From f980df734cf5c0eaded2f7b38c6c60bccfeebb48 Mon Sep 17 00:00:00 2001 From: c-basalt <117849907+c-basalt@users.noreply.github.com> Date: Fri, 6 Oct 2023 18:31:33 -0400 Subject: [PATCH] [ie/neteasemusic] Fix extractors (#8181) Closes #4388 Authored by: c-basalt --- yt_dlp/extractor/neteasemusic.py | 575 +++++++++++++++++-------------- 1 file changed, 312 insertions(+), 263 deletions(-) diff --git a/yt_dlp/extractor/neteasemusic.py b/yt_dlp/extractor/neteasemusic.py index 5b7307bc8..68bfcb6ba 100644 --- a/yt_dlp/extractor/neteasemusic.py +++ b/yt_dlp/extractor/neteasemusic.py @@ -2,105 +2,74 @@ import json import re import time -from base64 import b64encode -from binascii import hexlify -from datetime import datetime from hashlib import md5 from random import randint from .common import InfoExtractor from ..aes import aes_ecb_encrypt, pkcs7_padding -from ..compat import compat_urllib_parse_urlencode -from ..networking import Request from ..utils import ( ExtractorError, - bytes_to_intlist, - error_to_compat_str, - float_or_none, int_or_none, - intlist_to_bytes, - try_get, + join_nonempty, + str_or_none, + strftime_or_none, + traverse_obj, + unified_strdate, + url_or_none, + urljoin, + variadic, ) class NetEaseMusicBaseIE(InfoExtractor): _FORMATS = ['bMusic', 'mMusic', 'hMusic'] - _NETEASE_SALT = '3go8&$8*3*3h0k(2)2' _API_BASE = 'http://music.163.com/api/' + _GEO_BYPASS = False - @classmethod - def _encrypt(cls, dfsid): - salt_bytes = bytearray(cls._NETEASE_SALT.encode('utf-8')) - string_bytes = bytearray(str(dfsid).encode('ascii')) - salt_len = len(salt_bytes) - for i in range(len(string_bytes)): - string_bytes[i] = string_bytes[i] ^ salt_bytes[i % salt_len] - m = md5() - m.update(bytes(string_bytes)) - result = b64encode(m.digest()).decode('ascii') - return result.replace('/', '_').replace('+', '-') + @staticmethod + def kilo_or_none(value): + return int_or_none(value, scale=1000) - def make_player_api_request_data_and_headers(self, song_id, bitrate): - KEY = b'e82ckenh8dichen8' - URL = '/api/song/enhance/player/url' - now = int(time.time() * 1000) - rand = randint(0, 1000) - cookie = { - 'osver': None, - 'deviceId': None, + def _create_eapi_cipher(self, api_path, query_body, cookies): + request_text = json.dumps({**query_body, 'header': cookies}, separators=(',', ':')) + + message = f'nobody{api_path}use{request_text}md5forencrypt'.encode('latin1') + msg_digest = md5(message).hexdigest() + + data = pkcs7_padding(list(str.encode( + f'{api_path}-36cd479b6b5-{request_text}-36cd479b6b5-{msg_digest}'))) + encrypted = bytes(aes_ecb_encrypt(data, list(b'e82ckenh8dichen8'))) + return f'params={encrypted.hex().upper()}'.encode() + + def _download_eapi_json(self, path, video_id, query_body, headers={}, **kwargs): + cookies = { + 'osver': 'undefined', + 'deviceId': 'undefined', 'appver': '8.0.0', 'versioncode': '140', - 'mobilename': None, + 'mobilename': 'undefined', 'buildver': '1623435496', 'resolution': '1920x1080', '__csrf': '', 'os': 'pc', - 'channel': None, - 'requestId': '{0}_{1:04}'.format(now, rand), + 'channel': 'undefined', + 'requestId': f'{int(time.time() * 1000)}_{randint(0, 1000):04}', + **traverse_obj(self._get_cookies(self._API_BASE), { + 'MUSIC_U': ('MUSIC_U', {lambda i: i.value}), + }) } - request_text = json.dumps( - {'ids': '[{0}]'.format(song_id), 'br': bitrate, 'header': cookie}, - separators=(',', ':')) - message = 'nobody{0}use{1}md5forencrypt'.format( - URL, request_text).encode('latin1') - msg_digest = md5(message).hexdigest() - - data = '{0}-36cd479b6b5-{1}-36cd479b6b5-{2}'.format( - URL, request_text, msg_digest) - data = pkcs7_padding(bytes_to_intlist(data)) - encrypted = intlist_to_bytes(aes_ecb_encrypt(data, bytes_to_intlist(KEY))) - encrypted_params = hexlify(encrypted).decode('ascii').upper() - - cookie = '; '.join( - ['{0}={1}'.format(k, v if v is not None else 'undefined') - for [k, v] in cookie.items()]) - - headers = { - 'User-Agent': self.extractor.get_param('http_headers')['User-Agent'], - 'Content-Type': 'application/x-www-form-urlencoded', - 'Referer': 'https://music.163.com', - 'Cookie': cookie, - } - return ('params={0}'.format(encrypted_params), headers) + return self._download_json( + urljoin('https://interface3.music.163.com/', f'/eapi{path}'), video_id, + data=self._create_eapi_cipher(f'/api{path}', query_body, cookies), headers={ + 'Referer': 'https://music.163.com', + 'Cookie': '; '.join([f'{k}={v}' for k, v in cookies.items()]), + **headers, + }, **kwargs) def _call_player_api(self, song_id, bitrate): - url = 'https://interface3.music.163.com/eapi/song/enhance/player/url' - data, headers = self.make_player_api_request_data_and_headers(song_id, bitrate) - try: - msg = 'empty result' - result = self._download_json( - url, song_id, data=data.encode('ascii'), headers=headers) - if result: - return result - except ExtractorError as e: - if type(e.cause) in (ValueError, TypeError): - # JSON load failure - raise - except Exception as e: - msg = error_to_compat_str(e) - self.report_warning('%s API call (%s) failed: %s' % ( - song_id, bitrate, msg)) - return {} + return self._download_eapi_json( + '/song/enhance/player/url', song_id, {'ids': f'[{song_id}]', 'br': bitrate}, + note=f'Downloading song URL info: bitrate {bitrate}') def extract_formats(self, info): err = 0 @@ -110,45 +79,50 @@ def extract_formats(self, info): details = info.get(song_format) if not details: continue - bitrate = int_or_none(details.get('bitrate')) or 999000 - data = self._call_player_api(song_id, bitrate) - for song in try_get(data, lambda x: x['data'], list) or []: - song_url = try_get(song, lambda x: x['url']) - if not song_url: - continue + for song in traverse_obj(self._call_player_api(song_id, bitrate), ('data', lambda _, v: url_or_none(v['url']))): + song_url = song['url'] if self._is_valid_url(song_url, info['id'], 'song'): formats.append({ 'url': song_url, - 'ext': details.get('extension'), - 'abr': float_or_none(song.get('br'), scale=1000), 'format_id': song_format, - 'filesize': int_or_none(song.get('size')), - 'asr': int_or_none(details.get('sr')), + 'asr': traverse_obj(details, ('sr', {int_or_none})), + **traverse_obj(song, { + 'ext': ('type', {str}), + 'abr': ('br', {self.kilo_or_none}), + 'filesize': ('size', {int_or_none}), + }), }) elif err == 0: - err = try_get(song, lambda x: x['code'], int) + err = traverse_obj(song, ('code', {int})) or 0 if not formats: - msg = 'No media links found' if err != 0 and (err < 200 or err >= 400): - raise ExtractorError( - '%s (site code %d)' % (msg, err, ), expected=True) + raise ExtractorError(f'No media links found (site code {err})', expected=True) else: self.raise_geo_restricted( - msg + ': probably this video is not available from your location