[script.cu.lrclyrics] 6.7.1

Author: ronie

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="6.6.9" provider-name="Taxigps, ronie">
+<addon id="script.cu.lrclyrics" name="CU LRC Lyrics" version="6.7.1" provider-name="Taxigps, ronie">
 	<requires>
 		<import addon="xbmc.python" version="3.0.0"/>
 		<import addon="script.module.beautifulsoup4" version="4.8.2+matrix.1"/>

script.cu.lrclyrics/changelog.txt

@@ -1,3 +1,12 @@
+v6.7.1
+- fix genius scraper
+- fix musicmatch scraper
+- fix supermusic scraper
+- remove redundant language files
+
+v6.7.0
+- fixed SyntaxWarning errors
+
 v6.6.9
 - python 3.13 compatibility
 - fixed Genius scraper

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

@@ -52,7 +52,7 @@ def search(self, artist, title):
             searchResponse = req.text
         except:
             return None
-        searchResult = re.findall('<h2><a\shref="(.*?#([0-9]+))".*?>(.*?)</a></h2>', searchResponse)
+        searchResult = re.findall(r'<h2><a\shref="(.*?#([0-9]+))".*?>(.*?)</a></h2>', searchResponse)
         if len(searchResult) == 0:
             return None
         links = []
@@ -75,7 +75,7 @@ def findLyrics(self, url, index):
             res = req.text
         except:
             return None
-        pattern = '<a\sname="%index%">(.*?)(?:<h3>|<div)' # require multi line and dot all mode
+        pattern = r'<a\sname="%index%">(.*?)(?:<h3>|<div)' # require multi line and dot all mode
         pattern = pattern.replace('%index%', index)
         match = re.search(pattern, res, re.MULTILINE | re.DOTALL)
         if match:
@@ -96,7 +96,7 @@ def getAlbumName(self, url):
             res = req.text
         except:
             return ''
-        match = re.search('<h2>(?:album|single|ep|live):?\s?(.*?)</h2>', res, re.IGNORECASE)
+        match = re.search(r'<h2>(?:album|single|ep|live):?\s?(.*?)</h2>', res, re.IGNORECASE)
         if match:
             return ('(' + match.group(1) + ')').replace('\'', '')
         else:

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

@@ -8,6 +8,7 @@
 import xbmcaddon
 import json
 import difflib
+from bs4 import BeautifulSoup
 from lib.utils import *
 
 __title__ = 'genius'
@@ -19,7 +20,7 @@ class LyricsFetcher:
     def __init__(self, *args, **kwargs):
         self.DEBUG = kwargs['debug']
         self.settings = kwargs['settings']
-        self.url = 'http://api.genius.com/search?q=%s%%20%s&access_token=Rq_cyNZ6fUOQr4vhyES6vu1iw3e94RX85ju7S8-0jhM-gftzEvQPG7LJrrnTji11'
+        self.url = 'https://genius.com/api/search/multi?per_page=5&q=%s %s'
 
