ytdl/youtube_dl/extractor/qqmusic.py

362 lines
13 KiB
Python
Raw Normal View History

2015-03-17 12:03:29 +01:00
# coding: utf-8
from __future__ import unicode_literals
2015-03-18 06:56:02 +01:00
import random
import time
2015-03-18 07:59:33 +01:00
import re
2015-03-18 06:56:02 +01:00
2015-03-17 12:03:29 +01:00
from .common import InfoExtractor
2015-03-18 18:47:07 +01:00
from ..utils import (
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 17:18:17 +01:00
sanitized_Request,
2015-03-18 18:47:07 +01:00
strip_jsonp,
unescapeHTML,
2015-06-18 07:59:37 +02:00
clean_html,
ExtractorError,
2015-03-18 18:47:07 +01:00
)
2015-03-17 12:03:29 +01:00
class QQMusicIE(InfoExtractor):
IE_NAME = 'qqmusic'
2015-07-10 18:52:07 +02:00
IE_DESC = 'QQ音乐'
_VALID_URL = r'https?://y.qq.com/#type=song&mid=(?P<id>[0-9A-Za-z]+)'
2015-03-17 12:03:29 +01:00
_TESTS = [{
'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
'md5': '9ce1c1c8445f561506d2e3cfb0255705',
2015-03-17 12:03:29 +01:00
'info_dict': {
'id': '004295Et37taLD',
'ext': 'mp3',
2015-03-17 12:03:29 +01:00
'title': '可惜没如果',
2015-09-26 17:08:23 +02:00
'release_date': '20141227',
2015-03-17 12:03:29 +01:00
'creator': '林俊杰',
'description': 'md5:d327722d0361576fde558f1ac68a7065',
'thumbnail': 're:^https?://.*\.jpg$',
}
}, {
'note': 'There is no mp3-320 version of this song.',
'url': 'http://y.qq.com/#type=song&mid=004MsGEo3DdNxV',
'md5': 'fa3926f0c585cda0af8fa4f796482e3e',
'info_dict': {
'id': '004MsGEo3DdNxV',
'ext': 'mp3',
'title': '如果',
2015-09-26 17:08:23 +02:00
'release_date': '20050626',
'creator': '李季美',
'description': 'md5:46857d5ed62bc4ba84607a805dccf437',
'thumbnail': 're:^https?://.*\.jpg$',
2015-03-17 12:03:29 +01:00
}
}, {
'note': 'lyrics not in .lrc format',
'url': 'http://y.qq.com/#type=song&mid=001JyApY11tIp6',
'info_dict': {
'id': '001JyApY11tIp6',
'ext': 'mp3',
'title': 'Shadows Over Transylvania',
2015-09-26 17:08:23 +02:00
'release_date': '19970225',
'creator': 'Dark Funeral',
'description': 'md5:ed14d5bd7ecec19609108052c25b2c11',
'thumbnail': 're:^https?://.*\.jpg$',
},
'params': {
'skip_download': True,
},
2015-03-17 12:03:29 +01:00
}]
_FORMATS = {
2015-06-05 00:04:26 +02:00
'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 06:56:02 +01:00
# 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 12:03:29 +01:00
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 07:59:33 +01:00
mid, note='Download song detail info',
errnote='Unable to get song detail info', encoding='gbk')
2015-03-17 12:03:29 +01:00
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 12:03:29 +01:00
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 12:03:29 +01:00
thumbnail_url = None
albummid = self._search_regex(
2015-06-18 15:13:03 +02:00
[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)
2015-03-18 06:56:02 +01:00
guid = self.m_r_get_ruin()
2015-03-17 12:03:29 +01:00
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 17:09:04 +02:00
self._check_formats(formats, mid)
self._sort_formats(formats)
2015-03-17 12:03:29 +01:00
actual_lrc_lyrics = ''.join(
line + '\n' for line in re.findall(
2015-09-26 17:15:34 +02:00
r'(?m)^(\[[0-9]{2}:[0-9]{2}(?:\.[0-9]{2,})?\][^\n]*|\[[^\]]*\])', lrc_content))
info_dict = {
2015-03-17 12:03:29 +01:00
'id': mid,
'formats': formats,
2015-03-17 12:03:29 +01:00
'title': song_name,
2015-09-26 17:08:23 +02:00
'release_date': publish_time,
2015-03-17 12:03:29 +01:00
'creator': singer,
'description': lrc_content,
'thumbnail': thumbnail_url
2015-03-17 12:03:29 +01:00
}
if actual_lrc_lyrics:
info_dict['subtitles'] = {
'origin': [{
'ext': 'lrc',
'data': actual_lrc_lyrics,
}]
}
return info_dict
2015-03-18 07:59:33 +01:00
2015-03-18 18:47:07 +01:00
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)
@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))
2015-03-18 18:47:07 +01:00
return entries
class QQMusicSingerIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:singer'
2015-07-10 19:21:36 +02:00
IE_DESC = 'QQ音乐 - 歌手'
_VALID_URL = r'https?://y.qq.com/#type=singer&mid=(?P<id>[0-9A-Za-z]+)'
2015-03-18 07:59:33 +01:00
_TEST = {
'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
'info_dict': {
'id': '001BLpXF2DyJe2',
'title': '林俊杰',
2016-01-02 15:39:09 +01:00
'description': 'md5:870ec08f7d8547c29c93010899103751',
2015-03-18 07:59:33 +01:00
},
'playlist_count': 12,
}
def _real_extract(self, url):
mid = self._match_id(url)
singer_page = self._download_webpage(
2015-03-18 18:47:07 +01:00
self.qq_static_url('singer', mid), mid, 'Download singer page')
2015-03-18 07:59:33 +01:00
2015-03-18 18:47:07 +01:00