due to geo restriction.', - countries=['CN']) - + 'No media links found: probably due to geo restriction.', countries=['CN']) return formats - @classmethod - def convert_milliseconds(cls, ms): - return int(round(ms / 1000.0)) - def query_api(self, endpoint, video_id, note): - req = Request('%s%s' % (self._API_BASE, endpoint)) - req.headers['Referer'] = self._API_BASE - return self._download_json(req, video_id, note) + result = self._download_json( + f'{self._API_BASE}{endpoint}', video_id, note, headers={'Referer': self._API_BASE}) + code = traverse_obj(result, ('code', {int})) + message = traverse_obj(result, ('message', {str})) or '' + if code == -462: + self.raise_login_required(f'Login required to download: {message}') + elif code != 200: + raise ExtractorError(f'Failed to get meta info: {code} {message}') + return result + + def _get_entries(self, songs_data, entry_keys=None, id_key='id', name_key='name'): + for song in traverse_obj(songs_data, ( + *variadic(entry_keys, (str, bytes, dict, set)), + lambda _, v: int_or_none(v[id_key]) is not None)): + song_id = str(song[id_key]) + yield self.url_result( + f'http://music.163.com/#/song?id={song_id}', NetEaseMusicIE, + song_id, traverse_obj(song, (name_key, {str}))) class NetEaseMusicIE(NetEaseMusicBaseIE): @@ -156,16 +130,18 @@ class NetEaseMusicIE(NetEaseMusicBaseIE): IE_DESC = '网易云音乐' _VALID_URL = r'https?://(y\.)?music\.163\.com/(?:[#m]/)?song\?.*?\bid=(?P[0-9]+)' _TESTS = [{ - 'url': 'http://music.163.com/#/song?id=32102397', - 'md5': '3e909614ce09b1ccef4a3eb205441190', + 'url': 'https://music.163.com/#/song?id=548648087', 'info_dict': { - 'id': '32102397', + 'id': '548648087', 'ext': 'mp3', - 'title': 'Bad Blood', - 'creator': 'Taylor Swift / Kendrick Lamar', - 'upload_date': '20150516', - 'timestamp': 1431792000, - 'description': 'md5:25fc5f27e47aad975aa6d36382c7833c', + 'title': '戒烟 (Live)', + 'creator': '李荣浩 / 朱正廷 / 陈立农 / 尤长靖 / ONER灵超 / ONER木子洋 / 杨非同 / 陆定昊', + 'timestamp': 1522944000, + 'upload_date': '20180405', + 'description': 'md5:3650af9ee22c87e8637cb2dde22a765c', + 'subtitles': {'lyrics': [{'ext': 'lrc'}]}, + "duration": 256, + 'thumbnail': r're:^http.*\.jpg', }, }, { 'note': 'No lyrics.', @@ -176,21 +152,9 @@ class NetEaseMusicIE(NetEaseMusicBaseIE): 'title': 'Opus 28', 'creator': 'Dustin O\'Halloran', 'upload_date': '20080211', - 'description': 'md5:f12945b0f6e0365e3b73c5032e1b0ff4', 'timestamp': 1202745600, - }, - }, { - 'note': 'Has translated name.', - 'url': 'http://music.163.com/#/song?id=22735043', - 'info_dict': { - 'id': '22735043', - 'ext': 'mp3', - 'title': '소원을 말해봐 (Genie)', - 'creator': '少女时代', - 'description': 'md5:79d99cc560e4ca97e0c4d86800ee4184', - 'upload_date': '20100127', - 'timestamp': 1264608000, - 'alt_title': '说出愿望吧(Genie)', + 'duration': 263, + 'thumbnail': r're:^http.*\.jpg', }, }, { 'url': 'https://y.music.163.com/m/song?app_version=8.8.45&id=95670&uct2=sKnvS4+0YStsWkqsPhFijw%3D%3D&dlt=0846', @@ -203,59 +167,99 @@ class NetEaseMusicIE(NetEaseMusicBaseIE): 'upload_date': '19911130', 'timestamp': 691516800, 'description': 'md5:1ba2f911a2b0aa398479f595224f2141', + 'subtitles': {'lyrics': [{'ext': 'lrc'}]}, + 'duration': 268, + 'alt_title': '伴唱:现代人乐队 合唱:总政歌舞团', + 'thumbnail': r're:^http.