import re
import urllib.request
import markovify
from time import sleep

def scrape():
    originalLyrics = open('lyrics.txt', 'w')
    
    url = "https://www.azlyrics.com/l/linkinpark.html"
    artistHtml = urllib.request.urlopen(url)
    artistHtmlStr = str(artistHtml.read())

    links = re.findall('href="([^"]+)"', artistHtmlStr)

    songLinks = []

    songLinksTxt = open("linkinpark-links.txt", 'w')
    for x in links:
        if "lyrics/linkinpark" in x:
            x = x.replace("..", "")
            x = "https://www.azlyrics.com" + x
            songLinks.append(x)
            songLinksTxt.write(x+'\n')
    songLinksTxt.close()

    # songLinksTxt = open("linkinpark-links.txt", 'r').readlines()
    # for x in songLinksTxt:
    #     songLinks.append(x)
    
    print("# Links:", len(songLinks))

    for x in songLinks:
        songHtml = urllib.request.urlopen(x)
        songHtmlStr = str(songHtml.read())
        split = songHtmlStr.split('<!-- Usage of azlyrics.com content by any third-party lyrics provider is prohibited by our licensing agreement. Sorry about that. -->', 1)
        splitHtml = split[1]
        split = splitHtml.split('</div>', 1)
        lyrics = split[0]
        lyrics = lyrics.replace('<br>', '\n')
        lyrics = lyrics.replace('\\', '')
        lyrics = lyrics.replace('\nn', '\n')
        lyrics = lyrics.replace('<i>', '')
        lyrics = lyrics.replace('</i>', '')
        lyrics = lyrics.replace('[Chorus]', '')
        originalLyrics.write(lyrics)
        print("\t--", x)
        sleep(5)
    
    originalLyrics.close()

# scrape()

generatedLyrics = ()
file = open('lyrics.txt', 'r')
text = file.read()

markovifyTextModel = markovify.Text(text)
generatedLyrics = markovifyTextModel.make_sentence()
print(generatedLyrics)