

pyproject.toml

@@ -15,16 +15,16 @@ classifiers = [
 
 [tool.poetry.dependencies]
 python = ">=3.8"
-requests = "^2.31.0"
-rapidfuzz = "^3.5.2"
-beautifulsoup4 = "^4.12.2"
+curl_cffi = "^0.6.2"
+rapidfuzz = "^3.6.2"
+beautifulsoup4 = "^4.12.3"
 
 [tool.poetry.scripts]
 syncedlyrics = "syncedlyrics.cli:cli_handler"
 
 [tool.poetry.group.dev.dependencies]
-black = "^23.11.0"
-pytest = "^7.4.3"
+black = "^24.2.0"
+pytest = "^8.0.2"
 
 [build-system]
 requires = ["poetry-core"]

syncedlyrics/__init__.py

@@ -7,9 +7,10 @@
 ```
 """
 
-from typing import Optional, List
 import logging
-from .providers import NetEase, Megalobiz, Musixmatch, Lrclib
+from typing import List, Optional
+
+from .providers import Deezer, Lrclib, Megalobiz, Musixmatch, NetEase
 from .utils import is_lrc_valid, save_lrc_file
 
 logger = logging.getLogger(__name__)
@@ -18,9 +19,9 @@
 def search(
     search_term: str,
     allow_plain_format: bool = False,
-    save_path: str = None,
-    providers: List[str] = None,
-    lang: str = None,
+    save_path: Optional[str] = None,
+    providers: Optional[List[str]] = None,
+    lang: Optional[str] = None,
 ) -> Optional[str]:
     """
     Returns the synced lyrics of the song in [LRC](https://en.wikipedia.org/wiki/LRC_(file_format)) format if found.
@@ -31,7 +32,7 @@ def search(
     - `providers`: A list of provider names to include in searching; loops over all the providers as soon as an LRC is found
     - `lang`: Language of the translation along with the lyrics. **Only supported by Musixmatch**
     """
-    _providers = [Musixmatch(lang=lang), Lrclib(), NetEase(), Megalobiz()]
+    _providers = [Musixmatch(lang=lang), Lrclib(), NetEase(), Megalobiz(), Deezer()]
     if providers and any(providers):
         # Filtering the providers
         _providers = [
@@ -43,7 +44,7 @@ def search(
         logger.error(
             f"Providers {providers} not found in the list of available providers."
         )
-        return
+        return None
     lrc = None
     for provider in _providers:
         logger.debug(f"Looking for an LRC on {provider.__class__.__name__}")
@@ -55,7 +56,7 @@ def search(
             break
     if not lrc:
         logger.info(f'No synced-lyrics found for "{search_term}" :(')
-        return
+        return None
     if save_path:
         save_path = save_path.format(search_term=search_term)
         save_lrc_file(save_path, lrc)

syncedlyrics/cli.py

@@ -16,8 +16,12 @@ def cli_handler():
         "-p",
         help="Comma-separated list of providers to include in searching",
         default="",
+        choices=["deezer", "lrclib", "megalobiz", "musixmatch", "netease"],
+        nargs="+",
+    )
+    parser.add_argument(
+        "-l", "--lang", help="Language of the translation along with the lyrics"
     )
-    parser.add_argument("-l", "--lang", help="Language of the translation along with the lyrics")
     parser.add_argument(
         "-o", "--output", help="Path to save '.lrc' lyrics", default="{search_term}.lrc"
     )
@@ -31,7 +35,6 @@ def cli_handler():
     )
     args = parser.parse_args()
     logging.basicConfig(level=logging.DEBUG if args.verbose else logging.INFO)
-    p = args.p.split(",") if args.p else None
-    lrc = search(args.search_term, args.allow_plain, args.output, p, lang=args.lang)
+    lrc = search(args.search_term, args.allow_plain, args.output, args.p, lang=args.lang)
     if lrc:
         print(lrc)

syncedlyrics/providers/base.py

