azlScrap/azl.py

37 lines
1.2 KiB
Python

from bs4 import BeautifulSoup
import requests
from requests import get
def getLink(artist, title):
base_start = 'https://www.azlyrics.com/lyrics/'
artist = artist.lower()
artist = artist.replace(' ', '')
artist = artist.replace('-', '')
title = title.lower()
title = title.replace(' ', '')
title = title.replace('?', '')
title = title.replace("'", '')
link = base_start + artist + '/' + title + '.html'
return(link)
def getLyrics(link):
w = requests.get(link)
soup = BeautifulSoup(w.text, 'html.parser')
lyr = soup.find_all('div', class_=False)
let = str(lyr)
return(let)
def parsero(lyrics):
let = lyrics
let = let.replace('<br/>', ' ')
let = let.replace('<i>', '')
let = let.replace('</i>', '')
let = let.replace('<div>', '')
let = let.replace('</div>,', '')
let = let.replace('</div>', '')
let = let.replace('<div id="RTK_vQAi">', '')
let = let.replace('<div id="RTK_QZjx">', '')
let = let.replace('<div id="RTK_sdL2">', '')
let = let.replace('<!-- Usage of azlyrics.com content by any third-party lyrics provider is prohibited by our licensing agreement. Sorry about that. -->', '')
return(let[1:-1])