Merge pull request #3995 from wisp3rwind/pr_lyrics_tekstowo_no_crashes

Crash-resilient Tekstowo lyrics source

beetsplug/lyrics.py

@@ -442,14 +442,15 @@ def fetch(self, artist, title):
         search_results = self.fetch_url(url)
         if not search_results:
             return None
-        song_page_url = self.parse_search_results(search_results)
 
+        song_page_url = self.parse_search_results(search_results)
         if not song_page_url:
             return None
 
         song_page_html = self.fetch_url(song_page_url)
         if not song_page_html:
             return None
+
         return self.extract_lyrics(song_page_html)
 
     def parse_search_results(self, html):
@@ -460,20 +461,27 @@ def parse_search_results(self, html):
         if not soup:
             return None
 
-        song_rows = soup.find("div", class_="content"). \
-            find("div", class_="card"). \
-            find_all("div", class_="box-przeboje")
+        content_div = soup.find("div", class_="content")
+        if not content_div:
+            return None
 
+        card_div = content_div.find("div", class_="card")
+        if not card_div:
+            return None
+
+        song_rows = card_div.find_all("div", class_="box-przeboje")
         if not song_rows:
             return None
 
         song_row = song_rows[0]
-
         if not song_row:
             return None
 
-        href = song_row.find('a').get('href')
-        return self.BASE_URL + href
+        link = song_row.find('a')
+        if not link:
+            return None
+
+        return self.BASE_URL + link.get('href')
 
     def extract_lyrics(self, html):
         html = _scrape_strip_cruft(html)
@@ -483,10 +491,11 @@ def extract_lyrics(self, html):
         if not soup:
             return None
 
-        c = soup.find("div", class_="song-text")
-        if c:
-            return c.get_text()
-        return None
+        lyrics_div = soup.find("div", class_="song-text")
+        if not lyrics_div:
+            return None
+
+        return lyrics_div.get_text()
 
 
 def remove_credits(text):

docs/changelog.rst

@@ -212,6 +212,9 @@ Other new things:
 * Get ISRC identifiers from musicbrainz
   Thanks to :user:`aereaux`.
 * :doc:`/plugins/metasync`: The ``metasync`` plugin now also fetches the ``Date Added`` field from iTunes databases and stores it in the``itunes_dateadded`` field.Thanks to :user:`sandersantema`.
+* :doc:`/plugins/lyrics`: Added Tekstowo.pl lyrics provider. Thanks to various
+  people for the implementation and for reporting issues with the initial version.
+  :bug:`3344` :bug:`3904` :bug:`3905` :bug:`3994`
 
   .. _py7zr: https://pypi.org/project/py7zr/
 
@@ -294,8 +297,6 @@ Fixes:
 * Removed ``@classmethod`` decorator from dbcore.query.NoneQuery.match method
   failing with AttributeError when called. It is now an instance method.
   :bug:`3516` :bug:`3517`
-* :doc:`/plugins/lyrics`: Added Tekstowo.pl lyrics provider
-  :bug:`3344`
 * :doc:`/plugins/lyrics`: Tolerate missing lyrics div in Genius scraper.
   Thanks to :user:`thejli21`.
   :bug:`3535` :bug:`3554`
@@ -355,8 +356,6 @@ Fixes:
   :bug:`3870`
 * Allow equals within ``--set`` value when importing.
   :bug:`2984`
-* :doc:`/plugins/lyrics`: Fix crashes for Tekstowo false positives
-  :bug:`3904`
 * :doc`/reference/cli`: Remove reference to rarfile version in link
 * Fix :bug:`2873`. Duplicates can now generate checksums. Thanks user:`wisp3rwind`
   for the pointer to how to solve. Thanks to :user:`arogl`.