@@ -1,4 +1,4 @@
-import requests
+from curl_cffi import requests
 from typing import Optional
 
 
@@ -7,14 +7,8 @@ class LRCProvider:
     Base class for all of the synced (LRC format) lyrics providers.
     """
 
-    session = requests.Session()
-
     def __init__(self) -> None:
-        self.session.headers.update(
-            {
-                "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36"
-            }
-        )
+        self.session = requests.Session(impersonate="chrome")
 
     def get_lrc_by_id(self, track_id: str) -> Optional[str]:
         """

syncedlyrics/providers/deezer.py

@@ -44,9 +44,10 @@ def get_lrc_by_id(self, track_id: str) -> Optional[str]:
         return lrc or None
 
     def get_lrc(self, search_term: str) -> Optional[str]:
-        search_results = self.session.get(self.SEARCH_ENDPOINT + search_term).json()
+        url = self.SEARCH_ENDPOINT + search_term.replace(" ", "+")
+        search_results = self.session.get(url).json()
         cmp_key = lambda t: f"{t.get('title')} {t.get('artist').get('name')}"
         track = get_best_match(search_results.get("data", []), search_term, cmp_key)
         if not track:
-            return
+            return None
         return self.get_lrc_by_id(track["id"])

syncedlyrics/providers/lrclib.py

@@ -20,18 +20,18 @@ def get_lrc_by_id(self, track_id: str) -> Optional[str]:
         url = self.LRC_ENDPOINT + track_id
         r = self.session.get(url)
         if not r.ok:
-            return
+            return None
         track = r.json()
         return track.get("syncedLyrics", track.get("plainLyrics"))
 
     def get_lrc(self, search_term: str) -> Optional[str]:
         url = self.SEARCH_ENDPOINT
         r = self.session.get(url, params={"q": search_term})
         if not r.ok:
-            return
+            return None
         tracks = r.json()
         if not tracks:
-            return
+            return None
         tracks = sort_results(
             tracks, search_term, lambda t: f'{t["artistName"]} - {t["trackName"]}'
         )
@@ -43,5 +43,5 @@ def get_lrc(self, search_term: str) -> Optional[str]:
                 _id = str(track["id"])
                 break
         if not _id:
-            return
+            return None
         return self.get_lrc_by_id(_id)

syncedlyrics/providers/megalobiz.py

@@ -13,7 +13,7 @@ class Megalobiz(LRCProvider):
     SEARCH_ENDPOINT = ROOT_URL + "/search/all?qry={q}&searchButton.x=0&searchButton.y=0"
 
     def get_lrc(self, search_term: str) -> Optional[str]:
-        url = self.SEARCH_ENDPOINT.format(q=search_term)
+        url = self.SEARCH_ENDPOINT.format(q=search_term.replace(" ", "+"))
 
         def href_match(h: Optional[str]):
             if h and h.startswith("/lrc/maker/"):

syncedlyrics/providers/musixmatch.py

@@ -16,16 +16,10 @@ class Musixmatch(LRCProvider):
 
     ROOT_URL = "https://apic-desktop.musixmatch.com/ws/1.1/"
 
-    def __init__(self, lang : str = None) -> None:
+    def __init__(self, lang : Optional[str] = None) -> None:
         super().__init__()
         self.lang = lang
         self.token = None
-        self.session.headers.update(
-            {
-                "authority": "apic-desktop.musixmatch.com",
-                "cookie": "AWSELBCORS=0; AWSELB=0",
-            }
-        )
 
     def _get(self, action: str, query: List[tuple]):
         if action != "token.get" and self.token is None:
