1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 08:27:43 +00:00
youtube-dl/youtube_dl/extractor/qqmusic.py

370 lines
13 KiB
Python
Raw Normal View History

2015-03-17 11:03:29 +00:00
# coding: utf-8
from __future__ import unicode_literals
2015-03-18 05:56:02 +00:00
import random
2015-03-18 06:59:33 +00:00
import re
2017-08-02 03:12:17 +00:00
import time
2015-03-18 05:56:02 +00:00
2015-03-17 11:03:29 +00:00
from .common import InfoExtractor
2015-03-18 17:47:07 +00:00
from ..utils import (
2015-06-18 05:59:37 +00:00
clean_html,
ExtractorError,
2017-08-17 08:39:57 +00:00
strip_jsonp,
unescapeHTML,
2015-03-18 17:47:07 +00:00
)
2015-03-17 11:03:29 +00:00
class QQMusicIE(InfoExtractor):
IE_NAME = 'qqmusic'
2015-07-10 16:52:07 +00:00
IE_DESC = 'QQ音乐'
2017-08-02 03:12:17 +00:00
_VALID_URL = r'https?://y\.qq\.com/n/yqq/song/(?P<id>[0-9A-Za-z]+)\.html'
2015-03-17 11:03:29 +00:00
_TESTS = [{
2017-08-02 03:12:17 +00:00
'url': 'https://y.qq.com/n/yqq/song/004295Et37taLD.html',
2017-08-17 08:39:57 +00:00
'md5': '5f1e6cea39e182857da7ffc5ef5e6bb8',
2015-03-17 11:03:29 +00:00
'info_dict': {
'id': '004295Et37taLD',
'ext': 'mp3',
2015-03-17 11:03:29 +00:00
'title': '可惜没如果',
2015-09-26 15:08:23 +00:00
'release_date': '20141227',
2015-03-17 11:03:29 +00:00
'creator': '林俊杰',
2017-08-17 08:39:57 +00:00
'description': 'md5:d85afb3051952ecc50a1ee8a286d1eac',
'thumbnail': r're:^https?://.*\.jpg$',
}
}, {
'note': 'There is no mp3-320 version of this song.',
2017-08-02 03:12:17 +00:00
'url': 'https://y.qq.com/n/yqq/song/004MsGEo3DdNxV.html',
'md5': 'fa3926f0c585cda0af8fa4f796482e3e',
'info_dict': {
'id': '004MsGEo3DdNxV',
'ext': 'mp3',
'title': '如果',
2015-09-26 15:08:23 +00:00
'release_date': '20050626',
'creator': '李季美',
'description': 'md5:46857d5ed62bc4ba84607a805dccf437',
'thumbnail': r're:^https?://.*\.jpg$',
2015-03-17 11:03:29 +00:00
}
}, {
'note': 'lyrics not in .lrc format',
2017-08-02 03:12:17 +00:00
'url': 'https://y.qq.com/n/yqq/song/001JyApY11tIp6.html',
'info_dict': {
'id': '001JyApY11tIp6',
'ext': 'mp3',
'title': 'Shadows Over Transylvania',
2015-09-26 15:08:23 +00:00
'release_date': '19970225',
'creator': 'Dark Funeral',
2017-08-17 08:39:57 +00:00
'description': 'md5:c9b20210587cbcd6836a1c597bab4525',
'thumbnail': r're:^https?://.*\.jpg$',
},
'params': {
'skip_download': True,
},
2015-03-17 11:03:29 +00:00
}]
_FORMATS = {
2015-06-04 22:04:26 +00:00
'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}
}
2015-03-18 05:56:02 +00:00
# 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)
2015-03-17 11:03:29 +00:00
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,
2015-03-18 06:59:33 +00:00
mid, note='Download song detail info',
errnote='Unable to get song detail info', encoding='gbk')
2015-03-17 11:03:29 +00:00
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('-', '')
2015-03-17 11:03:29 +00:00
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')
2015-03-17 11:03:29 +00:00
thumbnail_url = None
albummid = self._search_regex(
2015-06-18 13:13:03 +00:00
[r'albummid:\'([0-9a-zA-Z]+)\'', r'"albummid":"([0-9a-zA-Z]+)"'],
detail_info_page, 'album mid', default=None)
if albummid:
2017-08-17 08:39:57 +00:00
thumbnail_url = 'http://i.gtimg.cn/music/photo/mid_album_500/%s/%s/%s.jpg' \
% (albummid[-2:-1], albummid[-1], albummid)
2015-03-18 05:56:02 +00:00
guid = self.m_r_get_ruin()
2015-03-17 11:03:29 +00:00
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():
formats.append({
'url': 'http://cc.stream.qqmusic.qq.com/%s%s.%s?vkey=%s&guid=%s&fromtag=0'
% (details['prefix'], mid, details['ext'], vkey, guid),
'format': format_id,
'format_id': format_id,
'preference': details['preference'],
'abr': details.get('abr'),
})
2015-06-18 15:09:04 +00:00
self._check_formats(formats, mid)
self._sort_formats(formats)
2015-03-17 11:03:29 +00:00
actual_lrc_lyrics = ''.join(
line + '\n' for line in re.findall(
2015-09-26 15:15:34 +00:00
r'(?m)^(\[[0-9]{2}:[0-9]{2}(?:\.[0-9]{2,})?\][^\n]*|\[[^\]]*\])', lrc_content))
info_dict = {
2015-03-17 11:03:29 +00:00
'id': mid,
'formats': formats,
2015-03-17 11:03:29 +00:00
'title': song_name,
2015-09-26 15:08:23 +00:00
'release_date': publish_time,
2015-03-17 11:03:29 +00:00
'creator': singer,
'description': lrc_content,
'thumbnail': thumbnail_url
2015-03-17 11:03:29 +00:00
}
if actual_lrc_lyrics:
info_dict['subtitles'] = {
'origin': [{
'ext': 'lrc',
'data': actual_lrc_lyrics,
}]
}
return info_dict
2015-03-18 06:59:33 +00:00
2015-03-18 17:47:07 +00:00
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)
2017-08-02 07:08:38 +00:00
def get_singer_all_songs(self, singmid, num):
return self._download_webpage(
2017-08-17 08:39:57 +00:00
r'https://c.y.qq.com/v8/fcg-bin/fcg_v8_singer_track_cp.fcg', singmid,
query={
'format': 'json',
'inCharset': 'utf8',
'outCharset': 'utf-8',
'platform': 'yqq',
'needNewCode': 0,
'singermid': singmid,
'order': 'listen',
'begin': 0,
'num': num,
'songstatus': 1,
})
2017-08-02 07:08:38 +00:00
def get_entries_from_page(self, singmid):
2015-03-18 17:47:07 +00:00
entries = []
2017-08-02 07:08:38 +00:00
default_num = 1
json_text = self.get_singer_all_songs(singmid, default_num)
2017-08-14 00:28:41 +00:00
json_obj_all_songs = self._parse_json(json_text, singmid)
2017-08-02 07:08:38 +00:00
2017-08-14 00:28:41 +00:00
if json_obj_all_songs['code'] == 0:
total = json_obj_all_songs['data']['total']
2017-08-02 07:08:38 +00:00
json_text = self.get_singer_all_songs(singmid, total)
2017-08-14 00:28:41 +00:00
json_obj_all_songs = self._parse_json(json_text, singmid)
2017-08-02 07:08:38 +00:00
2017-08-14 00:28:41 +00:00
for item in json_obj_all_songs['data']['list']:
if item['musicData'].get('songmid') is not None:
2017-08-02 07:08:38 +00:00
songmid = item['musicData']['songmid']
2017-08-17 08:39:57 +00:00
entries.append(self.url_result(
r'https://y.qq.com/n/yqq/song/%s.html' % songmid, 'QQMusic', songmid))
2015-03-18 17:47:07 +00:00
return entries
class QQMusicSingerIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:singer'
2015-07-10 17:21:36 +00:00
IE_DESC = 'QQ音乐 - 歌手'
2017-08-02 03:12:17 +00:00
_VALID_URL = r'https?://y\.qq\.com/n/yqq/singer/(?P<id>[0-9A-Za-z]+)\.html'
2015-03-18 06:59:33 +00:00
_TEST = {
2017-08-02 03:12:17 +00:00
'url': 'https://y.qq.com/n/yqq/singer/001BLpXF2DyJe2.html',
2015-03-18 06:59:33 +00:00
'info_dict': {
'id': '001BLpXF2DyJe2',
'title': '林俊杰',
2016-01-02 14:39:09 +00:00
'description': 'md5:870ec08f7d8547c29c93010899103751',
2015-03-18 06:59:33 +00:00
},
2017-08-17 08:39:57 +00:00
'playlist_mincount': 12,
2015-03-18 06:59:33 +00:00
}
def _real_extract(self, url):
mid = self._match_id(url)
2017-08-02 07:08:38 +00:00
entries = self.get_entries_from_page(mid)
singer_page = self._download_webpage(url, mid, 'Download singer page')
2017-08-17 08:39:57 +00:00
singer_name = self._html_search_regex(
r"singername\s*:\s*'(.*?)'", singer_page, 'singer name', default=None)
2015-03-18 06:59:33 +00:00
singer_desc = None
2017-08-02 07:08:38 +00:00
if mid:
2015-03-18 06:59:33 +00:00
singer_desc_page = self._download_xml(
2017-08-17 08:39:57 +00:00
'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg', mid,
'Donwload singer description XML',
query={'utf8': 1, 'outCharset': 'utf-8', 'format': 'xml', 'singermid': mid},
headers={'Referer': 'https://y.qq.com/n/yqq/singer/'})
2015-03-18 06:59:33 +00:00
singer_desc = singer_desc_page.find('./data/info/desc').text
return self.playlist_result(entries, mid, singer_name, singer_desc)
2015-03-18 17:47:07 +00:00
class QQMusicAlbumIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:album'
2015-07-10 17:21:36 +00:00
IE_DESC = 'QQ音乐 - 专辑'
2017-08-02 03:12:17 +00:00
_VALID_URL = r'https?://y\.qq\.com/n/yqq/album/(?P<id>[0-9A-Za-z]+)\.html'
2015-03-18 17:47:07 +00:00
2015-06-18 07:52:04 +00:00
_TESTS = [{
2017-08-02 03:12:17 +00:00
'url': 'https://y.qq.com/n/yqq/album/000gXCTb2AhRR1.html',
2015-03-18 17:47:07 +00:00
'info_dict': {
'id': '000gXCTb2AhRR1',
'title': '我们都是这样长大的',
2015-07-06 09:08:32 +00:00
'description': 'md5:179c5dce203a5931970d306aa9607ea6',
2015-03-18 17:47:07 +00:00
},
'playlist_count': 4,
2015-06-18 07:52:04 +00:00
}, {
2017-08-02 03:12:17 +00:00
'url': 'https://y.qq.com/n/yqq/album/002Y5a3b3AlCu3.html',
2015-06-18 07:52:04 +00:00
'info_dict': {
'id': '002Y5a3b3AlCu3',
'title': '그리고...',
2015-07-06 09:08:32 +00:00
'description': 'md5:a48823755615508a95080e81b51ba729',
2015-06-18 07:52:04 +00:00
},
'playlist_count': 8,
}]
2015-03-18 17:47:07 +00:00
def _real_extract(self, url):
mid = self._match_id(url)
2015-06-18 07:52:04 +00:00
album = self._download_json(
'http://i.y.qq.com/v8/fcg-bin/fcg_v8_album_info_cp.fcg?albummid=%s&format=json' % mid,
mid, 'Download album page')['data']
entries = [
self.url_result(
2017-08-14 00:28:41 +00:00
'https://y.qq.com/n/yqq/song/' + song['songmid'] + '.html', 'QQMusic', song['songmid']
2015-06-18 07:52:04 +00:00
) for song in album['list']
]
album_name = album.get('name')
2015-06-18 07:52:04 +00:00
album_detail = album.get('desc')
2015-07-06 09:08:32 +00:00
if album_detail is not None:
album_detail = album_detail.strip()
2015-03-18 17:47:07 +00:00
return self.playlist_result(entries, mid, album_name, album_detail)
class QQMusicToplistIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:toplist'
2015-07-10 17:21:36 +00:00
IE_DESC = 'QQ音乐 - 排行榜'
2017-08-02 04:20:53 +00:00
_VALID_URL = r'https?://y\.qq\.com/n/yqq/toplist/(?P<id>[0-9]+)\.html'
2015-05-14 15:25:43 +00:00
_TESTS = [{
2017-08-02 03:12:17 +00:00
'url': 'https://y.qq.com/n/yqq/toplist/123.html',
'info_dict': {
2017-08-17 08:39:57 +00:00
'id': '123',
2015-06-04 03:27:18 +00:00
'title': '美国iTunes榜',
2017-08-17 08:39:57 +00:00
'description': 'md5:89db2335fdbb10678dee2d43fe9aba08',
},
2017-08-17 08:39:57 +00:00
'playlist_count': 100,
}, {
2017-08-02 03:12:17 +00:00
'url': 'https://y.qq.com/n/yqq/toplist/3.html',
'info_dict': {
2017-08-17 08:39:57 +00:00
'id': '3',
2016-01-02 14:39:09 +00:00
'title': '巅峰榜·欧美',
2017-08-17 08:39:57 +00:00
'description': 'md5:5a600d42c01696b26b71f8c4d43407da',
},
'playlist_count': 100,
}, {
2017-08-02 03:12:17 +00:00
'url': 'https://y.qq.com/n/yqq/toplist/106.html',
'info_dict': {
2017-08-17 08:39:57 +00:00
'id': '106',
2015-06-04 03:27:18 +00:00
'title': '韩国Mnet榜',
2017-08-17 08:39:57 +00:00
'description': 'md5:cb84b325215e1d21708c615cac82a6e7',
},
'playlist_count': 50,
}]
def _real_extract(self, url):
list_id = self._match_id(url)
2015-05-14 15:28:42 +00:00
toplist_json = self._download_json(
2017-08-17 08:39:57 +00:00
'http://i.y.qq.com/v8/fcg-bin/fcg_v8_toplist_cp.fcg', list_id,
note='Download toplist page',
query={'type': 'toplist', 'topid': list_id, 'format': 'json'})
2017-08-17 08:39:57 +00:00
entries = [self.url_result(
'https://y.qq.com/n/yqq/song/' + song['data']['songmid'] + '.html', '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')
2015-06-04 03:27:18 +00:00
return self.playlist_result(entries, list_id, list_name, list_description)
2015-06-18 05:59:37 +00:00
class QQMusicPlaylistIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:playlist'
2015-07-10 17:21:36 +00:00
IE_DESC = 'QQ音乐 - 歌单'
2017-08-02 03:12:17 +00:00
_VALID_URL = r'https?://y\.qq\.com/n/yqq/playlist/(?P<id>[0-9]+)\.html'
2015-06-18 05:59:37 +00:00
_TESTS = [{
2017-08-02 03:12:17 +00:00
'url': 'http://y.qq.com/n/yqq/playlist/3462654915.html',
2015-06-18 05:59:37 +00:00
'info_dict': {
'id': '3462654915',
'title': '韩国5月新歌精选下旬',
'description': 'md5:d2c9d758a96b9888cf4fe82f603121d4',
},
'playlist_count': 40,
'skip': 'playlist gone',
}, {
2017-08-02 03:12:17 +00:00
'url': 'https://y.qq.com/n/yqq/playlist/1374105607.html',
'info_dict': {
'id': '1374105607',
'title': '易入人心的华语民谣',
'description': '民谣的歌曲易于传唱、、歌词朗朗伤口、旋律简单温馨。属于那种才入耳孔。却上心头的感觉。没有太多的复杂情绪。简单而直接地表达乐者的情绪,就是这样的简单才易入人心。',
},
'playlist_count': 20,
}]
2015-06-18 05:59:37 +00:00
def _real_extract(self, url):
list_id = self._match_id(url)
list_json = self._download_json(
2017-08-17 08:39:57 +00:00
'http://i.y.qq.com/qzone-music/fcg-bin/fcg_ucc_getcdinfo_byids_cp.fcg',
list_id, 'Download list page',
query={'type': 1, 'json': 1, 'utf8': 1, 'onlysong': 0, 'disstid': list_id},
transform_source=strip_jsonp)
if not len(list_json.get('cdlist', [])):
if list_json.get('code'):
raise ExtractorError(
'QQ Music said: error %d in fetching playlist info' % list_json['code'],
expected=True)
raise ExtractorError('Unable to get playlist info')
cdlist = list_json['cdlist'][0]
2017-08-17 08:39:57 +00:00
entries = [self.url_result(
'https://y.qq.com/n/yqq/song/' + song['songmid'] + '.html', 'QQMusic', song['songmid'])
for song in cdlist['songlist']]
2015-06-18 05:59:37 +00:00
list_name = cdlist.get('dissname')
list_description = clean_html(unescapeHTML(cdlist.get('desc')))
2015-06-18 05:59:37 +00:00
return self.playlist_result(entries, list_id, list_name, list_description)