Upgrade to 1.1

README.md

@@ -54,5 +54,10 @@ You can also install it system-wide using `sudo python3 -m pip install.`
 
 After installing, you can use it like this: `nicole -ior -d ~/music/artist --rm_explicit`
 
+## Changelog
+### 1.1
+- Lyrics are now properly encoded.
+- If a title contains paranthesis or umlaute, multiple possible urls will be checked.
+
 ## Importand Notice
 This software comes with no warranty!

nicole/nicole.py

@@ -50,8 +50,6 @@ class Nicole:
     def __del__(self):
         if self.write_history:
             self._write_history()
-        else:
-            print("NO")
 
     def _load_history(self):
         config_path = path.expanduser("~") + "/.config/nicole/"
@@ -81,9 +79,10 @@ class Nicole:
             failed_file.write(file + "\n")
         failed_file.close()
 
-    def get_url_azlyrics(self, artist:str, title:str):
+    def get_urls_azlyrics(self, artist:str, title:str):
         """
         Create a azlyrics html from the artist and title
+        If the title contains paranthesis or äüö, there will be multiple versions, one that contains the (...)öäü and one that doesn't.
         """
         # convert to lower case
         artist = artist.casefold()
@@ -99,26 +98,70 @@ class Nicole:
         for match in re.finditer(r"\[.*\]", title):
             title = title.replace(match.group(), "")
 
-        # remove spaces, from the title
+        titles = [title]
-        for c in [' ', '-', ',', '.', '\'', '"', '°', '`', '´', '/', '!', '?', '#', '*', '(', ')']:
-            title = title.replace(c, '')
-            artist = artist.replace(c, '')
 
-        # replace some stuff
+        # if title has(), create one version with and one without them
-        old = ['ä', 'ö', 'ü', '&']
+        if re.search(r"\(.*\)", title):
-        new = ['a', 'o', 'u', "and"]
+            for match in re.finditer(r"\(.*\)", title):
-        # new2 = ['', '', '', "and"]
+                title = title.replace(match.group(), "")
+            titles.append(title)
 
+        # some special chars
+        toNone = [' ', '-', ',', '.', '…', '\'', '"', '°', '`', '´', '/', '!', '?', '#', '*', '(', ')']
+        for c in toNone:
+            artist = artist.replace(c, "")
+
+        #
+        # replace umlaute, create multiple versions
+        #
+        old = ['ä', 'ö', 'ü', 'ß', '&']
+        new1 = ['a', 'o', 'u', 'ss', "and"]
+        new2 = ['', '', '', '', "and"]
+
+        # in artist
+        if any(c in old for c in artist):
             for i in range(len(old)):
-            title = title.replace(old[i], new[i])
+                artist = artist.replace(old[i], new1[i])
-            artist = artist.replace(old[i], new[i])
+        # multiple loops are needed since the array might grow
 
-        return "https://azlyrics.com/lyrics/" + artist + '/' + title + ".html"
+        # umlaute
+        for n in range(len(titles)):
+            if any(c in old for c in titles[n]):
+                # replace titles[n] with the first version and append the second
+                title2 = titles[n]
+                for i in range(len(old)):
+                    titles[n] = titles[n].replace(old[i], new1[i])
+                    title2 = title2.replace(old[i], new2[i])
+                titles.append(title2)
 
-    def get_lyrics_azlyrics(self, url):
+        # features
+        for title in titles:
+            match = re.search(r"fe?a?t\.?.*", title)
+            if match:
+                titles.append(title.replace(match.group(), ""))
+
+        # spaces, etc
+        for n in range(len(titles)):
+            for c in toNone:
+                titles[n] = titles[n].replace(c, '')
+
+        #
+        # create urls
+        #
+        urls = []
+        for title in titles:
+            urls.append("https://azlyrics.com/lyrics/" + artist + '/' + title + ".html")
+        print(urls)
+        return urls
+
+
+    def get_lyrics_azlyrics(self, urls):
         """
         Extract the lyrics from the html
         """
+
+        message = ""
+        for url in urls:
             # visit the url
             html = None
             try:
@@ -126,7 +169,8 @@ class Nicole:
                 sleep(self.delay) # azlyrics blocks requests if there is no delay
             except Exception:
                 sleep(self.delay) # azlyrics blocks requests if there is no delay
-            return (False, f"Could not access url: {url}")
+                message += f"Could not access url: {url}\n    "
+                continue
 
             lyrics = None
             match = re.search(r"<!\-\- Usage of azlyrics.com content by any third\-party lyrics provider is prohibited by our licensing agreement. Sorry about that. \-\->(.|\n)+?</div>", html)
@@ -147,7 +191,10 @@ class Nicole:
                     lyrics = lyrics.replace(tag.group(), "")
 
                 return (True, lyrics)
-        return (False, f"Could not find lyrics in html: {url}")
+
+            message += f"Could not lyrics in html for {url}\n    "
+        message = message.strip(" \n")
+        return (False, message)
 
     def process_dir(self, directory):
         if not path.isabs(directory):
@@ -254,9 +301,9 @@ class Nicole:
 
         # currently the only supported site
         if self.lyrics_site == "azlyrics":
-            url = self.get_url_azlyrics(artist, title)
+            urls = self.get_urls_azlyrics(artist, title)
             
-            success, lyrics = self.get_lyrics_azlyrics(url)
+            success, lyrics = self.get_lyrics_azlyrics(urls)
             if success:
                 if self.test_run:
                     print(f"{artist} - {title}:\n{lyrics}\n\n")
@@ -283,6 +330,9 @@ class Nicole:
 
 
 def main():
+    print("Nicole version 1.1")
+    # print("Get updates here: https://github.com/MatthiasQuintern/nicole")
+
     helpstring = """Command line options:
     -d [directory]      process directory [directory]
     -f [file]           process file [file]

setup.py

@@ -2,7 +2,7 @@ from setuptools import setup
 
 setup(
         name="nicole",
-        version="1.0",
+        version="1.1",
         description="Add lyrics from azlyrics.com to mp3-tag",
 
         author="Matthias Quintern",