yt-dlc/youtube_dl/extractor/newgrounds.py

from __future__ import unicode_literals

import json
import re

from .common import InfoExtractor
from ..utils import determine_ext


class NewgroundsIE(InfoExtractor):
    _VALID_URL = r'(?:https?://)?(?:www\.)?newgrounds\.com/audio/listen/(?P<id>\d+)'
    _TEST = {
        'url': 'http://www.newgrounds.com/audio/listen/549479',
        'file': '549479.mp3',
        'md5': 'fe6033d297591288fa1c1f780386f07a',
        'info_dict': {
            "title": "B7 - BusMode",
            "uploader": "Burn7",
        }
    }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        music_id = mobj.group('id')
        webpage = self._download_webpage(url, music_id)
        
        title = self._html_search_regex(
            r',"name":"([^"]+)",', webpage, 'music title')
        uploader = self._html_search_regex(
            r',"artist":"([^"]+)",', webpage, 'music uploader')
        
        music_url_json_string = self._html_search_regex(
            r'({"url":"[^"]+"),', webpage, 'music url') + '}'
        music_url_json = json.loads(music_url_json_string)
        music_url = music_url_json['url']

        return {
            'id': music_id,
            'title': title,
            'url': music_url,
            'uploader': uploader,
        }