Backup_Repos/beets
1
0
Fork 0
mirror of https://github.com/beetbox/beets.git synced 2025-12-30 12:32:33 +01:00
Code Issues Projects Releases Wiki Activity

Add alternative scraping algorithm to deal with Genius's new song page html layout.

Browse source
This commit is contained in:
stlutz 2020-05-16 17:15:45 +02:00
parent 46143d9762
commit 15402f6aa7
1 changed files with 27 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

33
beetsplug/lyrics.py
View file

@ -373,13 +373,34 @@ class Genius(Backend):
# Remove script tags that they put in the middle of the lyrics.
[h.extract() for h in html('script')]
# At least Genius is nice and has a tag called 'lyrics'!
# Updated css where the lyrics are based in HTML.
# Most of the time, the page contains a div with class="lyrics" where
# all of the lyrics can be found already correctly formatted
# Sometimes, though, it packages the lyrics into separate divs, most
# likely for easier ad placement
lyrics_div = html.find("div", class_="lyrics")
if lyrics_div is None:
self._log.debug(u'Genius lyrics for {0} not found',
page_url)
return None
if not lyrics_div:
self._log.debug(u'Received unusual song page html')
verse_div = html.find("div",
class_=re.compile("Lyrics__Container"))
if not verse_div:
with open('instrumental.html', 'w') as text_file:
text_file.write(str(html))
if html.find("div",
class_=re.compile("LyricsPlaceholder__Message"),
string="This song is an instrumental"):
self._log.debug('Detected instrumental')
return "[Instrumental]"
else:
self._log.debug("Couldn't scrape page using known layouts")
return None
lyrics_div = verse_div.parent
for br in lyrics_div.find_all("br"):
br.replace_with("\n")
ads = lyrics_div.find_all("div",
class_=re.compile("InreadAd__Container"))
for ad in ads:
ad.replace_with("\n")
return lyrics_div.get_text()