yt-dlp/youtube_dl/extractor/deezer.py

82 lines
2.8 KiB
Python
Raw Normal View History

2014-09-12 07:25:58 +02:00
from __future__ import unicode_literals
import json
import re
from .common import InfoExtractor
from ..utils import (
2014-09-13 08:51:21 +02:00
ExtractorError,
2014-09-12 07:25:58 +02:00
int_or_none,
orderedSet,
)
class DeezerPlaylistIE(InfoExtractor):
2019-08-18 23:35:39 +02:00
_VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?playlist/(?P<id>[0-9]+)'
2014-09-12 07:25:58 +02:00
_TEST = {
'url': 'http://www.deezer.com/playlist/176747451',
'info_dict': {
'id': '176747451',
'title': 'Best!',
2019-08-12 17:50:03 +02:00
'uploader': 'anonymous',
2019-08-18 23:35:39 +02:00
'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
2014-09-12 07:25:58 +02:00
},
2019-08-12 17:50:03 +02:00
'playlist_count': 29,
2014-09-12 07:25:58 +02:00
}
def _real_extract(self, url):
if 'test' not in self._downloader.params:
self._downloader.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!')
mobj = re.match(self._VALID_URL, url)
playlist_id = mobj.group('id')
webpage = self._download_webpage(url, playlist_id)
2014-09-13 08:51:21 +02:00
geoblocking_msg = self._html_search_regex(
r'<p class="soon-txt">(.*?)</p>', webpage, 'geoblocking message',
default=None)
if geoblocking_msg is not None:
raise ExtractorError(
'Deezer said: %s' % geoblocking_msg, expected=True)
2014-09-12 07:25:58 +02:00
data_json = self._search_regex(
2016-04-05 18:27:33 +02:00
(r'__DZR_APP_STATE__\s*=\s*({.+?})\s*</script>',
r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n'),
webpage, 'data JSON')
2014-09-12 07:25:58 +02:00
data = json.loads(data_json)
2019-08-13 12:46:06 +02:00
playlist_title = data.get('DATA').get('TITLE')
playlist_uploader = data.get('DATA').get('PARENT_USERNAME')
2014-09-12 07:25:58 +02:00
playlist_thumbnail = self._search_regex(
r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage,
'playlist thumbnail')
entries = []
2019-08-13 12:46:06 +02:00
for s in data.get('SONGS').get('data'):
2014-09-12 07:25:58 +02:00
formats = [{
'format_id': 'preview',
2019-08-13 12:46:06 +02:00
'url': s.get('MEDIA')[0].get('HREF'),
2014-09-12 07:25:58 +02:00
'preference': -100, # Only the first 30 seconds
'ext': 'mp3',
}]
self._sort_formats(formats)
artists = ', '.join(
2019-08-13 12:46:06 +02:00
orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
2014-09-12 07:25:58 +02:00
entries.append({
2019-08-13 12:46:06 +02:00
'id': s.get('SNG_ID'),
2014-09-12 07:25:58 +02:00
'duration': int_or_none(s.get('DURATION')),
2019-08-13 12:46:06 +02:00
'title': '%s - %s' % (artists, s.get('SNG_TITLE')),
'uploader': s.get('ART_NAME'),
'uploader_id': s.get('ART_ID'),
2014-09-12 07:25:58 +02:00
'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
'formats': formats,
})
return {
'_type': 'playlist',
'id': playlist_id,
'title': playlist_title,
'uploader': playlist_uploader,
'thumbnail': playlist_thumbnail,
'entries': entries,
}