From af1fa6234e9623a1a09e66c24c0dedc6996645c9 Mon Sep 17 00:00:00 2001 From: ping Date: Sun, 21 Jun 2015 11:12:31 +0800 Subject: [PATCH 1/7] [neteasemusic] Add new extractor for music.163.com --- youtube_dl/extractor/__init__.py | 9 + youtube_dl/extractor/neteasemusic.py | 434 +++++++++++++++++++++++++++ 2 files changed, 443 insertions(+) create mode 100644 youtube_dl/extractor/neteasemusic.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 6c548d8e9..c8692ffa9 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -339,6 +339,15 @@ from .ndtv import NDTVIE from .netzkino import NetzkinoIE from .nerdcubed import NerdCubedFeedIE from .nerdist import NerdistIE +from .neteasemusic import ( + NetEaseMusicIE, + NetEaseMusicAlbumIE, + NetEaseMusicSingerIE, + NetEaseMusicListIE, + NetEaseMusicMvIE, + NetEaseMusicProgramIE, + NetEaseMusicDjRadioIE, +) from .newgrounds import NewgroundsIE from .newstube import NewstubeIE from .nextmedia import ( diff --git a/youtube_dl/extractor/neteasemusic.py b/youtube_dl/extractor/neteasemusic.py new file mode 100644 index 000000000..ebed5d3b4 --- /dev/null +++ b/youtube_dl/extractor/neteasemusic.py @@ -0,0 +1,434 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from hashlib import md5 +from datetime import datetime +import itertools +import re + +from .common import InfoExtractor +from ..compat import ( + compat_urllib_request, + compat_urllib_parse, +) + + +class NetEaseMusicBaseIE(InfoExtractor): + _FORMATS = ['bMusic', 'mMusic', 'hMusic'] + _NETEASE_SALT = '3go8&$8*3*3h0k(2)2' + _API_BASE = 'http://music.163.com/api/' + + @classmethod + def _encrypt(cls, dfsid): + salt_bytes = bytearray(str(cls._NETEASE_SALT)) + string_bytes = bytearray(str(dfsid)) + salt_len = len(salt_bytes) + for i in xrange(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] + return result.replace('/', '_').replace('+', '-') + + @classmethod + def extract_formats(cls, info): + formats = [] + for song_format in cls._FORMATS: + details = info.get(song_format) + if not details: + continue + formats.append({ + 'url': 'http://m1.music.126.net/%s/%s.%s' % + (cls._encrypt(details['dfsId']), details['dfsId'], + details['extension']), + 'ext': details['extension'], + 'abr': details['bitrate'] / 1000, + 'preference': details['bitrate'], + 'format_id': song_format, + 'filesize': details['size'], + 'asr': details['sr'] + }) + return formats + + def query_api(self, endpoint, video_id, note): + req = compat_urllib_request.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' + _VALID_URL = r'https?://music\.163\.com/(#/)?song\?id=(?P[0-9]+)' + _TESTS = [{ + 'url': 'http://music.163.com/#/song?id=32102397', + 'md5': 'f2e97280e6345c74ba9d5677dd5dcb45', + 'info_dict': { + 'id': '32102397', + 'ext': 'mp3', + 'title': 'Bad Blood (feat. Kendrick Lamar)', + 'creator': 'Taylor Swift / Kendrick Lamar', + 'upload_date': '20150517', + 'timestamp': 1431878400, + 'description': 'md5:a10a54589c2860300d02e1de821eb2ef', + }, + }, { + 'note': 'No lyrics translation.', + 'url': 'http://music.163.com/#/song?id=29822014', + 'info_dict': { + 'id': '29822014', + 'ext': 'mp3', + 'title': '听见下雨的声音', + 'creator': '周杰伦', + 'upload_date': '20141225', + 'timestamp': 1419523200, + 'description': 'md5:a4d8d89f44656af206b7b2555c0bce6c', + }, + }, { + 'note': 'No lyrics.', + 'url': 'http://music.163.com/song?id=17241424', + 'info_dict': { + 'id': '17241424', + 'ext': 'mp3', + 'title': 'Opus 28', + 'creator': 'Dustin O\'Halloran', + 'upload_date': '20080211', + 'timestamp': 1202745600, + }, + }] + + def _process_lyrics(self, lyrics_info): + original = lyrics_info.get('lrc', {}).get('lyric') + translated = lyrics_info.get('tlyric', {}).get('lyric') + + if not translated: + return original + + 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) + } + + 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 + + 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] + + formats = self.extract_formats(info) + self._sort_formats(formats) + + 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('alias'): + alt_title = '/'.join(info.get('alias')) + + 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), + 'thumbnail': info.get('album', {}).get('picUrl'), + 'duration': int(info.get('duration', 0)/1000), + 'description': lyrics, + 'formats': formats, + } + + +class NetEaseMusicAlbumIE(NetEaseMusicBaseIE): + IE_NAME = 'netease:album' + _VALID_URL = r'https?://music\.163\.com/(#/)?album\?id=(?P[0-9]+)' + _TEST = { + 'url': 'http://music.163.com/#/album?id=220780', + 'info_dict': { + 'id': '220780', + 'title': 'B\'day', + }, + 'playlist_count': 23, + } + + def _real_extract(self, url): + album_id = self._match_id(url) + + 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) + + +class NetEaseMusicSingerIE(NetEaseMusicBaseIE): + IE_NAME = 'netease:singer' + _VALID_URL = r'https?://music\.163\.com/(#/)?artist\?id=(?P[0-9]+)' + _TESTS = [{ + 'note': 'Singer has aliases.', + 'url': 'http://music.163.com/#/artist?id=10559', + 'info_dict': { + 'id': '10559', + 'title': '张惠妹 - aMEI;阿密特', + }, + 'playlist_count': 50, + }, { + 'note': 'Singer has translated name.', + 'url': 'http://music.163.com/#/artist?id=124098', + 'info_dict': { + 'id': '124098', + 'title': '李昇基 - 이승기', + }, + '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') + + 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'])) + + 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) + + +class NetEaseMusicListIE(NetEaseMusicBaseIE): + IE_NAME = 'netease:playlist' + _VALID_URL = r'https?://music\.163\.com/(#/)?(playlist|discover/toplist)\?id=(?P[0-9]+)' + _TESTS = [{ + 'url': 'http://music.163.com/#/playlist?id=79177352', + 'info_dict': { + 'id': '79177352', + 'title': 'Billboard 2007 Top 100', + 'description': 'md5:12fd0819cab2965b9583ace0f8b7b022' + }, + 'playlist_count': 99, + }, { + 'note': 'Toplist/Charts sample', + 'url': 'http://music.163.com/#/discover/toplist?id=3733003', + 'info_dict': { + 'id': '3733003', + 'title': 're:韩国Melon排行榜周榜 [0-9]{4}-[0-9]{2}-[0-9]{2}', + 'description': 'md5:73ec782a612711cadc7872d9c1e134fc', + }, + 'playlist_count': 50, + }] + + 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'] + + 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') + 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) + + +class NetEaseMusicMvIE(NetEaseMusicBaseIE): + IE_NAME = 'netease:mv' + _VALID_URL = r'https?://music\.163\.com/(#/)?mv\?id=(?P[0-9]+)' + _TEST = { + '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', + 'upload_date': '20150520', + }, + } + + 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'] + + formats = [ + {'url': mv_url, 'ext': 'mp4', 'format_id': '%sp' % brs, 'preference': int(brs)} + for brs, mv_url in info['brs'].items() + ] + self._sort_formats(formats) + + 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': int(info.get('duration', 0)/1000), + } + + +class NetEaseMusicProgramIE(NetEaseMusicBaseIE): + IE_NAME = 'netease:program' + _VALID_URL = r'https?://music\.163\.com/(#/?)program\?id=(?P[0-9]+)' + _TESTS = [{ + 'url': 'http://music.163.com/#/program?id=10109055', + 'info_dict': { + 'id': '10109055', + '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': 1434179341, + 'upload_date': '20150613', + 'duration': 900, + }, + }, { + '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>', + 'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b', + }, + 'playlist_count': 4, + }, { + 'note': 'This program has accompanying songs.', + 'url': 'http://music.163.com/#/program?id=10141022', + 'info_dict': { + 'id': '10141022', + 'ext': 'mp3', + 'title': '25岁，你是自在如风的少年<27°C>', + 'description': 'md5:8d594db46cc3e6509107ede70a4aaa3b', + 'timestamp': 1434450840, + 'upload_date': '20150616', + }, + 'params': { + 'noplaylist': True + } + }] + + 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'] + + name = info['name'] + description = info['description'] + + if not info['songs'] or self._downloader.params.get('noplaylist'): + if info['songs']: + 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) + + return { + 