*\.jpg', }, + }, { + 'url': 'http://music.163.com/#/song?id=32102397', + 'md5': '3e909614ce09b1ccef4a3eb205441190', + 'info_dict': { + 'id': '32102397', + 'ext': 'mp3', + 'title': 'Bad Blood', + 'creator': 'Taylor Swift / Kendrick Lamar', + 'upload_date': '20150516', + 'timestamp': 1431792000, + 'description': 'md5:21535156efb73d6d1c355f95616e285a', + 'subtitles': {'lyrics': [{'ext': 'lrc'}]}, + 'duration': 199, + 'thumbnail': r're:^http.*\.jpg', + }, + 'skip': 'Blocked outside Mainland China', + }, { + 'note': 'Has translated name.', + 'url': 'http://music.163.com/#/song?id=22735043', + 'info_dict': { + 'id': '22735043', + 'ext': 'mp3', + 'title': '소원을 말해봐 (Genie)', + 'creator': '少女时代', + 'upload_date': '20100127', + 'timestamp': 1264608000, + 'description': 'md5:03d1ffebec3139aa4bafe302369269c5', + 'subtitles': {'lyrics': [{'ext': 'lrc'}]}, + 'duration': 229, + 'alt_title': '说出愿望吧(Genie)', + 'thumbnail': r're:^http.*\.jpg', + }, + 'skip': 'Blocked outside Mainland China', }] def _process_lyrics(self, lyrics_info): - original = lyrics_info.get('lrc', {}).get('lyric') - translated = lyrics_info.get('tlyric', {}).get('lyric') + original = traverse_obj(lyrics_info, ('lrc', 'lyric', {str})) + translated = traverse_obj(lyrics_info, ('tlyric', 'lyric', {str})) + + if not original or original == '[99:00.00]纯音乐，请欣赏\n': + return None if not translated: - return original + return { + 'lyrics': [{'data': original, 'ext': 'lrc'}], + } lyrics_expr = r'(\[[0-9]{2}:[0-9]{2}\.[0-9]{2,}\])([^\n]+)' original_ts_texts = re.findall(lyrics_expr, original) - translation_ts_dict = dict( - (time_stamp, text) for time_stamp, text in re.findall(lyrics_expr, translated) - ) - lyrics = '\n'.join([ - '%s%s / %s' % (time_stamp, text, translation_ts_dict.get(time_stamp, '')) - for time_stamp, text in original_ts_texts - ]) - return lyrics + translation_ts_dict = dict(re.findall(lyrics_expr, translated)) + + merged = '\n'.join( + join_nonempty(f'{timestamp}{text}', translation_ts_dict.get(timestamp, ''), delim=' / ') + for timestamp, text in original_ts_texts) + + return { + 'lyrics_merged': [{'data': merged, 'ext': 'lrc'}], + 'lyrics': [{'data': original, 'ext': 'lrc'}], + 'lyrics_translated': [{'data': translated, 'ext': 'lrc'}], + } def _real_extract(self, url): song_id = self._match_id(url) - params = { - 'id': song_id, - 'ids': '[%s]' % song_id - } info = self.query_api( - 'song/detail?' + compat_urllib_parse_urlencode(params), - song_id, 'Downloading song info')['songs'][0] + f'song/detail?id={song_id}&ids=%5B{song_id}%5D', song_id, 'Downloading song info')['songs'][0] formats = self.extract_formats(info) - lyrics_info = self.query_api( - 'song/lyric?id=%s&lv=-1&tv=-1' % song_id, - song_id, 'Downloading lyrics data') - lyrics = self._process_lyrics(lyrics_info) - - alt_title = None - if info.get('transNames'): - alt_title = '/'.join(info.get('transNames')) + lyrics = self._process_lyrics(self.query_api( + f'song/lyric?id={song_id}&lv=-1&tv=-1', song_id, 'Downloading lyrics data')) + lyric_data = { + 'description': traverse_obj(lyrics, (('lyrics_merged', 'lyrics'), 0, 'data'), get_all=False), + 'subtitles': lyrics, + } if lyrics else {} return { 'id': song_id, - 'title': info['name'], - 'alt_title': alt_title, - 'creator': ' / '.join([artist['name'] for artist in info.get('artists', [])]), - 'timestamp': self.convert_milliseconds(info.get('album', {}).get('publishTime')), - 'thumbnail': info.get('album', {}).get('picUrl'), - 'duration': self.convert_milliseconds(info.get('duration', 