@@ -82,10 +76,10 @@ def get_lrc_by_id(self, track_id: str) -> Optional[str]:
             )
             body_tr = r_tr.json()["message"]["body"]
         if not r.ok:
-            return
+            return None
         body = r.json()["message"]["body"]
         if not body:
-            return
+            return None
         lrc = body["subtitle"]["subtitle_body"]
         if self.lang is not None and body_tr:
             for i in body_tr["translations_list"]:
@@ -109,5 +103,5 @@ def get_lrc(self, search_term: str) -> Optional[str]:
         cmp_key = lambda t: f"{t['track']['track_name']} {t['track']['artist_name']}"
         track = get_best_match(tracks, search_term, cmp_key)
         if not track:
-            return
+            return None
         return self.get_lrc_by_id(track["track"]["track_id"])

syncedlyrics/providers/netease.py

@@ -4,21 +4,6 @@
 from .base import LRCProvider
 from ..utils import get_best_match
 
-headers = {
-    "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
-    "accept-language": "en-US,en;q=0.9,fa;q=0.8",
-    "cache-control": "max-age=0",
-    "sec-ch-ua": '".Not/A)Brand";v="99", "Google Chrome";v="103", "Chromium";v="103"',
-    "sec-ch-ua-mobile": "?0",
-    "sec-ch-ua-platform": '"Windows"',
-    "sec-fetch-dest": "document",
-    "sec-fetch-mode": "navigate",
-    "sec-fetch-site": "none",
-    "sec-fetch-user": "?1",
-    "upgrade-insecure-requests": "1",
-    "cookie": "NMTID=00OAVK3xqDG726ITU6jopU6jF2yMk0AAAGCO8l1BA; JSESSIONID-WYYY=8KQo11YK2GZP45RMlz8Kn80vHZ9%2FGvwzRKQXXy0iQoFKycWdBlQjbfT0MJrFa6hwRfmpfBYKeHliUPH287JC3hNW99WQjrh9b9RmKT%2Fg1Exc2VwHZcsqi7ITxQgfEiee50po28x5xTTZXKoP%2FRMctN2jpDeg57kdZrXz%2FD%2FWghb%5C4DuZ%3A1659124633932; _iuqxldmzr_=32; _ntes_nnid=0db6667097883aa9596ecfe7f188c3ec,1659122833973; _ntes_nuid=0db6667097883aa9596ecfe7f188c3ec; WNMCID=xygast.1659122837568.01.0; WEVNSM=1.0.0; WM_NI=CwbjWAFbcIzPX3dsLP%2F52VB%2Bxr572gmqAYwvN9KU5X5f1nRzBYl0SNf%2BV9FTmmYZy%2FoJLADaZS0Q8TrKfNSBNOt0HLB8rRJh9DsvMOT7%2BCGCQLbvlWAcJBJeXb1P8yZ3RHA%3D; WM_NIKE=9ca17ae2e6ffcda170e2e6ee90c65b85ae87b9aa5483ef8ab3d14a939e9a83c459959caeadce47e991fbaee82af0fea7c3b92a81a9ae8bd64b86beadaaf95c9cedac94cf5cedebfeb7c121bcaefbd8b16dafaf8fbaf67e8ee785b6b854f7baff8fd1728287a4d1d246a6f59adac560afb397bbfc25ad9684a2c76b9a8d00b2bb60b295aaafd24a8e91bcd1cb4882e8beb3c964fb9cbd97d04598e9e5a4c6499394ae97ef5d83bd86a3c96f9cbeffb1bb739aed9ea9c437e2a3; WM_TID=AAkRFnl03RdABEBEQFOBWHCPOeMra4IL; playerid=94262567",
-}
-
 
 class NetEase(LRCProvider):
     """NetEase provider class"""
@@ -28,15 +13,17 @@ class NetEase(LRCProvider):
 
     def __init__(self) -> None:
         super().__init__()
-        self.session.headers.update(headers)
+        self.session.headers["cookie"] = (
+            "NMTID=00OAVK3xqDG726ITU6jopU6jF2yMk0AAAGCO8l1BA; JSESSIONID-WYYY=8KQo11YK2GZP45RMlz8Kn80vHZ9%2FGvwzRKQXXy0iQoFKycWdBlQjbfT0MJrFa6hwRfmpfBYKeHliUPH287JC3hNW99WQjrh9b9RmKT%2Fg1Exc2VwHZcsqi7ITxQgfEiee50po28x5xTTZXKoP%2FRMctN2jpDeg57kdZrXz%2FD%2FWghb%5C4DuZ%3A1659124633932; _iuqxldmzr_=32; _ntes_nnid=0db6667097883aa9596ecfe7f188c3ec,1659122833973; _ntes_nuid=0db6667097883aa9596ecfe7f188c3ec; WNMCID=xygast.1659122837568.01.0; WEVNSM=1.0.0; WM_NI=CwbjWAFbcIzPX3dsLP%2F52VB%2Bxr572gmqAYwvN9KU5X5f1nRzBYl0SNf%2BV9FTmmYZy%2FoJLADaZS0Q8TrKfNSBNOt0HLB8rRJh9DsvMOT7%2BCGCQLbvlWAcJBJeXb1P8yZ3RHA%3D; WM_NIKE=9ca17ae2e6ffcda170e2e6ee90c65b85ae87b9aa5483ef8ab3d14a939e9a83c459959caeadce47e991fbaee82af0fea7c3b92a81a9ae8bd64b86beadaaf95c9cedac94cf5cedebfeb7c121bcaefbd8b16dafaf8fbaf67e8ee785b6b854f7baff8fd1728287a4d1d246a6f59adac560afb397bbfc25ad9684a2c76b9a8d00b2bb60b295aaafd24a8e91bcd1cb4882e8beb3c964fb9cbd97d04598e9e5a4c6499394ae97ef5d83bd86a3c96f9cbeffb1bb739aed9ea9c437e2a3; WM_TID=AAkRFnl03RdABEBEQFOBWHCPOeMra4IL; playerid=94262567"