     def get_lyrics(self, song):
         log('%s: searching lyrics for %s - %s' % (__title__, song.artist, song.title), debug=self.DEBUG)
@@ -29,40 +30,51 @@ def get_lyrics(self, song):
         lyrics.lrc = __lrc__
         try:
             headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; rv:77.0) Gecko/20100101 Firefox/77.0'}
-            url = self.url % (urllib.parse.quote(song.artist), urllib.parse.quote(song.title))
+            url = self.url % (song.artist, song.title)
             req = requests.get(url, headers=headers, timeout=10)
             response = req.text
         except:
             return None
         data = json.loads(response)
-        try:
-            name = data['response']['hits'][0]['result']['primary_artist']['name']
-            track = data['response']['hits'][0]['result']['title']
-            if (difflib.SequenceMatcher(None, song.artist.lower(), name.lower()).ratio() > 0.8) and (difflib.SequenceMatcher(None, song.title.lower(), track.lower()).ratio() > 0.8):
-                self.page = data['response']['hits'][0]['result']['url']
-            else:
-                return None
-        except:
+        links = []
+        if (len(data['response']['sections']) < 2):
+            return None
+        for item in data['response']['sections'][1]['hits']:
+            try:
+                artistname = item['result']['artist_names']
+                songtitle = item['result']['title']
+                url = item['result']['url']
+                if (difflib.SequenceMatcher(None, song.artist.lower(), artistname.lower()).ratio() > 0.8) and (difflib.SequenceMatcher(None, song.title.lower(), songtitle.lower()).ratio() > 0.8):
+                    links.append((artistname + ' - ' + songtitle, url, artistname, songtitle))
+            except:
+                continue
+        if len(links) == 0:
             return None
-        log('%s: search url: %s' % (__title__, self.page), debug=self.DEBUG)
+        elif len(links) > 1:
+            lyrics.list = links
+        for link in links:
+            lyr = self.get_lyrics_from_list(link)
+            if lyr:
+                lyrics.lyrics = lyr
+                return lyrics
+        return None
+
+    def get_lyrics_from_list(self, link):
+        title,url,artist,song = link
+        log('%s: search url: %s' % (__title__, url), debug=self.DEBUG)
         try:
             headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; rv:77.0) Gecko/20100101 Firefox/77.0'}
-            req = requests.get(self.page, headers=headers, timeout=10)
+            req = requests.get(url, headers=headers, timeout=10)
             response = req.text
         except:
             return None
-        response = html.unescape(response)
-        matchcode = re.findall('class="Lyrics-.*?">(.*?)</div><div', response, flags=re.DOTALL)
         try:
-            lyricscode = ""
-            for matchCodeItem in matchcode:
-                lyricscode = lyricscode + matchCodeItem + '\n'
-            lyr1 = re.sub('<br/>', '\n', lyricscode)
-            lyr2 = re.sub('<[^<]+?>', '', lyr1)
-            lyr3 = lyr2.replace('\\n','\n').strip()
-            if not lyr3 or lyr3 == '[Instrumental]' or lyr3.startswith('Lyrics for this song have yet to be released'):
-                return None
-            lyrics.lyrics = lyr3
-            return lyrics
+            matchcode = re.search(r'\\"html\\":\\"(.*?)\\",\\"', response, flags=re.DOTALL)
+            if matchcode:
+                lyr1 = matchcode.group(1).replace('\\\\\\', '')
+                lyr2 = re.sub('<[^<]+?>', '', lyr1)
+                lyr3 = lyr2.replace('\\\\n','\n').replace("\\'", "'").strip()
+                lyrics = lyr3
+                return lyrics
         except:
             return None

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

@@ -45,7 +45,7 @@ def get_lyrics(self, song):
             response = search.text
         except:
             return None
-        matchcode = re.search('Lyrics of (.*?)Writer\(s\): ', response, flags=re.DOTALL)
+        matchcode = re.search(r'body":"(.*?)"', response, flags=re.DOTALL)
         if matchcode:
             lyricscode = (matchcode.group(1))
             lyr = re.sub('<[^<]+?>', '\n', lyricscode)

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

@@ -2,63 +2,89 @@
 import sys
 import re
 import requests
+import difflib
 import html
 import xbmc
 import xbmcaddon
+from bs4 import BeautifulSoup
 from lib.utils import *
 
 __title__ = 'supermusic'
 __priority__ = '250'
 __lrc__ = False
 
+headers = {}
+headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:51.0) Gecko/20100101 Firefox/51.0'
+
 
 class LyricsFetcher:
     def __init__(self, *args, **kwargs):
         self.DEBUG = kwargs['debug']
         self.settings = kwargs['settings']
+        self.SEARCH_URL = 'https://www.supermusic.cz/najdi.php?hladane=%s+%s&typhladania=skupina'
+        self.LYRIC_URL = 'https://supermusic.cz/'
 