0)), - 'description': lyrics, 'formats': formats, + 'alt_title': '/'.join(traverse_obj(info, (('transNames', 'alias'), ...))) or None, + 'creator': ' / '.join(traverse_obj(info, ('artists', ..., 'name'))) or None, + **lyric_data, + **traverse_obj(info, { + 'title': ('name', {str}), + 'timestamp': ('album', 'publishTime', {self.kilo_or_none}), + 'thumbnail': ('album', 'picUrl', {url_or_none}), + 'duration': ('duration', {self.kilo_or_none}), + }), } @@ -263,31 +267,44 @@ class NetEaseMusicAlbumIE(NetEaseMusicBaseIE): IE_NAME = 'netease:album' IE_DESC = '网易云音乐 - 专辑' _VALID_URL = r'https?://music\.163\.com/(#/)?album\?id=(?P[0-9]+)' - _TEST = { + _TESTS = [{ + 'url': 'https://music.163.com/#/album?id=133153666', + 'info_dict': { + 'id': '133153666', + 'title': '桃几的翻唱', + 'upload_date': '20210913', + 'description': '桃几2021年翻唱合集', + 'thumbnail': r're:^http.*\.jpg', + }, + 'playlist_mincount': 13, + }, { 'url': 'http://music.163.com/#/album?id=220780', 'info_dict': { 'id': '220780', - 'title': 'B\'day', + 'title': 'B\'Day', + 'upload_date': '20060904', + 'description': 'md5:71a74e1d8f392d88cf1bbe48879ad0b0', + 'thumbnail': r're:^http.*\.jpg', }, 'playlist_count': 23, - 'skip': 'Blocked outside Mainland China', - } + }] def _real_extract(self, url): album_id = self._match_id(url) + webpage = self._download_webpage(f'https://music.163.com/album?id={album_id}', album_id) - info = self.query_api( - 'album/%s?id=%s' % (album_id, album_id), - album_id, 'Downloading album data')['album'] - - name = info['name'] - desc = info.get('description') - entries = [ - self.url_result('http://music.163.com/#/song?id=%s' % song['id'], - 'NetEaseMusic', song['id']) - for song in info['songs'] - ] - return self.playlist_result(entries, album_id, name, desc) + songs = self._search_json( + r']+\bid="song-list-pre-data"[^>]*>', webpage, 'metainfo', album_id, + end_pattern=r'', contains_pattern=r'\[(?s:.+)\]') + metainfo = { + 'title': self._og_search_property('title', webpage, 'title', fatal=False), + 'description': self._html_search_regex( + (rf']+\bid="album-desc-{suffix}"[^>]*>(.*?)' for suffix in ('more', 'dot')), + webpage, 'description', flags=re.S, fatal=False), + 'thumbnail': self._og_search_property('image', webpage, 'thumbnail', fatal=False), + 'upload_date': unified_strdate(self._html_search_meta('music:release_date', webpage, 'date', fatal=False)), + } + return self.playlist_result(self._get_entries(songs), album_id, **metainfo) class NetEaseMusicSingerIE(NetEaseMusicBaseIE): @@ -299,10 +316,9 @@ class NetEaseMusicSingerIE(NetEaseMusicBaseIE): 'url': 'http://music.163.com/#/artist?id=10559', 'info_dict': { 'id': '10559', - 'title': '张惠妹 - aMEI;阿密特', + 'title': '张惠妹 - aMEI;阿妹;阿密特', }, 'playlist_count': 50, - 'skip': 'Blocked outside Mainland China', }, { 'note': 'Singer has translated name.', 'url': 'http://music.163.com/#/artist?id=124098', @@ -311,28 +327,28 @@ class NetEaseMusicSingerIE(NetEaseMusicBaseIE): 'title': '李昇基 - 이승기', }, 'playlist_count': 50, - 'skip': 'Blocked outside Mainland China', + }, { + 'note': 'Singer with both translated and alias', + 'url': 'https://music.163.com/#/artist?id=159692', + 'info_dict': { + 'id': '159692', + 'title': '初音ミク - 初音未来;Hatsune Miku', + }, + 'playlist_count': 50, }] def _real_extract(self, url): singer_id = self._match_id(url) info = self.query_api( - 