'id': program_id, + 'title': name, + 'description': description, + 'creator': info['dj']['brand'], + 'timestamp': int(info['createTime']/1000), + 'thumbnail': info['coverUrl'], + 'duration': int(info.get('duration', 0)/1000), + 'formats': formats, + } + + self.to_screen( + 'Downloading playlist %s - add --no-playlist to just download the main audio %s' + % (program_id, info['mainSong']['id'])) + + 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) + + +class NetEaseMusicDjRadioIE(NetEaseMusicBaseIE): + IE_NAME = 'netease:djradio' + _VALID_URL = r'https?://music\.163\.com/(#/)?djradio\?id=(?P[0-9]+)' + _TEST = { + 'url': 'http://music.163.com/#/djradio?id=42', + 'info_dict': { + 'id': '42', + 'title': '声音蔓延', + 'description': 'md5:766220985cbd16fdd552f64c578a6b15' + }, + 'playlist_mincount': 40, + } + _PAGE_SIZE = 1000 + + def _real_extract(self, url): + dj_id = self._match_id(url) + + name = None + desc = None + 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) + + 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'] + + if not info['more']: + break + + return self.playlist_result(entries, dj_id, name, desc) From 2da0cad6ae08e3c78f85a340260aef80a464cb20 Mon Sep 17 00:00:00 2001 From: ping Date: Sun, 21 Jun 2015 11:44:50 +0800 Subject: [PATCH 2/7] [neteasemusic] Do proper rounding conversion of millisecond timestamps/durations --- youtube_dl/extractor/neteasemusic.py | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/neteasemusic.py b/youtube_dl/extractor/neteasemusic.py index ebed5d3b4..a70c65ca5 100644 --- a/youtube_dl/extractor/neteasemusic.py +++ b/youtube_dl/extractor/neteasemusic.py @@ -50,6 +50,10 @@ class NetEaseMusicBaseIE(InfoExtractor): }) 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.add_header('Referer', self._API_BASE) @@ -143,9 +147,9 @@ class NetEaseMusicIE(NetEaseMusicBaseIE): '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, } @@ -255,7 +259,8 @@ class NetEaseMusicListIE(NetEaseMusicBaseIE): 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 = [ @@ -302,7 +307,7 @@ 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)), } @@ -317,7 +322,7 @@ 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 +343,7 @@ 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': { @@ -370,9 +375,9 @@ 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, } From 02b386f80abc16f5334e980c2fb729b0cc69a0d6 Mon Sep 17 00:00:00 2001 From: ping Date: Fri, 10 Jul 2015 13:29:57 +0800 Subject: [PATCH 3/7] [neteasemusic] Changes after review --- youtube_dl/extractor/neteasemusic.py | 42 ++++++++++++++++++---------- 1 file changed, 27 insertions(+), 15 deletions(-) diff --git a/youtube_dl/extractor/neteasemusic.py b/youtube_dl/extractor/neteasemusic.py index a70c65ca5..419f3ecc9 100644 --- a/youtube_dl/extractor/neteasemusic.py +++ b/youtube_dl/extractor/neteasemusic.py @@ -2,6 +2,7 @@ from __future__ import unicode_literals from hashlib import md5 +from base64 import b64encode from datetime import datetime import itertools import re @@ -20,14 +21,14 @@ class NetEaseMusicBaseIE(InfoExtractor): @classmethod def _encrypt(cls, dfsid): - salt_bytes = bytearray(str(cls._NETEASE_SALT)) + salt_bytes = bytearray(cls._NETEASE_SALT, 'utf-8') string_bytes = bytearray(str(dfsid)) 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] + result = b64encode(m.digest()) return result.replace('/', '_').replace('+', '-') @classmethod @@ -41,12 +42,11 @@ class NetEaseMusicBaseIE(InfoExtractor): 'url': 'http://m1.