     def get_lyrics(self, song):
         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__
-        artist = song.artist.lower()
-        title = song.title.lower()
-
+        artist = song.artist.lower().replace(' ', '+')
+        title = song.title.lower().replace(' ', '+')
         try:
-            req = requests.post('https://supermusic.cz/najdi.php', data={'hladane': title, 'typhladania': 'piesen', 'fraza': 'off'})
+            req = requests.get(self.SEARCH_URL % (artist, title), headers=headers, timeout=10)
             response = req.text
         except:
             return None
         req.close()
-        url = None
-        try:
-            items = re.search(r'Počet nájdených piesní.+<br><br>(.*)<BR>', response, re.S).group(1)
-            for match in re.finditer(r'<a href=(?P<url>"[^"]+?") target="_parent"><b>(?P<artist>.*?)</b></a> - (?P<type>.+?) \(<a href', items):
-                matched_url, matched_artist, matched_type = match.groups()
-                if matched_type not in ('text', 'akordy a text'):
-                    continue
-                if matched_artist.lower() == artist:
-                    url = matched_url.strip('"')
-                    break
-        except:
-            return None
-
-        if not url:
+        links = []
+        soup = BeautifulSoup(response, 'html.parser')
+        for item in soup.find_all('div', {'class': 'result-item'}):
+            try:
+                artistdata = item.find('span', {'class': 'result-artist'})
+                songdata = item.find('h3', {'class': 'result-title'})
+                artistname = artistdata.find('a').get_text()
+                songtitle = songdata.find('a').get_text()
+                url = songdata.find('a').get('href')
+                if (difflib.SequenceMatcher(None, song.artist.lower(), artistname.lower()).ratio() > 0.8) and (difflib.SequenceMatcher(None, song.title.lower(), songtitle.lower()).ratio() > 0.8):
+                    links.append((artistname + ' - ' + songtitle, self.LYRIC_URL + url, artistname, songtitle))
+            except:
+                continue
+        if len(links) == 0:
             return None
+        elif len(links) > 1:
+            lyrics.list = links
+        for link in links:
+            lyr = self.get_lyrics_from_list(link)
+            if lyr:
+                lyrics.lyrics = lyr
+                return lyrics
+        return None
 
+    def get_lyrics_from_list(self, link):
+        title,url,artist,song = link
+        log('%s: search url: %s' % (__title__, url), debug=self.DEBUG)
         try:
-            req = requests.get('https://supermusic.cz/%s' % url)
-            response = req.text
-            lyr = re.search(r'class=piesen>(.*?)</font>', response, re.S).group(1)
-            lyr = re.sub(r'<sup>.*?</sup>', '', lyr)
-            lyr = re.sub(r'<br\s*/>\s*', '\n', lyr)
-            lyr = re.sub(r'<!--.*?-->', '', lyr, flags=re.DOTALL)
-            lyr = re.sub(r'<[^>]*?>', '', lyr, flags=re.DOTALL)
-            lyr = lyr.strip('\r\n')
-            lyr = html.unescape(lyr)
-            lyrics.lyrics = lyr
-            return lyrics
+            response = requests.get(url, headers=headers, timeout=10)
+            result = response.text
         except:
             return None
+        soup = BeautifulSoup(result, 'html.parser')
+        for item in soup.find_all('a', {'class': 'version-tab'}):
+            if item.get_text() == 'text':
+                newurl = self.LYRIC_URL + item.get('href')
+                if newurl != url:
+                    try:
+                        log('%s: search url: %s' % (__title__, newurl), debug=self.DEBUG)
+                        response = requests.get(newurl, headers=headers, timeout=10)
+                        result = response.text
+                    except:
+                        return None
+                    soup = BeautifulSoup(result, 'html.parser')
+                try:
+                    lyr = soup.find('div', {'class': 'chord-text'}).get_text()
+                except:
+                    return None
+                lyrics = lyr
+                return lyrics

script.cu.lrclyrics/lib/embedlrc.py

@@ -176,7 +176,7 @@ def getAPELyrics(bfile, getlrc):
         return
 
 def isLRC(lyr):
-    match = re.compile('\[(\d+):(\d\d)(\.\d+|)\]').search(lyr)
+    match = re.compile(r'\[(\d+):(\d\d)(\.\d+|)\]').search(lyr)
     if match:
         return True
     else:

script.cu.lrclyrics/lib/gui.py

@@ -253,7 +253,7 @@ def save_lyrics_to_file(self, lyrics, adjust=None):
             # save our manual sync offset to file
             adjust = int(adjust * 1000)
             # check if there's an existing offset tag
-            found = re.search('\[offset:(.*?)\]', lyr, flags=re.DOTALL)
+            found = re.search(r'\[offset:(.*?)\]', lyr, flags=re.DOTALL)
             if found:
                 # get the sum of both values
                 try:
@@ -436,7 +436,7 @@ def __init__(self, *args, **kwargs):
         self.dialog = xbmcgui.Dialog()
 
     def onInit(self):
-        self.matchlist = ['@', 'www\.(.*?)\.(.*?)', 'QQ(.*?)[1-9]', 'artist ?: ?.', 'album ?: ?.', 'title ?: ?.', 'song ?: ?.', 'by ?: ?.']
+        self.matchlist = ['@', r'www\.(.*?)\.(.*?)', 'QQ(.*?)[1-9]', 'artist ?: ?.', 'album ?: ?.', 'title ?: ?.', 'song ?: ?.', 'by ?: ?.']
         self.text = self.getControl(110)
         self.label = self.getControl(200)
         self.setup_gui()
@@ -619,12 +619,12 @@ def get_parts(self, line):
 
     def parser_lyrics(self, lyrics):
         offset = 0.00
-        found = re.search('\[offset:\s?(-?\d+)\]', lyrics)
+        found = re.search(r'\[offset:\s?(-?\d+)\]', lyrics)
         if found:
             offset = float(found.group(1)) / 1000
         self.pOverlay = []
-        tag1 = re.compile('\[(\d+):(\d\d)[\.:](\d\d)\]')
-        tag2 = re.compile('\[(\d+):(\d\d)([\.:]\d+|)\]')
+        tag1 = re.compile(r'\[(\d+):(\d\d)[\.:](\d\d)\]')
+        tag2 = re.compile(r'\[(\d+):(\d\d)([\.:]\d+|)\]')
         lyrics = lyrics.replace('\r\n' , '\n')
         sep = '\n'
         for x in lyrics.split(sep):

script.cu.lrclyrics/lib/scrapertest.py

@@ -69,8 +69,8 @@ def test_scrapers():
     dialog.update(16, LANGUAGE(32163) % 'genius')
     log('==================== genius ====================', debug=True)
     song = Song(opt=lyricssettings)
-    song.artist = 'Maren Morris'
-    song.title = 'My Church'
+    song.artist = 'Michael Jackson'
+    song.title = 'Beat It'
     st = time.time()
     lyrics = lyricsScraper_genius.LyricsFetcher(settings=lyricssettings, debug=True).get_lyrics(song)
     ft = time.time()
@@ -126,8 +126,8 @@ def test_scrapers():
     dialog.update(40, LANGUAGE(32163) % 'lyricsmode')
     log('==================== lyricsmode ====================', debug=True)
     song = Song(opt=lyricssettings)
-    song.artist = 'Maren Morris'
-    song.title = 'My Church'
+    song.artist = 'M83'
+    song.title = 'Kim'
     st = time.time()
     lyrics = lyricsScraper_lyricsmode.LyricsFetcher(settings=lyricssettings, debug=True).get_lyrics(song)
     ft = time.time()
@@ -240,8 +240,8 @@ def test_scrapers():
     dialog.update(88, LANGUAGE(32163) % 'supermusic')
     log('==================== supermusic ====================', debug=True)
     song = Song(opt=lyricssettings)
-    song.artist = 'Karel Gott'
-    song.title = 'Trezor'
+    song.artist = 'Madonna'
+    song.title = 'Holiday'
     st = time.time()
     lyrics = lyricsScraper_supermusic.LyricsFetcher(settings=lyricssettings, debug=True).get_lyrics(song)
     ft = time.time()

script.cu.lrclyrics/resources/language/resource.language.af_za/strings.po

@@ -270,10 +270,6 @@ msgctxt "#32904"
 msgid "Music 163"
 msgstr ""
 
-msgctxt "#32905"
-msgid "Lyricsify"
-msgstr ""
-
 msgctxt "#32912"
 msgid "Genius"
 msgstr ""