From 4c6039385466e4be3a0e20459e75886052653de7 Mon Sep 17 00:00:00 2001
From: Mamay Alexander <alexander@mamay.su>
Date: Mon, 9 Mar 2015 19:06:49 +0600
Subject: [PATCH] [YandexMusic] Add new extractor
---
youtube_dl/extractor/__init__.py | 5 ++
youtube_dl/extractor/yamusic.py | 104 +++++++++++++++++++++++++++++++
2 files changed, 109 insertions(+)
create mode 100644 youtube_dl/extractor/yamusic.py
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 14172ca56..2db938516 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -611,6 +611,11 @@ from .yahoo import (
YahooSearchIE,
)
from .yam import YamIE
+from .yamusic import (
+ YandexMusicTrackIE,
+ YandexMusicAlbumIE,
+ YandexMusicPlaylistIE,
+)
from .yesjapan import YesJapanIE
from .ynet import YnetIE
from .youjizz import YouJizzIE
diff --git a/youtube_dl/extractor/yamusic.py b/youtube_dl/extractor/yamusic.py
new file mode 100644
index 000000000..5af6df89d
--- /dev/null
+++ b/youtube_dl/extractor/yamusic.py
@@ -0,0 +1,104 @@
+# coding=utf-8
+from __future__ import unicode_literals
+
+import re
+import hashlib
+import time
+
+from .common import InfoExtractor
+
+class YandexMusicAlbumIE(InfoExtractor):
+ _VALID_URL = r'http://music.yandex.ru/album/(?P<id>\d+)'
+
+ def _get_track_url(self, storage_dir, track_id):
+ data = self._download_json('http://music.yandex.ru/api/v1.5/handlers/api-jsonp.jsx?requestId=2&nc=%d&action=getTrackSrc&p=download-info/%s/2.mp3' % (time.time(), storage_dir), track_id)
+
+ hsh = hashlib.md5()
+ hsh.update('XGRlBW9FXlekgbPrRHuSiA' + data['path'][1:] + data['s'])
+ hash = hsh.hexdigest()
+ storage = storage_dir.split('.')
+
+ return 'http://%s/get-mp3/%s/%s?track-id=%s&from=service-10-track&similarities-experiment=default' % (data['host'], hash, data['ts'] + data['path'], storage[1])
+
+ def _get_album_id_and_data(self, url):
+ matched = re.match(self._VALID_URL, url)
+ id = matched.group('id')
+
+ webpage = self._download_webpage(url, id)
+ data = self._parse_json(
+ self._search_regex(
+ r'var\s+Mu\s+=\s+(.+?);\s+<\/script>', webpage, 'player'),
+ id)
+ return id, data['pageData']
+
+ def _real_extract(self, url):
+
+ id, data = self._get_album_id_and_data(url)
+
+ entries = []
+
+ for track in data['volumes'][0]:
+ entries.append({
+ 'id': track['id'],
+ 'ext': 'mp3',
+ 'url': self._get_track_url(track['storageDir'], track['id']),
+ 'title': track['artists'][0]['name'] + ' - ' + track['title'],
+ })
+
+ return {
+ '_type': 'playlist',
+ 'entries': entries,
+ 'id': id,
+ 'title': data['title'],
+ }
+
+class YandexMusicPlaylistIE(YandexMusicAlbumIE):
+ _VALID_URL = r'http://music.yandex.ru/users/(?P<user_name>[^/]+)/playlists/(?P<id>\d+)'
+
+ def _real_extract(self, url):
+ id, data = self._get_album_id_and_data(url)
+ data = data['playlist']
+
+ entries = []
+
+ for track in data['tracks']:
+ entries.append({
+ 'id': track['id'],
+ 'ext': 'mp3',
+ 'url': self._get_track_url(track['storageDir'], track['id']),
+ 'title': track['artists'][0]['name'] + ' - ' + track['title'],
+ })
+
+ return {
+ '_type': 'playlist',
+ 'entries': entries,
+ 'id': id,
+ 'title': data['title'],
+ }
+
+class YandexMusicTrackIE(YandexMusicAlbumIE):
+ _VALID_URL = r'http://music.yandex.ru/album/(?P<album_id>\d+)/track/(?P<id>\d+)'
+ _TEST = {
+ 'url': 'http://music.yandex.ru/album/540508/track/4878838',
+ 'info_dict': {
+ 'id': '4878838',
+ 'ext': 'mp3',
+ 'title': 'Carlo Ambrosio - Gypsy Eyes 1',
+ }
+ }
+
+ def _real_extract(self, url):
+
+ id, data = self._get_album_id_and_data(url)
+
+ for track in data['volumes'][0]:
+ if track['id'] == id:
+ track_url = self._get_track_url(track['storageDir'], id)
+ break
+
+ return {
+ 'id': id,
+ 'ext': 'mp3',
+ 'url': track_url,
+ 'title': track['artists'][0]['name'] + ' - ' + track['title'],
+ }