X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fneteasemusic.py;h=15eca825ad9925ac4ab90902123edebc432c0500;hb=5c2266df4b9aeb7881ed8c026a038e2a25e43734;hp=ebed5d3b4928278617472da17d68594629cc78ff;hpb=af1fa6234e9623a1a09e66c24c0dedc6996645c9;p=youtube-dl diff --git a/youtube_dl/extractor/neteasemusic.py b/youtube_dl/extractor/neteasemusic.py index ebed5d3b4..15eca825a 100644 --- a/youtube_dl/extractor/neteasemusic.py +++ b/youtube_dl/extractor/neteasemusic.py @@ -2,15 +2,17 @@ from __future__ import unicode_literals from hashlib import md5 +from base64 import b64encode from datetime import datetime -import itertools import re from .common import InfoExtractor from ..compat import ( - compat_urllib_request, compat_urllib_parse, + compat_str, + compat_itertools_count, ) +from ..utils import sanitized_Request class NetEaseMusicBaseIE(InfoExtractor): @@ -20,14 +22,14 @@ class NetEaseMusicBaseIE(InfoExtractor): @classmethod def _encrypt(cls, dfsid): - salt_bytes = bytearray(str(cls._NETEASE_SALT)) - string_bytes = bytearray(str(dfsid)) + salt_bytes = bytearray(cls._NETEASE_SALT.encode('utf-8')) + string_bytes = bytearray(compat_str(dfsid).encode('ascii')) salt_len = len(salt_bytes) - for i in xrange(len(string_bytes)): + for i in range(len(string_bytes)): string_bytes[i] = string_bytes[i] ^ salt_bytes[i % salt_len] m = md5() - m.update(string_bytes) - result = m.digest().encode('base64')[:-1] + m.update(bytes(string_bytes)) + result = b64encode(m.digest()).decode('ascii') return result.replace('/', '_').replace('+', '-') @classmethod @@ -38,26 +40,30 @@ class NetEaseMusicBaseIE(InfoExtractor): if not details: continue formats.append({ - 'url': 'http://m1.music.126.net/%s/%s.%s' % + 'url': 'http://m5.music.126.net/%s/%s.%s' % (cls._encrypt(details['dfsId']), details['dfsId'], details['extension']), - 'ext': details['extension'], - 'abr': details['bitrate'] / 1000, - 'preference': details['bitrate'], + 'ext': details.get('extension'), + 'abr': details.get('bitrate', 0) / 1000, 'format_id': song_format, - 'filesize': details['size'], - 'asr': details['sr'] + 'filesize': details.get('size'), + 'asr': details.get('sr') }) return formats + @classmethod + def convert_milliseconds(cls, ms): + return int(round(ms / 1000.0)) + def query_api(self, endpoint, video_id, note): - req = compat_urllib_request.Request('%s%s' % (self._API_BASE, endpoint)) + req = sanitized_Request('%s%s' % (self._API_BASE, endpoint)) req.add_header('Referer', self._API_BASE) return self._download_json(req, video_id, note) class NetEaseMusicIE(NetEaseMusicBaseIE): IE_NAME = 'netease:song' + IE_DESC = '网易云音乐' _VALID_URL = r'https?://music\.163\.com/(#/)?song\?id=(?P[0-9]+)' _TESTS = [{ 'url': 'http://music.163.com/#/song?id=32102397', @@ -94,6 +100,19 @@ class NetEaseMusicIE(NetEaseMusicBaseIE): 'upload_date': '20080211', '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)', + } }] def _process_lyrics(self, lyrics_info): @@ -105,10 +124,9 @@ class NetEaseMusicIE(NetEaseMusicBaseIE): lyrics_expr = r'(\[[0-9]{2}:[0-9]{2}\.[0-9]{2,}\])([^\n]+)' original_ts_texts = re.findall(lyrics_expr, original) - translation_ts_dict = { - time_stamp: text for time_stamp, text in re.findall(lyrics_expr, translated) - } - + 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 @@ -130,22 +148,22 @@ class NetEaseMusicIE(NetEaseMusicBaseIE): self._sort_formats(formats) lyrics_info = self.query_api( - 'song/lyric?id=%s&lv=-1&tv=-1' % song_id, + '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('alias'): - alt_title = '/'.join(info.get('alias')) + if info.get('transNames'): + alt_title = '/'.join(info.get('transNames')) return { 'id': song_id, 'title': info['name'], 'alt_title': alt_title, 'creator': ' / '.join([artist['name'] for artist in info.get('artists', [])]), - 'timestamp': int(info.get('album', {}).get('publishTime')/1000), + 'timestamp': self.convert_milliseconds(info.get('album', {}).get('publishTime')), 'thumbnail': info.get('album', {}).get('picUrl'), - 'duration': int(info.get('duration', 0)/1000), + 'duration': self.convert_milliseconds(info.get('duration', 0)), 'description': lyrics, 'formats': formats, } @@ -153,6 +171,7 @@ class NetEaseMusicIE(NetEaseMusicBaseIE): 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 = { 'url': 'http://music.163.com/#/album?id=220780', @@ -167,7 +186,7 @@ class NetEaseMusicAlbumIE(NetEaseMusicBaseIE): album_id = self._match_id(url) info = self.query_api( - 'album/%s?id=%s' % (album_id, album_id), + 'album/%s?id=%s' % (album_id, album_id), album_id, 'Downloading album data')['album'] name = info['name'] @@ -182,6 +201,7 @@ class NetEaseMusicAlbumIE(NetEaseMusicBaseIE): class NetEaseMusicSingerIE(NetEaseMusicBaseIE): IE_NAME = 'netease:singer' + IE_DESC = '网易云音乐 - 歌手' _VALID_URL = r'https?://music\.163\.com/(#/)?artist\?id=(?P[0-9]+)' _TESTS = [{ 'note': 'Singer has aliases.', @@ -205,14 +225,14 @@ class NetEaseMusicSingerIE(NetEaseMusicBaseIE): singer_id = self._match_id(url) info = self.query_api( - 'artist/%s?id=%s' % (singer_id, singer_id), + 'artist/%s?id=%s' % (singer_id, singer_id), singer_id, '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 = '%s - %s' % (name, ';'.join(info['artist']['alias'])) entries = [ self.url_result('http://music.163.com/#/song?id=%s' % song['id'], @@ -224,6 +244,7 @@ class NetEaseMusicSingerIE(NetEaseMusicBaseIE): class NetEaseMusicListIE(NetEaseMusicBaseIE): IE_NAME = 'netease:playlist' + IE_DESC = '网易云音乐 - 歌单' _VALID_URL = r'https?://music\.163\.com/(#/)?(playlist|discover/toplist)\?id=(?P[0-9]+)' _TESTS = [{ 'url': 'http://music.163.com/#/playlist?id=79177352', @@ -248,14 +269,15 @@ class NetEaseMusicListIE(NetEaseMusicBaseIE): list_id = self._match_id(url) info = self.query_api( - 'playlist/detail?id=%s&lv=-1&tv=-1' % list_id, + 'playlist/detail?id=%s&lv=-1&tv=-1' % list_id, list_id, 'Downloading playlist data')['result'] name = info['name'] desc = info.get('description') if info.get('specialType') == 10: # is a chart/toplist - datestamp = datetime.fromtimestamp(info['updateTime']/1000).strftime('%Y-%m-%d') + datestamp = datetime.fromtimestamp( + self.convert_milliseconds(info['updateTime'])).strftime('%Y-%m-%d') name = '%s %s' % (name, datestamp) entries = [ @@ -268,6 +290,7 @@ class NetEaseMusicListIE(NetEaseMusicBaseIE): 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 = { 'url': 'http://music.163.com/#/mv?id=415350', @@ -289,7 +312,7 @@ class NetEaseMusicMvIE(NetEaseMusicBaseIE): mv_id, 'Downloading mv info')['data'] formats = [ - {'url': mv_url, 'ext': 'mp4', 'format_id': '%sp' % brs, 'preference': int(brs)} + {'url': mv_url, 'ext': 'mp4', 'format_id': '%sp' % brs, 'height': int(brs)} for brs, mv_url in info['brs'].items() ] self._sort_formats(formats) @@ -302,12 +325,13 @@ class NetEaseMusicMvIE(NetEaseMusicBaseIE): 'upload_date': info['publishTime'].replace('-', ''), 'formats': formats, 'thumbnail': info.get('cover'), - 'duration': int(info.get('duration', 0)/1000), + 'duration': self.convert_milliseconds(info.get('duration', 0)), } class NetEaseMusicProgramIE(NetEaseMusicBaseIE): IE_NAME = 'netease:program' + IE_DESC = '网易云音乐 - 电台节目' _VALID_URL = r'https?://music\.163\.com/(#/?)program\?id=(?P[0-9]+)' _TESTS = [{ 'url': 'http://music.163.com/#/program?id=10109055', @@ -317,7 +341,7 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE): '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': 1434179341, + 'timestamp': 1434179342, 'upload_date': '20150613', 'duration': 900, }, @@ -338,7 +362,7 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE): 'ext': 'mp3', 'title': '25岁，你是自在如风的少年<27°C>', 'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b', - 'timestamp': 1434450840, + 'timestamp': 1434450841, 'upload_date': '20150616', }, 'params': { @@ -361,7 +385,7 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE): self.to_screen( 'Downloading just the main audio %s because of --no-playlist' % info['mainSong']['id']) - + formats = self.extract_formats(info['mainSong']) self._sort_formats(formats) @@ -370,9 +394,9 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE): 'title': name, 'description': description, 'creator': info['dj']['brand'], - 'timestamp': int(info['createTime']/1000), + 'timestamp': self.convert_milliseconds(info['createTime']), 'thumbnail': info['coverUrl'], - 'duration': int(info.get('duration', 0)/1000), + 'duration': self.convert_milliseconds(info.get('duration', 0)), 'formats': formats, } @@ -392,6 +416,7 @@ class NetEaseMusicProgramIE(NetEaseMusicBaseIE): class NetEaseMusicDjRadioIE(NetEaseMusicBaseIE): IE_NAME = 'netease:djradio' + IE_DESC = '网易云音乐 - 电台' _VALID_URL = r'https?://music\.163\.com/(#/)?djradio\?id=(?P[0-9]+)' _TEST = { 'url': 'http://music.163.com/#/djradio?id=42', @@ -410,9 +435,9 @@ class NetEaseMusicDjRadioIE(NetEaseMusicBaseIE): name = None desc = None entries = [] - for offset in itertools.count(start=0, step=self._PAGE_SIZE): + for offset in compat_itertools_count(start=0, step=self._PAGE_SIZE): info = self.query_api( - 'dj/program/byradio?asc=false&limit=%d&radioId=%s&offset=%d' + 'dj/program/byradio?asc=false&limit=%d&radioId=%s&offset=%d' % (self._PAGE_SIZE, dj_id, offset), dj_id, 'Downloading dj programs - %d' % offset)