'artist/%s?id=%s' % (singer_id, singer_id), - singer_id, 'Downloading singer data') + f'artist/{singer_id}?id={singer_id}', singer_id, note='Downloading singer data') - name = info['artist']['name'] - if info['artist']['trans']: - name = '%s - %s' % (name, info['artist']['trans']) - if info['artist']['alias']: - name = '%s - %s' % (name, ';'.join(info['artist']['alias'])) + name = join_nonempty( + traverse_obj(info, ('artist', 'name', {str})), + join_nonempty(*traverse_obj(info, ('artist', ('trans', ('alias', ...)), {str})), delim=';'), + delim=' - ') - entries = [ - self.url_result('http://music.163.com/#/song?id=%s' % song['id'], - 'NetEaseMusic', song['id']) - for song in info['hotSongs'] - ] - return self.playlist_result(entries, singer_id, name) + return self.playlist_result(self._get_entries(info, 'hotSongs'), singer_id, name) class NetEaseMusicListIE(NetEaseMusicBaseIE): @@ -344,10 +360,28 @@ class NetEaseMusicListIE(NetEaseMusicBaseIE): 'info_dict': { 'id': '79177352', 'title': 'Billboard 2007 Top 100', - 'description': 'md5:12fd0819cab2965b9583ace0f8b7b022' + 'description': 'md5:12fd0819cab2965b9583ace0f8b7b022', + 'tags': ['欧美'], + 'uploader': '浑然破灭', + 'uploader_id': '67549805', + 'timestamp': int, + 'upload_date': r're:\d{8}', }, - 'playlist_count': 99, - 'skip': 'Blocked outside Mainland China', + 'playlist_mincount': 95, + }, { + 'note': 'Toplist/Charts sample', + 'url': 'https://music.163.com/#/discover/toplist?id=60198', + 'info_dict': { + 'id': '60198', + 'title': 're:美国Billboard榜 [0-9]{4}-[0-9]{2}-[0-9]{2}', + 'description': '美国Billboard排行榜', + 'tags': ['流行', '欧美', '榜单'], + 'uploader': 'Billboard公告牌', + 'uploader_id': '48171', + 'timestamp': int, + 'upload_date': r're:\d{8}', + }, + 'playlist_count': 100, }, { 'note': 'Toplist/Charts sample', 'url': 'http://music.163.com/#/discover/toplist?id=3733003', @@ -363,64 +397,86 @@ class NetEaseMusicListIE(NetEaseMusicBaseIE): def _real_extract(self, url): list_id = self._match_id(url) - info = self.query_api( - 'playlist/detail?id=%s&lv=-1&tv=-1' % list_id, - list_id, 'Downloading playlist data')['result'] + info = self._download_eapi_json( + '/v3/playlist/detail', list_id, + {'id': list_id, 't': '-1', 'n': '500', 's': '0'}, + note="Downloading playlist info") - name = info['name'] - desc = info.get('description') + metainfo = traverse_obj(info, ('playlist', { + 'title': ('name', {str}), + 'description': ('description', {str}), + 'tags': ('tags', ..., {str}), + 'uploader': ('creator', 'nickname', {str}), + 'uploader_id': ('creator', 'userId', {str_or_none}), + 'timestamp': ('updateTime', {self.kilo_or_none}), + })) + if traverse_obj(info, ('playlist', 'specialType')) == 10: + metainfo['title'] = f'{metainfo.get("title")} {strftime_or_none(metainfo.get("timestamp"), "%Y-%m-%d")}' - if info.get('specialType') == 10: # is a chart/toplist - datestamp = datetime.fromtimestamp( - self.convert_milliseconds(info['updateTime'])).strftime('%Y-%m-%d') - name = '%s %s' % (name, datestamp) - - entries = [ - self.url_result('http://music.163.com/#/song?id=%s' % song['id'], - 'NetEaseMusic', song['id']) - for song in info['tracks'] - ] - return self.playlist_result(entries, list_id, name, desc) + return self.playlist_result(self._get_entries(info, ('playlist', 'tracks')), list_id, **metainfo) class NetEaseMusicMvIE(NetEaseMusicBaseIE): IE_NAME = 'netease:mv' IE_DESC = '网易云音乐 - MV' _VALID_URL = r'https?://music\.163\.com/(#/)?mv\?id=(?P[0-9]+)' - _TEST = { + _TESTS = [{ + 'url': 'https://music.163.com/#/mv?id=10958064', + 'info_dict': { + 'id': '10958064', + 'ext': 'mp4', + 'title': '交换余生', + 'description': 'md5:e845872cff28820642a2b02eda428fea', + 'creator': '林俊杰', + 'upload_date': '20200916', + 'thumbnail': r're:http.