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 @@ -98,6 +98,19 @@ 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): @@ -109,10 +122,9 @@ 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 @@ -139,8 +151,8 @@ class NetEaseMusicIE(NetEaseMusicBaseIE): 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, @@ -294,7 +306,7 @@ 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) From 15830339eff9076b1c4ca2cb6322fc1ec55233a8 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Fri, 10 Jul 2015 18:30:23 +0800 Subject: [PATCH 4/7] [neteasemusic] PEP8 --- youtube_dl/extractor/neteasemusic.py | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/youtube_dl/extractor/neteasemusic.py b/youtube_dl/extractor/neteasemusic.py index 419f3ecc9..e73c77f89 100644 --- a/youtube_dl/extractor/neteasemusic.py +++ b/youtube_dl/extractor/neteasemusic.py @@ -52,7 +52,7 @@ class NetEaseMusicBaseIE(InfoExtractor): @classmethod def convert_milliseconds(cls, ms): - return int(round(ms/1000.0)) + 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)) @@ -146,7 +146,7 @@ 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) @@ -183,7 +183,7 @@ 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'] @@ -221,7 +221,7 @@ 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'] @@ -264,7 +264,7 @@ 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'] @@ -378,7 +378,7 @@ 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) @@ -429,7 +429,7 @@ class NetEaseMusicDjRadioIE(NetEaseMusicBaseIE): 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' + 'dj/program/byradio?asc=false&limit=%d&radioId=%s&offset=%d' % (self._PAGE_SIZE, dj_id, offset), dj_id, 'Downloading dj programs - %d' % offset) From 397a8ea96e228f918f127313f837f7de7dd78aed Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Fri, 10 Jul 2015 18:43:38 +0800 Subject: [PATCH 5/7] [neteasemusic] Encoding fixes for Python 2.6 and 3.x --- youtube_dl/extractor/neteasemusic.py | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/youtube_dl/extractor/neteasemusic.py b/youtube_dl/extractor/neteasemusic.py index e73c77f89..9e99ddbda 100644 --- a/youtube_dl/extractor/neteasemusic.py +++ b/youtube_dl/extractor/neteasemusic.py @@ -11,6 +11,7 @@ from .common import InfoExtractor from ..compat import ( compat_urllib_request, compat_urllib_parse, + compat_str, ) @@ -21,14 +22,14 @@ class NetEaseMusicBaseIE(InfoExtractor): @classmethod def _encrypt(cls, dfsid): - salt_bytes = bytearray(cls._NETEASE_SALT, 'utf-8') - 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 range(len(string_bytes)): string_bytes[i] = string_bytes[i] ^ salt_bytes[i % salt_len] m = md5() - m.update(string_bytes) - result = b64encode(m.digest()) + m.update(bytes(string_bytes)) + result = b64encode(m.digest()).decode('ascii') return result.replace('/', '_').replace('+', '-') @classmethod From a0e060ac1e9871974c02fe7cb3e812a3cbe79e73 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Fri, 10 Jul 2015 18:58:12 +0800 Subject: [PATCH 6/7] [compat] Add compat_itertools_count 'step' parameter is added in Python 2.7 --- youtube_dl/compat.py | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index f9529210d..c3783337a 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -9,6 +9,7 @@ import shutil import socket import subprocess import sys +import itertools try: @@ -388,6 +389,15 @@ else: pass return _terminal_size(columns, lines) +try: + itertools.count(start=0, step=1) + compat_itertools_count = itertools.count +except TypeError: # Python 2.6 + def compat_itertools_count(start=0, step=1): + n = start + while True: + yield n + n += step __all__ = [ 'compat_HTTPError', @@ -401,6 +411,7 @@ __all__ = [ 'compat_html_entities', 'compat_http_client', 'compat_http_server', + 'compat_itertools_count', 'compat_kwargs', 'compat_ord', 'compat_parse_qs', From 4eab60cbd27ea8ce31ae9c6bf6b3f6e0e469d3af Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Fri, 10 Jul 2015 18:59:12 +0800 Subject: [PATCH 7/7] [netease:djradio] Use compat_itertools_count --- youtube_dl/extractor/neteasemusic.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/neteasemusic.py b/youtube_dl/extractor/neteasemusic.py index 9e99ddbda..bdfe7e63f 100644 --- a/youtube_dl/extractor/neteasemusic.py +++ b/youtube_dl/extractor/neteasemusic.py @@ -4,7 +4,6 @@ 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 @@ -12,6 +11,7 @@ from ..compat import ( compat_urllib_request, compat_urllib_parse, compat_str, + compat_itertools_count, ) @@ -428,7 +428,7 @@ 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' % (self._PAGE_SIZE, dj_id, offset),