codey/api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

allow for excluding cache on lyrics search (temp?) + addl genius fixes

Browse Source
This commit is contained in:
codey 2025-04-08 11:27:56 -04:00
parent fed5307386
commit c4ae59ca9f
3 changed files with 17 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
lyric_search/sources/aggregate.py
View File

@ -47,7 +47,7 @@ class Aggregate:
search_result: Optional[LyricsResult] = None search_result: Optional[LyricsResult] = None
for source in sources: for source in sources:
if source.label.lower() in self.exclude_methods: if source.label.lower() in self.exclude_methods:
if source.label.lower() == "cache" or not plain: if not plain:
logging.info("Exclude conditions rejected - source requested to exclude: %s, plain: %s", logging.info("Exclude conditions rejected - source requested to exclude: %s, plain: %s",
source.label, plain) source.label, plain)
else: else:

14
lyric_search/sources/genius.py
View File

@ -3,6 +3,7 @@ sys.path.insert(1,'..')
import traceback import traceback
import logging import logging
import time import time
import re
from typing import Optional from typing import Optional
from aiohttp import ClientTimeout, ClientSession from aiohttp import ClientTimeout, ClientSession
from bs4 import BeautifulSoup, ResultSet # type: ignore from bs4 import BeautifulSoup, ResultSet # type: ignore
@ -101,16 +102,23 @@ class Genius:
html = BeautifulSoup(htm.unescape(scrape_text).replace('<br/>', '\n'), "html.parser") html = BeautifulSoup(htm.unescape(scrape_text).replace('<br/>', '\n'), "html.parser")
header_tags: Optional[ResultSet] = html.find_all(['h1', 'h2', 'h3', 'h4', 'h5', 'span'])
if header_tags: header_tags_genius: Optional[ResultSet] = html.find_all(class_=re.compile('.*Header.*'))
for tag in header_tags: if header_tags_genius:
for tag in header_tags_genius:
tag.extract() tag.extract()
divs: Optional[ResultSet] = html.find_all("div", {"data-lyrics-container": "true"}) divs: Optional[ResultSet] = html.find_all("div", {"data-lyrics-container": "true"})
if not divs: if not divs:
return return
for div in divs: for div in divs:
header_tags: Optional[ResultSet] = div.find_all(['h1', 'h2', 'h3', 'h4', 'h5'])
if header_tags:
for tag in header_tags:
tag.extract()
returned_lyrics += div.get_text() returned_lyrics += div.get_text()
returned_lyrics: str = self.datautils.scrub_lyrics(returned_lyrics) returned_lyrics: str = self.datautils.scrub_lyrics(returned_lyrics)

6
utils/radio_util.py
View File

@ -186,15 +186,15 @@ class RadioUtil:
LIMITED TO ONE/SMALL SUBSET OF GENRES LIMITED TO ONE/SMALL SUBSET OF GENRES
""" """
# db_query = 'SELECT distinct(artist || " - " || song) AS artistdashsong, id, artist, song, album, genre, file_path, duration FROM tracks\ db_query = 'SELECT distinct(artist || " - " || song) AS artistdashsong, id, artist, song, album, genre, file_path, duration FROM tracks\
# WHERE artist LIKE "%tethered%" OR artist LIKE "%more of mysel%" ORDER BY artist DESC, album ASC, song ASC' WHERE genre LIKE "%edm%" OR artist LIKE "%sullivan king%" OR artist LIKE "%kai wachi%" OR artist LIKE "%kayzo%" ORDER BY RANDOM()' #ORDER BY artist DESC, album ASC, song ASC'
""" """
LIMITED TO ONE/SOME ARTISTS... LIMITED TO ONE/SOME ARTISTS...
""" """
# db_query = 'SELECT distinct(artist || " - " || song) AS artistdashsong, id, artist, song, album, genre, file_path, duration FROM tracks\ # db_query = 'SELECT distinct(artist || " - " || song) AS artistdashsong, id, artist, song, album, genre, file_path, duration FROM tracks\
# WHERE (artist LIKE "%sullivan king%" OR artist LIKE "%kayzo%" OR artist like "%kai wachi%" OR genre LIKE "%edm%" OR genre LIKE "%electronicore%") AND (NOT song LIKE "%%stripped%%" AND NOT song LIKE "%(2022)%" AND NOT song LIKE "%(live%%" AND NOT song LIKE "%%acoustic%%" AND NOT song LIKE "%%instrumental%%" AND NOT song LIKE "%%remix%%" AND NOT song LIKE "%%reimagined%%" AND NOT song LIKE "%%alternative%%" AND NOT song LIKE "%%unzipped%%") GROUP BY artistdashsong ORDER BY RANDOM()'# ORDER BY album ASC, id ASC' # WHERE (artist LIKE "%a scent like wolves%" OR artist LIKE "%bad wolves%" or artist LIKE "%oceans%" OR artist LIKE "%oh,%" OR artist LIKE "%august%" OR artist LIKE "%periphery%") AND (NOT song LIKE "%%stripped%%" AND NOT song LIKE "%(2022)%" AND NOT song LIKE "%(live%%" AND NOT song LIKE "%%acoustic%%" AND NOT song LIKE "%%instrumental%%" AND NOT song LIKE "%%remix%%" AND NOT song LIKE "%%reimagined%%" AND NOT song LIKE "%%alternative%%" AND NOT song LIKE "%%unzipped%%") GROUP BY artistdashsong ORDER BY RANDOM()'# ORDER BY album ASC, id ASC'
async with sqlite3.connect(self.active_playlist_path, async with sqlite3.connect(self.active_playlist_path,
timeout=2) as db_conn: timeout=2) as db_conn: