aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/qqmusic.py
blob: 7ddc4ca25c6655258c8feb581dbbe809ee5b32fd (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
# coding: utf-8
from __future__ import unicode_literals

import random
import time
import re

from .common import InfoExtractor
from ..utils import (
    strip_jsonp,
    unescapeHTML,
    HEADRequest,
    ExtractorError,
)
from ..compat import (
    compat_urllib_request,
    compat_HTTPError,
)


class QQMusicIE(InfoExtractor):
    IE_NAME = 'qqmusic'
    _VALID_URL = r'http://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
    _TESTS = [{
        'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
        'md5': '9ce1c1c8445f561506d2e3cfb0255705',
        'info_dict': {
            'id': '004295Et37taLD',
            'ext': 'mp3',
            'title': '可惜没如果',
            'upload_date': '20141227',
            'creator': '林俊杰',
            '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
    def m_r_get_ruin():
        curMs = int(time.time() * 1000) % 1000
        return int(round(random.random() * 2147483647) * curMs % 1E10)

    def _real_extract(self, url):
        mid = self._match_id(url)

        detail_info_page = self._download_webpage(
            'http://s.plcloud.music.qq.com/fcgi-bin/fcg_yqq_song_detail_info.fcg?songmid=%s&play=0' % mid,
            mid, note='Download song detail info',
            errnote='Unable to get song detail info', encoding='gbk')

        song_name = self._html_search_regex(
            r"songname:\s*'([^']+)'", detail_info_page, 'song name')

        publish_time = self._html_search_regex(
            r'发行时间:(\d{4}-\d{2}-\d{2})', detail_info_page,
            'publish time', default=None)
        if publish_time:
            publish_time = publish_time.replace('-', '')

        singer = self._html_search_regex(
            r"singer:\s*'([^']+)", detail_info_page, 'singer', default=None)

        lrc_content = self._html_search_regex(
            r'<div class="content" id="lrc_content"[^<>]*>([^<>]+)</div>',
            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()

        vkey = self._download_json(
            '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']

        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,
            'formats': formats,
            'title': song_name,
            'upload_date': publish_time,
            'creator': singer,
            'description': lrc_content,
            'thumbnail': thumbnail_url,
        }


class QQPlaylistBaseIE(InfoExtractor):
    @staticmethod
    def qq_static_url(category, mid):
        return 'http://y.qq.com/y/static/%s/%s/%s/%s.html' % (category, mid[-2], mid[-1], mid)

    @classmethod
    def get_entries_from_page(cls, page):
        entries = []

        for item in re.findall(r'class="data"[^<>]*>([^<>]+)</', page):
            song_mid = unescapeHTML(item).split('|')[-5]
            entries.append(cls.url_result(
                'http://y.qq.com/#type=song&mid=' + song_mid, 'QQMusic',
                song_mid))

        return entries


class QQMusicSingerIE(QQPlaylistBaseIE):
    IE_NAME = 'qqmusic:singer'
    _VALID_URL = r'http://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
    _TEST = {
        'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
        'info_dict': {
            'id': '001BLpXF2DyJe2',
            'title': '林俊杰',
            'description': 'md5:2a222d89ba4455a3af19940c0481bb78',
        },
        'playlist_count': 12,
    }

    def _real_extract(self, url):
        mid = self._match_id(url)

        singer_page = self._download_webpage(
            self.qq_static_url('singer', mid), mid, 'Download singer page')

        entries = self.get_entries_from_page(singer_page)

        singer_name = self._html_search_regex(
            r"singername\s*:\s*'([^']+)'", singer_page, 'singer name',
            default=None)

        singer_id = self._html_search_regex(
            r"singerid\s*:\s*'([0-9]+)'", singer_page, 'singer id',
            default=None)

        singer_desc = None

        if singer_id:
            req = compat_urllib_request.Request(
                'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg?utf8=1&outCharset=utf-8&format=xml&singerid=%s' % singer_id)
            req.add_header(
                'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html')
            singer_desc_page = self._download_xml(
                req, mid, 'Donwload singer description XML')

            singer_desc = singer_desc_page.find('./data/info/desc').text

        return self.playlist_result(entries, mid, singer_name, singer_desc)


class QQMusicAlbumIE(QQPlaylistBaseIE):
    IE_NAME = 'qqmusic:album'
    _VALID_URL = r'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'

    _TEST = {
        'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1&play=0',
        'info_dict': {
            'id': '000gXCTb2AhRR1',
            'title': '我们都是这样长大的',
            'description': 'md5:d216c55a2d4b3537fe4415b8767d74d6',
        },
        'playlist_count': 4,
    }

    def _real_extract(self, url):
        mid = self._match_id(url)

        album_page = self._download_webpage(
            self.qq_static_url('album', mid), mid, 'Download album page')

        entries = self.get_entries_from_page(album_page)

        album_name = self._html_search_regex(
            r"albumname\s*:\s*'([^']+)',", album_page, 'album name',
            default=None)

        album_detail = self._html_search_regex(
            r'<div class="album_detail close_detail">\s*<p>((?:[^<>]+(?:<br />)?)+)</p>',
            album_page, 'album details', default=None)

        return self.playlist_result(entries, mid, album_name, album_detail)


class QQMusicToplistIE(QQPlaylistBaseIE):
    IE_NAME = 'qqmusic:toplist'
    _VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'

    _TESTS = [{
        'url': 'http://y.qq.com/#type=toplist&p=global_123',
        'info_dict': {
            'id': 'global_123',
            'title': '美国iTunes榜',
        },
        'playlist_count': 10,
    }, {
        'url': 'http://y.qq.com/#type=toplist&p=top_3',
        'info_dict': {
            '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_106',
        'info_dict': {
            'id': 'global_106',
            'title': '韩国Mnet榜',
        },
        'playlist_count': 50,
    }]

    def _real_extract(self, url):
        list_id = self._match_id(url)

        list_type, num_id = list_id.split("_")

        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 = [
            self.url_result(
                'http://y.qq.com/#type=song&mid=' + song['data']['songmid'], 'QQMusic', song['data']['songmid']
            ) for song in toplist_json['songlist']
        ]

        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)