66 lines
2.0 KiB
Python
Raw Normal View History

2019-01-01 16:46:03 +01:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
import re
import json
class GramofonOnlineIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?gramofononline\.hu(/(listen.php\?.*track=)?(?P<id>[0-9]+))?'
_TESTS = [{
'url': 'https://gramofononline.hu/1401835664/papageno-duett',
'md5': '1b4bcabde313f09cdd48c463b54d8125',
'info_dict': {
'id': '1401835664',
'title': 'Papageno-Duett ',
'artist': 'Johanna Gadski, Otto Goritz, ismeretlen zenekar',
'ext': 'mp3'
}
}, {
'url': 'https://gramofononline.hu/listen.php?autoplay=true&track=1401835664',
'md5': '1b4bcabde313f09cdd48c463b54d8125',
'info_dict': {
'id': '1401835664',
'title': 'Papageno-Duett ',
'artist': 'Johanna Gadski, Otto Goritz, ismeretlen zenekar',
'ext': 'mp3'
},
'params': {
'skip_download': True,
}
}]
def _get_entry(self, obj):
2019-01-01 17:10:51 +01:00
id1 = obj.get('id')
source = obj.get('source')
title = obj.get('name')
artist = obj.get('artist')
2019-01-01 16:46:03 +01:00
return {
'id': id1,
2019-01-01 17:10:51 +01:00
'title': title,
2019-01-01 16:46:03 +01:00
'http_headers': {'Referer': 'https://gramofononline.hu/' + id1},
'artist': artist,
'thumbnail': 'https://gramofononline.hu/getImage.php?id=' + source,
'formats': [{
'url': 'https://gramofononline.hu/go/master/' + source + '.mp3',
'ext': 'mp3'
}, {
'url': 'https://gramofononline.hu/go/noise_reduction/' + source + '.mp3',
'ext': 'mp3'
}]
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2019-01-01 17:10:51 +01:00
m = re.search(r'var\s+trackList\s*=\s*(\[.*\]);', webpage)
2019-01-01 16:46:03 +01:00
lineobjs = json.loads(m.group(1))
2019-01-01 17:10:51 +01:00
return {
'_type': 'playlist',
'entries': [self._get_entry(obj) for obj in lineobjs]
}