X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fqqmusic.py;h=5a18191bc55166c625abe4a00e0df487c16b0cdf;hb=0392ac98d2c5c5a6fd2ab51c51096f82312a287c;hp=3401dcaef1ec25168f2629e2914396465e2fc193;hpb=fd4eefed39595850b864d3be9711224e4e8e9dd4;p=youtube-dl diff --git a/youtube_dl/extractor/qqmusic.py b/youtube_dl/extractor/qqmusic.py index 3401dcaef..5a18191bc 100644 --- a/youtube_dl/extractor/qqmusic.py +++ b/youtube_dl/extractor/qqmusic.py @@ -9,26 +9,51 @@ from .common import InfoExtractor from ..utils import ( strip_jsonp, unescapeHTML, - js_to_json, + HEADRequest, + ExtractorError, +) +from ..compat import ( + compat_urllib_request, + compat_HTTPError, ) -from ..compat import compat_urllib_request class QQMusicIE(InfoExtractor): + IE_NAME = 'qqmusic' _VALID_URL = r'http://y.qq.com/#type=song&mid=(?P[0-9A-Za-z]+)' _TESTS = [{ 'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD', - 'md5': 'bed90b6db2a7a7a7e11bc585f471f63a', + 'md5': '9ce1c1c8445f561506d2e3cfb0255705', 'info_dict': { 'id': '004295Et37taLD', - 'ext': 'm4a', + 'ext': 'mp3', 'title': '可惜没如果', 'upload_date': '20141227', 'creator': '林俊杰', - 'description': 'md5:4348ff1dd24036906baa7b6f973f8d30', + 'description': 'md5:d327722d0361576fde558f1ac68a7065', + 'thumbnail': 'http://i.gtimg.cn/music/photo/mid_album_500/7/p/001IV22P1RDX7p.jpg', + } + }, { + 'note': 'There is no mp3-320 version of this song.', + 'url': 'http://y.qq.com/#type=song&mid=004MsGEo3DdNxV', + 'md5': 'fa3926f0c585cda0af8fa4f796482e3e', + 'info_dict': { + 'id': '004MsGEo3DdNxV', + 'ext': 'mp3', + 'title': '如果', + 'upload_date': '20050626', + 'creator': '李季美', + 'description': 'md5:46857d5ed62bc4ba84607a805dccf437', + 'thumbnail': 'http://i.gtimg.cn/music/photo/mid_album_500/r/Q/0042owYj46IxrQ.jpg', } }] + _FORMATS = { + 'mp3-320': {'prefix': 'M800', 'ext': 'mp3', 'preference': 40, 'abr': 320}, + 'mp3-128': {'prefix': 'M500', 'ext': 'mp3', 'preference': 30, 'abr': 128}, + 'm4a': {'prefix': 'C200', 'ext': 'm4a', 'preference': 10} + } + # Reference: m_r_GetRUin() in top_player.js # http://imgcache.gtimg.cn/music/portal_v3/y/top_player.js @staticmethod @@ -59,6 +84,16 @@ class QQMusicIE(InfoExtractor): lrc_content = self._html_search_regex( r'
]*>([^<>]+)
', detail_info_page, 'LRC lyrics', default=None) + if lrc_content: + lrc_content = lrc_content.replace('\\n', '\n') + + thumbnail_url = None + albummid = self._search_regex( + [r'albummid:\'([0-9a-zA-Z]+)\'', r'"albummid":"([0-9a-zA-Z]+)"'], + detail_info_page, 'album mid', default=None) + if albummid: + thumbnail_url = "http://i.gtimg.cn/music/photo/mid_album_500/%s/%s/%s.jpg" \ + % (albummid[-2:-1], albummid[-1], albummid) guid = self.m_r_get_ruin() @@ -66,15 +101,37 @@ class QQMusicIE(InfoExtractor): 'http://base.music.qq.com/fcgi-bin/fcg_musicexpress.fcg?json=3&guid=%s' % guid, mid, note='Retrieve vkey', errnote='Unable to get vkey', transform_source=strip_jsonp)['key'] - song_url = 'http://cc.stream.qqmusic.qq.com/C200%s.m4a?vkey=%s&guid=%s&fromtag=0' % (mid, vkey, guid) + + formats = [] + for format_id, details in self._FORMATS.items(): + video_url = 'http://cc.stream.qqmusic.qq.com/%s%s.