aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/deezer.py
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2014-09-12 07:25:58 +0200
committerPhilipp Hagemeister <phihag@phihag.de>2014-09-13 05:47:07 +0200
commitda2e1f53e07bb24405bb9e27c58fa52fe0b58087 (patch)
tree1915df74e7e65583dfc8159ba911c1df1cc4edac /youtube_dl/extractor/deezer.py
parent473219a77888fc733626aa7edc77b2687ac9eed7 (diff)
[deezer] Add simple support
Diffstat (limited to 'youtube_dl/extractor/deezer.py')
-rw-r--r--youtube_dl/extractor/deezer.py80
1 files changed, 80 insertions, 0 deletions
diff --git a/youtube_dl/extractor/deezer.py b/youtube_dl/extractor/deezer.py
new file mode 100644
index 000000000..62c181529
--- /dev/null
+++ b/youtube_dl/extractor/deezer.py
@@ -0,0 +1,80 @@
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ int_or_none,
+ orderedSet,
+)
+
+
+class DeezerPlaylistIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?deezer\.com/playlist/(?P<id>[0-9]+)'
+ _TEST = {
+ 'url': 'http://www.deezer.com/playlist/176747451',
+ 'info_dict': {
+ 'id': '176747451',
+ 'title': 'Best!',
+ 'uploader': 'Anonymous',
+ 'thumbnail': 're:^https?://cdn-images.deezer.com/images/cover/.*\.jpg$',
+ },
+ 'playlist_count': 30,
+ }
+
+ 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)
+ data_json = self._search_regex(
+ r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n', webpage, 'data JSON')
+ data = json.loads(data_json)
+
+ playlist_title = data.get('DATA', {}).get('TITLE')
+ playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME')
+ playlist_thumbnail = self._search_regex(
+ r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage,
+ 'playlist thumbnail')
+
+ preview_pattern = self._search_regex(
+ r"var SOUND_PREVIEW_GATEWAY\s*=\s*'([^']+)';", webpage,
+ 'preview URL pattern', fatal=False)
+ entries = []
+ for s in data['SONGS']['data']:
+ puid = s['MD5_ORIGIN']
+ preview_video_url = preview_pattern.\
+ replace('{0}', puid[0]).\
+ replace('{1}', puid).\
+ replace('{2}', s['MEDIA_VERSION'])
+ formats = [{
+ 'format_id': 'preview',
+ 'url': preview_video_url,
+ 'preference': -100, # Only the first 30 seconds
+ 'ext': 'mp3',
+ }]
+ self._sort_formats(formats)
+ artists = ', '.join(
+ orderedSet(a['ART_NAME'] for a in s['ARTISTS']))
+ entries.append({
+ 'id': s['SNG_ID'],
+ 'duration': int_or_none(s.get('DURATION')),
+ 'title': '%s - %s' % (artists, s['SNG_TITLE']),
+ 'uploader': s['ART_NAME'],
+ 'uploader_id': s['ART_ID'],
+ '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,
+ }