*\.jpg', + 'duration': 364, + 'view_count': int, + 'like_count': int, + 'comment_count': int, + }, + }, { 'url': 'http://music.163.com/#/mv?id=415350', 'info_dict': { 'id': '415350', 'ext': 'mp4', 'title': '이럴거면 그러지말지', 'description': '白雅言自作曲唱甜蜜爱情', - 'creator': '白雅言', + 'creator': '白娥娟', 'upload_date': '20150520', + 'thumbnail': r're:http.*\.jpg', + 'duration': 216, + 'view_count': int, + 'like_count': int, + 'comment_count': int, }, - 'skip': 'Blocked outside Mainland China', - } + }] def _real_extract(self, url): mv_id = self._match_id(url) info = self.query_api( - 'mv/detail?id=%s&type=mp4' % mv_id, - mv_id, 'Downloading mv info')['data'] + f'mv/detail?id={mv_id}&type=mp4', mv_id, 'Downloading mv info')['data'] formats = [ - {'url': mv_url, 'ext': 'mp4', 'format_id': '%sp' % brs, 'height': int(brs)} + {'url': mv_url, 'ext': 'mp4', 'format_id': f'{brs}p', 'height': int_or_none(brs)} for brs, mv_url in info['brs'].items() ] return { 'id': mv_id, - 'title': info['name'], - 'description': info.get('desc') or info.get('briefDesc'), - 'creator': info['artistName'], - 'upload_date': info['publishTime'].replace('-', ''), 'formats': formats, - 'thumbnail': info.get('cover'), - 'duration': self.convert_milliseconds(info.get('duration', 0)), + **traverse_obj(info, { + 'title': ('name', {str}), + 'description': (('desc', 'briefDesc'), {str}, {lambda x: x or None}), + 'creator': ('artistName', {str}), + 'upload_date': ('publishTime', {unified_strdate}), + 'thumbnail': ('cover', {url_or_none}), + 'duration': ('duration', {self.kilo_or_none}), + 'view_count': ('playCount', {int_or_none}), + 'like_count': ('likeCount', {int_or_none}), + 'comment_count': ('commentCount', {int_or_none}), + }, get_all=False), } @@ -431,75 +487,74 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE): _TESTS = [{ 'url': 'http://music.163.com/#/program?id=10109055', 'info_dict': { - 'id': '10109055', + 'id': '32593346', 'ext': 'mp3', 'title': '不丹足球背后的故事', 'description': '喜马拉雅人的足球梦 ...', 'creator': '大话西藏', - 'timestamp': 1434179342, + 'timestamp': 1434179287, 'upload_date': '20150613', + 'thumbnail': r're:http.*\.jpg', 'duration': 900, }, - 'skip': 'Blocked outside Mainland China', }, { 'note': 'This program has accompanying songs.', 'url': 'http://music.163.com/#/program?id=10141022', 'info_dict': { 'id': '10141022', - 'title': '25岁，你是自在如风的少年<27°C>', + 'title': '滚滚电台的有声节目', 'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b', + 'creator': '滚滚电台ORZ', + 'timestamp': 1434450733, + 'upload_date': '20150616', + 'thumbnail': r're:http.*\.jpg', }, 'playlist_count': 4, - 'skip': 'Blocked outside Mainland China', }, { 'note': 'This program has accompanying songs.', 'url': 'http://music.163.com/#/program?id=10141022', 'info_dict': { - 'id': '10141022', + 'id': '32647209', 'ext': 'mp3', - 'title': '25岁，你是自在如风的少年<27°C>', + 'title': '滚滚电台的有声节目', 'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b', - 'timestamp': 1434450841, + 'creator': '滚滚电台ORZ', + 'timestamp': 1434450733, 'upload_date': '20150616', + 'thumbnail': r're:http.