From 47fe42e1ab3e182aacbc0c749b9a4f17f1b9dad2 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 9 Mar 2015 21:43:46 +0600 Subject: [PATCH] [yamusic] Improve, simplify, fix python3 issues and add tests --- youtube_dl/extractor/yamusic.py | 160 ++++++++++++++++++-------------- 1 file changed, 92 insertions(+), 68 deletions(-) diff --git a/youtube_dl/extractor/yamusic.py b/youtube_dl/extractor/yamusic.py index 5af6df89d..e25c0be44 100644 --- a/youtube_dl/extractor/yamusic.py +++ b/youtube_dl/extractor/yamusic.py @@ -3,102 +3,126 @@ from __future__ import unicode_literals import re import hashlib -import time from .common import InfoExtractor +from ..compat import compat_str +from ..utils import ( + int_or_none, + float_or_none, +) -class YandexMusicAlbumIE(InfoExtractor): - _VALID_URL = r'http://music.yandex.ru/album/(?P\d+)' +class YandexMusicBaseIE(InfoExtractor): 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) + data = self._download_json( + 'http://music.yandex.ru/api/v1.5/handlers/api-jsonp.jsx?action=getTrackSrc&p=download-info/%s' + % storage_dir, + track_id, 'Downloading track location JSON') - hsh = hashlib.md5() - hsh.update('XGRlBW9FXlekgbPrRHuSiA' + data['path'][1:] + data['s']) - hash = hsh.hexdigest() + key = hashlib.md5(('XGRlBW9FXlekgbPrRHuSiA' + data['path'][1:] + data['s']).encode('utf-8')).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]) + return ('http://%s/get-mp3/%s/%s?track-id=%s&from=service-10-track&similarities-experiment=default' + % (data['host'], key, 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') + def _get_track_info(self, track): + return { + 'id': track['id'], + 'ext': 'mp3', + 'url': self._get_track_url(track['storageDir'], track['id']), + 'title': '%s - %s' % (track['artists'][0]['name'], track['title']), + 'filesize': int_or_none(track.get('fileSize')), + 'duration': float_or_none(track.get('durationMs'), 1000), + } - 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'] + +class YandexMusicTrackIE(YandexMusicBaseIE): + IE_NAME = 'yandexmusic:track' + IE_DESC = 'Яндекс.Музыка - Трек' + _VALID_URL = r'https?://music\.yandex\.ru/album/(?P\d+)/track/(?P\d+)' + + _TEST = { + 'url': 'http://music.yandex.ru/album/540508/track/4878838', + 'md5': 'f496818aa2f60b6c0062980d2e00dc20', + 'info_dict': { + 'id': '4878838', + 'ext': 'mp3', + 'title': 'Carlo Ambrosio - Gypsy Eyes 1', + 'filesize': 4628061, + 'duration': 193.04, + } + } def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + album_id, track_id = mobj.group('album_id'), mobj.group('id') - id, data = self._get_album_id_and_data(url) + track = self._download_json( + 'http://music.yandex.ru/handlers/track.jsx?track=%s:%s' % (track_id, album_id), + track_id, 'Downloading track JSON')['track'] - entries = [] + return self._get_track_info(track) - 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 YandexMusicAlbumIE(YandexMusicBaseIE): + IE_NAME = 'yandexmusic:album' + IE_DESC = 'Яндекс.Музыка - Альбом' + _VALID_URL = r'https?://music\.yandex\.ru/album/(?P\d+)' -class YandexMusicPlaylistIE(YandexMusicAlbumIE): - _VALID_URL = r'http://music.yandex.ru/users/(?P[^/]+)/playlists/(?P\d+)' + _TEST = { + 'url': 'http://music.yandex.ru/album/540508', + 'info_dict': { + 'id': '540508', + 'title': 'Carlo Ambrosio - Gypsy Soul (2009)', + }, + 'playlist_count': 50, + } def _real_extract(self, url): - id, data = self._get_album_id_and_data(url) - data = data['playlist'] + album_id = self._match_id(url) - entries = [] + album = self._download_json( + 'http://music.yandex.ru/handlers/album.jsx?album=%s' % album_id, + album_id, 'Downloading album JSON') - 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'], - }) + entries = [self._get_track_info(track) for track in album['volumes'][0]] + + title = '%s - %s' % (album['artists'][0]['name'], album['title']) + year = album.get('year') + if year: + title += ' (%s)' % year + + return self.playlist_result(entries, compat_str(album['id']), title) - return { - '_type': 'playlist', - 'entries': entries, - 'id': id, - 'title': data['title'], - } -class YandexMusicTrackIE(YandexMusicAlbumIE): - _VALID_URL = r'http://music.yandex.ru/album/(?P\d+)/track/(?P\d+)' +class YandexMusicPlaylistIE(YandexMusicBaseIE): + IE_NAME = 'yandexmusic:playlist' + IE_DESC = 'Яндекс.Музыка - Плейлист' + _VALID_URL = r'https?://music\.yandex\.ru/users/[^/]+/playlists/(?P\d+)' + _TEST = { - 'url': 'http://music.yandex.ru/album/540508/track/4878838', + 'url': 'http://music.yandex.ru/users/music.partners/playlists/1245', 'info_dict': { - 'id': '4878838', - 'ext': 'mp3', - 'title': 'Carlo Ambrosio - Gypsy Eyes 1', - } + 'id': '1245', + 'title': 'Что слушают Enter Shikari', + 'description': 'md5:3b9f27b0efbe53f2ee1e844d07155cc9', + }, + 'playlist_count': 6, } def _real_extract(self, url): + playlist_id = self._match_id(url) - id, data = self._get_album_id_and_data(url) + webpage = self._download_webpage(url, playlist_id) - for track in data['volumes'][0]: - if track['id'] == id: - track_url = self._get_track_url(track['storageDir'], id) - break + playlist = self._parse_json( + self._search_regex( + r'var\s+Mu\s*=\s*({.+?});\s*', webpage, 'player'), + playlist_id)['pageData']['playlist'] + + entries = [self._get_track_info(track) for track in playlist['tracks']] + + return self.playlist_result( + entries, compat_str(playlist_id), + playlist['title'], playlist.get('description')) - return { - 'id': id, - 'ext': 'mp3', - 'url': track_url, - 'title': track['artists'][0]['name'] + ' - ' + track['title'], - }