%s?vkey=%s&guid=%s&fromtag=0' \ + % (details['prefix'], mid, details['ext'], vkey, guid) + req = HEADRequest(video_url) + try: + res = self._request_webpage( + req, mid, note='Testing %s video URL' % format_id, fatal=False) + except ExtractorError as e: + if isinstance(e.cause, compat_HTTPError) and e.cause.code in [400, 404]: + self.report_warning('Invalid %s video URL' % format_id, mid) + else: + if res: + formats.append({ + 'url': video_url, + 'format': format_id, + 'format_id': format_id, + 'preference': details['preference'], + 'abr': details.get('abr'), + }) + self._sort_formats(formats) return { 'id': mid, - 'url': song_url, + 'formats': formats, 'title': song_name, 'upload_date': publish_time, 'creator': singer, 'description': lrc_content, + 'thumbnail': thumbnail_url, } @@ -97,6 +154,7 @@ class QQPlaylistBaseIE(InfoExtractor): class QQMusicSingerIE(QQPlaylistBaseIE): + IE_NAME = 'qqmusic:singer' _VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P[0-9A-Za-z]+)' _TEST = { 'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2', @@ -140,6 +198,7 @@ class QQMusicSingerIE(QQPlaylistBaseIE): class QQMusicAlbumIE(QQPlaylistBaseIE): + IE_NAME = 'qqmusic:album' _VALID_URL = r'http://y.qq.com/#type=album&mid=(?P[0-9A-Za-z]+)' _TEST = { @@ -172,66 +231,53 @@ class QQMusicAlbumIE(QQPlaylistBaseIE): class QQMusicToplistIE(QQPlaylistBaseIE): + IE_NAME = 'qqmusic:toplist' _VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P(top|global)_[0-9]+)' - + _TESTS = [{ - 'url': 'http://y.qq.com/#type=toplist&p=global_12', + 'url': 'http://y.qq.com/#type=toplist&p=global_123', 'info_dict': { - 'id': 'global_12', - 'title': 'itunes榜', + 'id': 'global_123', + 'title': '美国iTunes榜', }, 'playlist_count': 10, }, { - 'url': 'http://y.qq.com/#type=toplist&p=top_6', + 'url': 'http://y.qq.com/#type=toplist&p=top_3', 'info_dict': { - 'id': 'top_6', + 'id': 'top_3', 'title': 'QQ音乐巅峰榜·欧美', + 'description': 'QQ音乐巅峰榜·欧美根据用户收听行为自动生成，集结当下最流行的欧美新歌！:更新时间：每周四22点|统' + '计周期：一周（上周四至本周三）|统计对象：三个月内发行的欧美歌曲|统计数量：100首|统计算法：根据' + '歌曲在一周内的有效播放次数，由高到低取前100名（同一歌手最多允许5首歌曲同时上榜）|有效播放次数：' + '登录用户完整播放一首歌曲，记为一次有效播放；同一用户收听同一首歌曲，每天记录为1次有效播放' }, 'playlist_count': 100, }, { - 'url': 'http://y.qq.com/#type=toplist&p=global_5', + 'url': 'http://y.qq.com/#type=toplist&p=global_106', 'info_dict': { - 'id': 'global_5', - 'title': '韩国mnet排行榜', + 'id': 'global_106', + 'title': '韩国Mnet榜', }, 'playlist_count': 50, }] - @staticmethod - def strip_qq_jsonp(code): - return js_to_json(re.sub(r'^MusicJsonCallback\((.*?)\)/\*.+?\*/$', r'\1', code)) - def _real_extract(self, url): list_id = self._match_id(url) - list_type = list_id.split("_")[0] - num_id = list_id.split("_")[1] + list_type, num_id = list_id.split("_") - list_page = self._download_webpage( - "http://y.qq.com/y/static/toplist/index/%s.html" % list_id, + toplist_json = self._download_json( + 'http://i.y.qq.com/v8/fcg-bin/fcg_v8_toplist_cp.fcg?type=%s&topid=%s&format=json' + % (list_type, num_id), list_id, 'Download toplist page') - entries = [] - jsonp_url = "" - if list_type == 'top': - jsonp_url = "http://y.qq.com/y/static/toplist/json/top/%s/1.js" % num_id - elif list_type == 'global': - jsonp_url = "http://y.qq.com/y/static/toplist/json/global/%s/1_1.js" % num_id - - list = self._download_json(jsonp_url, list_id, note='Retrieve toplist json', - errnote='Unable to get toplist json', transform_source=self.strip_qq_jsonp) - - for song in list['l']: - s = song['s'] - song_mid = s.split("|")[20] - entries.append(self.url_result( - 'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic', - song_mid)) - - list_name = self._html_search_regex( - r'

([^\']+)

', list_page, 'top list name', - default=None) - list_desc = None + entries = [ + self.url_result( + 'http://y.qq.com/#type=song&mid=' + song['data']['songmid'], 'QQMusic', song['data']['songmid'] + ) for song in toplist_json['songlist'] + ] - return self.playlist_result(entries, list_id, list_name, list_desc) - \ No newline at end of file + topinfo = toplist_json.get('topinfo', {}) + list_name = topinfo.get('ListName') + list_description = topinfo.get('info') + return self.playlist_result(entries, list_id, list_name, list_description)