entries = self.get_entries_from_page(singer_page)
2015-03-18 07:59:33 +01:00
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:
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 17:18:17 +01:00
req = sanitized_Request(
2015-03-18 07:59:33 +01:00
'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(
2015-03-18 18:47:07 +01:00
req, mid, 'Donwload singer description XML')
2015-03-18 07:59:33 +01:00
singer_desc = singer_desc_page.find('./data/info/desc').text
return self.playlist_result(entries, mid, singer_name, singer_desc)
2015-03-18 18:47:07 +01:00
class QQMusicAlbumIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:album'
2015-07-10 19:21:36 +02:00
IE_DESC = 'QQ音乐 - 专辑'
_VALID_URL = r'https?://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
2015-03-18 18:47:07 +01:00
2015-06-18 09:52:04 +02:00
_TESTS = [{
'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1',
2015-03-18 18:47:07 +01:00
'info_dict': {
'id': '000gXCTb2AhRR1',
'title': '我们都是这样长大的',
2015-07-06 11:08:32 +02:00
'description': 'md5:179c5dce203a5931970d306aa9607ea6',
2015-03-18 18:47:07 +01:00
},
'playlist_count': 4,
2015-06-18 09:52:04 +02:00
}, {
'url': 'http://y.qq.com/#type=album&mid=002Y5a3b3AlCu3',
'info_dict': {
'id': '002Y5a3b3AlCu3',
'title': '그리고...',
2015-07-06 11:08:32 +02:00
'description': 'md5:a48823755615508a95080e81b51ba729',
2015-06-18 09:52:04 +02:00
},
'playlist_count': 8,
}]
2015-03-18 18:47:07 +01:00
def _real_extract(self, url):
mid = self._match_id(url)
2015-06-18 09:52:04 +02:00
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(
'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
) for song in album['list']
]
album_name = album.get('name')
2015-06-18 09:52:04 +02:00
album_detail = album.get('desc')
2015-07-06 11:08:32 +02:00
if album_detail is not None:
album_detail = album_detail.strip()
2015-03-18 18:47:07 +01:00
return self.playlist_result(entries, mid, album_name, album_detail)
class QQMusicToplistIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:toplist'
2015-07-10 19:21:36 +02:00
IE_DESC = 'QQ音乐 - 排行榜'
_VALID_URL = r'https?://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
2015-05-14 17:25:43 +02:00
_TESTS = [{
2015-06-04 05:27:18 +02:00
'url': 'http://y.qq.com/#type=toplist&p=global_123',
'info_dict': {
2015-06-04 05:27:18 +02:00
'id': 'global_123',
'title': '美国iTunes榜',
},
'playlist_count': 10,
}, {
2015-06-04 05:27:18 +02:00
'url': 'http://y.qq.com/#type=toplist&p=top_3',
'info_dict': {
2015-06-04 05:27:18 +02:00
'id': 'top_3',
2016-01-02 15:39:09 +01:00
'title': '巅峰榜·欧美',
2015-06-04 05:27:18 +02:00
'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,
}, {
2015-06-04 05:27:18 +02:00
'url': 'http://y.qq.com/#type=toplist&p=global_106',
'info_dict': {
2015-06-04 05:27:18 +02:00
'id': 'global_106',
'title': '韩国Mnet榜',
},
'playlist_count': 50,
}]
def _real_extract(self, url):
list_id = self._match_id(url)
2015-05-14 17:28:42 +02:00
list_type, num_id = list_id.split("_")
2015-05-14 17:28:42 +02:00
toplist_json = self._download_json(
2015-06-04 05:27:18 +02:00
'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')
2015-06-04 05:27:18 +02:00
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')
2015-06-04 05:27:18 +02:00
return self.playlist_result(entries, list_id, list_name, list_description)
2015-06-18 07:59:37 +02:00
class QQMusicPlaylistIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:playlist'
2015-07-10 19:21:36 +02:00
IE_DESC = 'QQ音乐 - 歌单'
_VALID_URL = r'https?://y\.qq\.com/#type=taoge&id=(?P<id>[0-9]+)'
2015-06-18 07:59:37 +02:00
_TESTS = [{
2015-06-18 07:59:37 +02:00
'url': 'http://y.qq.com/#type=taoge&id=3462654915',
'info_dict': {
'id': '3462654915',
'title': '韩国5月新歌精选下旬',
'description': 'md5:d2c9d758a96b9888cf4fe82f603121d4',
},
'playlist_count': 40,
'skip': 'playlist gone',
}, {
'url': 'http://y.qq.com/#type=taoge&id=1374105607',
'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 07:59:37 +02:00
def _real_extract(self, url):
list_id = self._match_id(url)
list_json = self._download_json(
'http://i.y.qq.com/qzone-music/fcg-bin/fcg_ucc_getcdinfo_byids_cp.fcg?type=1&json=1&utf8=1&onlysong=0&disstid=%s'
% list_id, list_id, 'Download list page',
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]
2015-06-18 07:59:37 +02:00
entries = [
self.url_result(
'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid']
) for song in cdlist['songlist']
2015-06-18 07:59:37 +02:00
]
list_name = cdlist.get('dissname')
list_description = clean_html(unescapeHTML(cdlist.get('desc')))
2015-06-18 07:59:37 +02:00
return self.playlist_result(entries, list_id, list_name, list_description)