*\.jpg', + 'duration': 1104, }, 'params': { 'noplaylist': True }, - 'skip': 'Blocked outside Mainland China', }] def _real_extract(self, url): program_id = self._match_id(url) info = self.query_api( - 'dj/program/detail?id=%s' % program_id, - program_id, 'Downloading program info')['program'] + f'dj/program/detail?id={program_id}', program_id, note='Downloading program info')['program'] - name = info['name'] - description = info['description'] + metainfo = traverse_obj(info, { + 'title': ('name', {str}), + 'description': ('description', {str}), + 'creator': ('dj', 'brand', {str}), + 'thumbnail': ('coverUrl', {url_or_none}), + 'timestamp': ('createTime', {self.kilo_or_none}), + }) if not self._yes_playlist(info['songs'] and program_id, info['mainSong']['id']): formats = self.extract_formats(info['mainSong']) return { - 'id': info['mainSong']['id'], - 'title': name, - 'description': description, - 'creator': info['dj']['brand'], - 'timestamp': self.convert_milliseconds(info['createTime']), - 'thumbnail': info['coverUrl'], - 'duration': self.convert_milliseconds(info.get('duration', 0)), + 'id': str(info['mainSong']['id']), 'formats': formats, + 'duration': traverse_obj(info, ('mainSong', 'duration', {self.kilo_or_none})), + **metainfo, } - song_ids = [info['mainSong']['id']] - song_ids.extend([song['id'] for song in info['songs']]) - entries = [ - self.url_result('http://music.163.com/#/song?id=%s' % song_id, - 'NetEaseMusic', song_id) - for song_id in song_ids - ] - return self.playlist_result(entries, program_id, name, description) + songs = traverse_obj(info, (('mainSong', ('songs', ...)),)) + return self.playlist_result(self._get_entries(songs), program_id, **metainfo) class NetEaseMusicDjRadioIE(NetEaseMusicBaseIE): @@ -511,38 +566,32 @@ class NetEaseMusicDjRadioIE(NetEaseMusicBaseIE): 'info_dict': { 'id': '42', 'title': '声音蔓延', - 'description': 'md5:766220985cbd16fdd552f64c578a6b15' + 'description': 'md5:c7381ebd7989f9f367668a5aee7d5f08' }, 'playlist_mincount': 40, - 'skip': 'Blocked outside Mainland China', } _PAGE_SIZE = 1000 def _real_extract(self, url): dj_id = self._match_id(url) - name = None - desc = None + metainfo = {} entries = [] for offset in itertools.count(start=0, step=self._PAGE_SIZE): info = self.query_api( - 'dj/program/byradio?asc=false&limit=%d&radioId=%s&offset=%d' - % (self._PAGE_SIZE, dj_id, offset), - dj_id, 'Downloading dj programs - %d' % offset) + f'dj/program/byradio?asc=false&limit={self._PAGE_SIZE}&radioId={dj_id}&offset={offset}', + dj_id, note=f'Downloading dj programs - {offset}') - entries.extend([ - self.url_result( - 'http://music.163.com/#/program?id=%s' % program['id'], - 'NetEaseMusicProgram', program['id']) - for program in info['programs'] - ]) - - if name is None: - radio = info['programs'][0]['radio'] - name = radio['name'] - desc = radio['desc'] + entries.extend(self.url_result( + f'http://music.163.com/#/program?id={program["id"]}', NetEaseMusicProgramIE, + program['id'], program.get('name')) for program in info['programs']) + if not metainfo: + metainfo = traverse_obj(info, ('programs', 0, 'radio', { + 'title': ('name', {str}), + 'description': ('desc', {str}), + })) if not info['more']: break - return self.playlist_result(entries, dj_id, name, desc) + return self.playlist_result(entries, dj_id, **metainfo)