dotfiles

#!/usr/bin/env python3
# Print the lyrics of a song by scraping genius.com.  This is primarily
# intended to be used to embed lyrics in music downloaded from
# YouTube.

import re
import sys
import requests
import json
from bs4 import BeautifulSoup
from urllib.parse import quote

lg = "https://genius.com"

def get_lyrics_url(term):
    # We could use this JSON to get considerably more metadata...
    data = json.loads(requests.get(lg + "/api/search?q=" + quote(term)).text)
    try:
        return lg + data["response"]["hits"][0]["result"]["path"]
    except:
        return None

def get_lyrics(url):
    soup = BeautifulSoup(requests.get(url).text, "html.parser")
    containers = soup.find_all(attrs={"data-lyrics-container": "true"})
    return "".join([pretty_lyrics(c) + "\n" for c in containers]).rstrip("\n")

def pretty_lyrics(html):
    text = ""
    for elem in html:
        if elem.name == None:
            text += elem.string
        elif elem.name == "br":
            text += "\n"
        elif elem.name == "span" or elem.name == "a":
            text += pretty_lyrics(elem)
        else:
            try:
                text += elem.string
            except:
                text += "\n"
    return text

if __name__ == "__main__":
    if len(sys.argv) != 2:
        print("Usage: lyrics 'some search term'", file=sys.stderr)
        sys.exit(1)
    else:
        url = get_lyrics_url(sys.argv[1])
        if url is None:
            print("No lyrics found", file=sys.stderr)
            sys.exit(1)
        else:
            print(get_lyrics(url))