[script.cu.lrclyrics] 6.6.2 (#2551)

Co-authored-by: ronie <[email protected]>

script.cu.lrclyrics/addon.xml

@@ -1,5 +1,5 @@
 <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
-<addon id="script.cu.lrclyrics" name="CU LRC Lyrics" version="6.5.2" provider-name="Taxigps, ronie">
+<addon id="script.cu.lrclyrics" name="CU LRC Lyrics" version="6.6.2" provider-name="Taxigps, ronie">
 	<requires>
 		<import addon="xbmc.python" version="3.0.0"/>
 		<import addon="script.module.beautifulsoup4" version="4.8.2+matrix.1"/>
@@ -80,6 +80,6 @@
 		<assets>
 			<icon>resources/icon.png</icon>
 		</assets>
-		<news>- remove invalid characters from filenames</news>
+		<news>- fixed broken scrapers and added new ones</news>
 	</extension>
 </addon>

script.cu.lrclyrics/changelog.txt

@@ -1,3 +1,16 @@
+v6.6.1
+- add supermusic scraper
+
+v6.6.0
+- removed minilyrics
+- removed gomaudio
+- fixed lyricsify
+- fixed lyricscom
+- fixed azlyrics
+- added lrclib
+- added megalobiz
+- added musixmatch lrc
+
 v6.5.2
 - remove invalid characters from filenames
 

script.cu.lrclyrics/lib/culrcscrapers/azlyrics/lyricsScraper.py

@@ -33,7 +33,7 @@ def get_lyrics(self, song):
             return None
         req.close()
         try:
-            lyricscode = response.split('. -->')[1].split('</div')[0]
+            lyricscode = response.split('t. -->')[1].split('</div')[0]
             lyricstext = html.unescape(lyricscode).replace('<br />', '\n')
             lyr = re.sub('<[^<]+?>', '', lyricstext)
             lyrics.lyrics = lyr

script.cu.lrclyrics/lib/culrcscrapers/darklyrics/lyricsScraper.py

@@ -18,7 +18,7 @@
     pass
 
 __title__ = 'darklyrics'
-__priority__ = '250'
+__priority__ = '260'
 __lrc__ = False
 
 

script.cu.lrclyrics/lib/culrcscrapers/lyricscom/lyricsScraper.py

@@ -15,40 +15,41 @@ class LyricsFetcher:
     def __init__(self, *args, **kwargs):
         self.DEBUG = kwargs['debug']
         self.settings = kwargs['settings']
-        self.url = 'http://www.lyrics.com/serp.php?st=%s&qtype=2'
+        self.url = 'https://www.lyrics.com/serp.php?st=%s&qtype=2'
 
     def get_lyrics(self, song):
+        sess = requests.Session()
         log('%s: searching lyrics for %s - %s' % (__title__, song.artist, song.title), debug=self.DEBUG)
         lyrics = Lyrics(settings=self.settings)
         lyrics.song = song
         lyrics.source = __title__
         lyrics.lrc = __lrc__
         try:
-            request = requests.get(self.url % urllib.parse.quote_plus(song.artist), timeout=10)
+            request = sess.get(self.url % urllib.parse.quote_plus(song.artist), timeout=10)
             response = request.text
         except:
             return
         soup = BeautifulSoup(response, 'html.parser')
         url = ''
         for link in soup.find_all('a'):
             if link.string and link.get('href').startswith('artist/'):
-                url = 'http://www.lyrics.com/' + link.get('href')
+                url = 'https://www.lyrics.com/' + link.get('href')
                 break
         if url:
             try:
-                req = requests.get(url, timeout=10)
+                req = sess.get(url, timeout=10)
                 resp = req.text
             except:
                 return
             soup = BeautifulSoup(resp, 'html.parser')
             url = ''
             for link in soup.find_all('a'):
                 if link.string and (difflib.SequenceMatcher(None, link.string.lower(), song.title.lower()).ratio() > 0.8):
-                    url = 'http://www.lyrics.com' + link.get('href')
+                    url = 'https://www.lyrics.com' + link.get('href')
                     break
             if url:
                 try:
-                    req2 = requests.get(url, timeout=10)
+                    req2 = sess.get(url, timeout=10)
                     resp2 = req2.text
                 except:
                     return

script.cu.lrclyrics/lib/culrcscrapers/lyricsify/lyricsScraper.py

@@ -20,7 +20,7 @@ class LyricsFetcher:
     def __init__(self, *args, **kwargs):
         self.DEBUG = kwargs['debug']
         self.settings = kwargs['settings']
-        self.SEARCH_URL = 'https://www.lyricsify.com/search?q=%s'
+        self.SEARCH_URL = 'https://www.lyricsify.com/lyrics/%s/%s'
         self.LYRIC_URL = 'https://www.lyricsify.com%s'
 
     def get_lyrics(self, song):
@@ -29,19 +29,18 @@ def get_lyrics(self, song):
         lyrics.song = song
         lyrics.source = __title__
         lyrics.lrc = __lrc__
-        artist = song.artist.replace(' ', '+')
-        title = song.title.replace(' ', '+')
-        search = '%s+%s' % (artist, title)
+        artist = song.artist.replace(' ', '-')
+        title = song.title.replace(' ', '-')
         try:
-            url = self.SEARCH_URL % search
+            url = self.SEARCH_URL % (artist, title)
             search = requests.get(url, headers=UserAgent, timeout=10)
             response = search.text
         except:
             return None
         links = []
         soup = BeautifulSoup(response, 'html.parser')
         for link in soup.find_all('a'):
-            if link.string and link.get('href').startswith('/lyrics/'):
+            if link.string and link.get('href').startswith('/lrc/'):
                 foundartist = link.string.split(' - ', 1)[0]
                 # some links don't have a proper 'artist - title' format
                 try:
@@ -69,7 +68,7 @@ def get_lyrics_from_list(self, link):
             response = search.text
         except:
             return None
-        matchcode = re.search('div id="entry">(.*?)<div', response, flags=re.DOTALL)
+        matchcode = re.search('/h3>(.*?)</div', response, flags=re.DOTALL)
         if matchcode:
             lyricscode = (matchcode.group(1))
             cleanlyrics = re.sub('<[^<]+?>', '', lyricscode)