+        )
 
     def search_track(self, search_term: str) -> Optional[dict]:
         """Returns a `dict` containing some metadata for the found track."""
         params = {"limit": 10, "type": 1, "offset": 0, "s": search_term}
         response = self.session.get(self.API_ENDPOINT_METADATA, params=params)
         results = response.json().get("result", {}).get("songs")
         if not results:
-            return
+            return None
         cmp_key = lambda t: f"{t.get('name')} {t.get('artists')[0].get('name')}"
         track = get_best_match(results, search_term, cmp_key)
         # Update the session cookies from the new sent cookies for the next request.
@@ -49,11 +36,11 @@ def get_lrc_by_id(self, track_id: str) -> Optional[str]:
         response = self.session.get(self.API_ENDPOINT_LYRICS, params=params)
         lrc = response.json().get("lrc", {}).get("lyric")
         if not lrc:
-            return
+            return None
         return lrc
 
     def get_lrc(self, search_term: str) -> Optional[str]:
         track = self.search_track(search_term)
         if not track:
-            return
+            return None
         return self.get_lrc_by_id(track["id"])

syncedlyrics/providers/spotify.py

@@ -11,7 +11,7 @@ def __init__(self) -> None:
         super().__init__()
 
     @classmethod
-    def get_track_id(search_term: str) -> Optional[str]:
+    def get_track_id(cls, search_term: str) -> Optional[str]:
         """Returns a Spotify track ID for given `search_term`"""
         # TODO: self.client.search(search_term) and processing the results
         raise NotImplementedError

syncedlyrics/utils.py

@@ -8,7 +8,7 @@
 R_FEAT = re.compile(r"\((feat.+)\)", re.IGNORECASE)
 
 
-def is_lrc_valid(lrc: str, allow_plain_format: bool = False) -> bool:
+def is_lrc_valid(lrc: Optional[str], allow_plain_format: bool = False) -> bool:
     """Checks whether a given LRC string is valid or not."""
     if not lrc:
         return False
@@ -84,9 +84,11 @@ def get_best_match(
     with the `search_term`.
     """
     if not results:
-        return
+        return None
     results = sort_results(results, search_term, compare_key=compare_key)
     best_match = results[0]
-    if not str_same(compare_key(best_match), search_term, n=min_score):
-        return
+
+    value_to_compare = best_match[compare_key] if isinstance(compare_key, str) else compare_key(best_match)
+    if not str_same(value_to_compare, search_term, n=min_score):
+        return None
     return best_match

tests.py

@@ -10,7 +10,9 @@
 
 
 def _test_provider(provider: str, **kwargs):
-    lrc = syncedlyrics.search(q, allow_plain_format=True, providers=[provider], **kwargs)
+    lrc = syncedlyrics.search(
+        search_term=q, allow_plain_format=True, providers=[provider], **kwargs
+    )
     logging.debug(lrc)
     assert isinstance(lrc, str)
 
@@ -26,8 +28,14 @@ def test_megalobiz():
 def test_musixmatch():
     _test_provider("Musixmatch")
 
+
 def test_musixmatch_translation():
     _test_provider("Musixmatch", lang="es")
 
+
 def test_lrclib():
     _test_provider("Lrclib")
+
+
+def test_deezer():
+    _test_provider("Deezer")