improve lyrics functionality

NEWS

@@ -1,4 +1,6 @@
 ncmpc 0.50 - not yet released
+* lyrics/musixmatch: add new lyrics extension
+* lyrics/google: fix partial loading of lyrics
 
 ncmpc 0.49 - (2023-08-04)
 * fix UI freeze if lyrics plugin is stuck

lyrics/25-musixmatch.py

@@ -0,0 +1,50 @@
+#!/usr/bin/env python3
+import requests
+import bs4
+import sys
+import html
+
+def normalize(s):
+    for i in [' ', '\'']:
+        s = s.replace(i, '-')
+    for i in [',', '(', ')']:
+        s = s.replace(i, '')
+    return html.escape(s)
+
+def main():
+    artist = normalize(sys.argv[1])
+    title = normalize(sys.argv[2])
+
+    try:
+        musixmatch_url = "https://www.musixmatch.com/lyrics/"
+        r = requests.get(
+                musixmatch_url + artist + "/" + title,
+                headers = {
+                    "Host": "www.musixmatch.com",
+                    # emulate a linux user
+                    "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36",
+                    "Accept": "*/*"
+                    }
+                )
+
+        if r.status_code == 404:
+            print("Lyrics not found :(", file=sys.stderr)
+            exit(1)
+
+        soup = bs4.BeautifulSoup(r.text, features="lxml")
+        p_tags = soup.find_all("p", {"class": "mxm-lyrics__content"})
+        if len(p_tags) == 0:
+            # Sometimes musixmatch shows a "Restricted Lyrics" page with a 200 status code
+            print("Unable to get lyrics :(")
+            exit(1)
+
+        for p in p_tags:
+            print(p.text)
+            exit(1)
+
+    except Exception as e:
+        print("Unknown error: ", e, file=sys.stderr)
+        exit(2)
+
+if __name__ == '__main__':
+    main()

lyrics/60-google.py

@@ -38,14 +38,30 @@ def normalize_parameter(s):
     title = title.replace(" ", "+")
     r = requests.get(
         f"{base_url}/search?q={artist}+{title}+lyrics",
-        headers={"client": "google-csbe"},
+        headers={
+            "authority": "www.google.com",
+            # doesn't seem to work without this
+            "user-agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36",
+            "accept": "text/html,application/xhtml+xml"
+        }
     )
     try:
         r.raise_for_status()
     except:
         exit(1)
     soup = bs4.BeautifulSoup(r.text, "html5lib")
-    results = [x for x in soup.select("div") if len(x.select("div")) == 0]
-    # element with the longest text node is usually a match
-    results.sort(key=lambda n: len(n.text))
-    print(results[-1].text)
+    try:
+        lyrics_container = soup.select_one("div[data-lyricid]")
+        if not lyrics_container: raise IndexError
+        print(lyrics_container)
+        for tag in lyrics_container:
+            lyrics = tag.find_all("span")
+            for lyric in lyrics:
+                print(lyric.text)
+            break
+    except IndexError:
+        print("Lyrics not found :(")
+        exit(1)
+    except Exception as e:
+        print("Unknown error: ", e)
+        exit(2)

meson.build

@@ -342,6 +342,7 @@ if enable_lyrics_screen
   conf.set_quoted('LYRICS_PLUGIN_DIR', lyrics_plugin_dir)
   install_data(
     'lyrics/20-azlyrics.py',
+    'lyrics/25-musixmatch.py',
     'lyrics/30-karaoke_texty.py',
     'lyrics/40-tekstowo.py',
     'lyrics/50-genius.py',