Created
October 29, 2017 14:39
-
-
Save tbnbooij/5b88a47dcf6cfe181d6d603b99821bd7 to your computer and use it in GitHub Desktop.
Ultimate Guitar Chord Scraper
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from flask import Flask, request, jsonify | |
import re | |
import requests | |
from bs4 import BeautifulSoup | |
app = Flask(__name__) | |
@app.route('/') | |
def main(): | |
arg = request.args.get('url') | |
match = re.search("https://tabs.ultimate-guitar.com/(.*)crd_(.*).htm", arg) | |
if match is not None: | |
url = match.group(0) | |
page = requests.get(url) | |
soup = BeautifulSoup(page.text, 'html.parser') | |
# Get the song title | |
try: | |
raw_title = soup.select(".t_title > div > h1")[0].text.strip() | |
title_words = raw_title.split(' ') | |
song_title = ' '.join(title_words[:len(title_words) - 1]) | |
except: | |
song_title = "UNKNOWN" | |
# Get the author of the song | |
try: | |
song_author = soup.select(".t_autor > a")[0].text | |
except: | |
song_author = "UNKNOWN" | |
# Get the lyrics and chords of the song | |
try: | |
raw_content = filter(None, soup.select(".js-tab-content")[0].text.replace("\r", "").replace('\"', """).split("\n")) | |
content = [i for i in raw_content if i != ""] | |
except: | |
content = "UNKNOWN" | |
return jsonify(title = song_title, author = song_author, content = content) | |
else: | |
return jsonify(error = "Invalid argument") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment