from __future__ import unicode_literals
import random
-import time
import re
+import time
from .common import InfoExtractor
from ..utils import (
+ sanitized_Request,
strip_jsonp,
unescapeHTML,
- HEADRequest,
+ clean_html,
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]+)'
+ IE_DESC = 'QQ音乐'
+ _VALID_URL = r'https?://y\.qq\.com/n/yqq/song/(?P<id>[0-9A-Za-z]+)\.html'
_TESTS = [{
- 'url': 'http://y.qq.com/#type=song&mid=004295Et37taLD',
+ 'url': 'https://y.qq.com/n/yqq/song/004295Et37taLD.html',
'md5': '9ce1c1c8445f561506d2e3cfb0255705',
'info_dict': {
'id': '004295Et37taLD',
'ext': 'mp3',
'title': '可惜没如果',
- 'upload_date': '20141227',
+ 'release_date': '20141227',
'creator': '林俊杰',
'description': 'md5:d327722d0361576fde558f1ac68a7065',
- 'thumbnail': 'http://i.gtimg.cn/music/photo/mid_album_500/7/p/001IV22P1RDX7p.jpg',
+ 'thumbnail': r're:^https?://.*\.jpg$',
}
}, {
'note': 'There is no mp3-320 version of this song.',
- 'url': 'http://y.qq.com/#type=song&mid=004MsGEo3DdNxV',
+ 'url': 'https://y.qq.com/n/yqq/song/004MsGEo3DdNxV.html',
'md5': 'fa3926f0c585cda0af8fa4f796482e3e',
'info_dict': {
'id': '004MsGEo3DdNxV',
'ext': 'mp3',
'title': '如果',
- 'upload_date': '20050626',
+ 'release_date': '20050626',
'creator': '李季美',
'description': 'md5:46857d5ed62bc4ba84607a805dccf437',
- 'thumbnail': 'http://i.gtimg.cn/music/photo/mid_album_500/r/Q/0042owYj46IxrQ.jpg',
+ 'thumbnail': r're:^https?://.*\.jpg$',
}
+ }, {
+ 'note': 'lyrics not in .lrc format',
+ 'url': 'https://y.qq.com/n/yqq/song/001JyApY11tIp6.html',
+ 'info_dict': {
+ 'id': '001JyApY11tIp6',
+ 'ext': 'mp3',
+ 'title': 'Shadows Over Transylvania',
+ 'release_date': '19970225',
+ 'creator': 'Dark Funeral',
+ 'description': 'md5:ed14d5bd7ecec19609108052c25b2c11',
+ 'thumbnail': r're:^https?://.*\.jpg$',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
}]
_FORMATS = {
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'),
- })
+ 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'),
+ })
+ self._check_formats(formats, mid)
self._sort_formats(formats)
- return {
+ actual_lrc_lyrics = ''.join(
+ line + '\n' for line in re.findall(
+ r'(?m)^(\[[0-9]{2}:[0-9]{2}(?:\.[0-9]{2,})?\][^\n]*|\[[^\]]*\])', lrc_content))
+
+ info_dict = {
'id': mid,
'formats': formats,
'title': song_name,
- 'upload_date': publish_time,
+ 'release_date': publish_time,
'creator': singer,
'description': lrc_content,
- 'thumbnail': thumbnail_url,
+ 'thumbnail': thumbnail_url
}
+ if actual_lrc_lyrics:
+ info_dict['subtitles'] = {
+ 'origin': [{
+ 'ext': 'lrc',
+ 'data': actual_lrc_lyrics,
+ }]
+ }
+ return info_dict
class QQPlaylistBaseIE(InfoExtractor):
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):
+ def get_singer_all_songs(self, singmid, num):
+ return self._download_webpage(
+ r'https://c.y.qq.com/v8/fcg-bin/fcg_v8_singer_track_cp.fcg?format=json&inCharset=utf8&outCharset=utf-8&platform=yqq&needNewCode=0&singermid=%s&order=listen&begin=0&num=%s&songstatus=1' %
+ (singmid, num), singmid)
+
+ def get_entries_from_page(self, singmid):
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))
+ default_num = 1
+ json_text = self.get_singer_all_songs(singmid, default_num)
+ json_obj_all_songs = self._parse_json(json_text, singmid)
+
+ if json_obj_all_songs['code'] == 0:
+ total = json_obj_all_songs['data']['total']
+ json_text = self.get_singer_all_songs(singmid, total)
+ json_obj_all_songs = self._parse_json(json_text, singmid)
+
+ for item in json_obj_all_songs['data']['list']:
+ if item['musicData'].get('songmid') is not None:
+ songmid = item['musicData']['songmid']
+ entries.append(self.url_result(r'https://y.qq.com/n/yqq/song/%s.html' % songmid, 'QQMusic', songmid))
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]+)'
+ IE_DESC = 'QQ音乐 - 歌手'
+ _VALID_URL = r'https?://y\.qq\.com/n/yqq/singer/(?P<id>[0-9A-Za-z]+)\.html'
_TEST = {
- 'url': 'http://y.qq.com/#type=singer&mid=001BLpXF2DyJe2',
+ 'url': 'https://y.qq.com/n/yqq/singer/001BLpXF2DyJe2.html',
'info_dict': {
'id': '001BLpXF2DyJe2',
'title': '林俊杰',
- 'description': 'md5:2a222d89ba4455a3af19940c0481bb78',
+ 'description': 'md5:870ec08f7d8547c29c93010899103751',
},
'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)
-
+ entries = self.get_entries_from_page(mid)
+ singer_page = self._download_webpage(url, mid, 'Download singer page')
+ singer_name = self._html_search_regex(r"singername : '(.*?)'", singer_page, 'singer name', 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)
+ if mid:
+ req = sanitized_Request(
+ 'http://s.plcloud.music.qq.com/fcgi-bin/fcg_get_singer_desc.fcg?utf8=1&outCharset=utf-8&format=xml&singermid=%s' % mid)
req.add_header(
- 'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html')
+ 'Referer', 'https://y.qq.com/n/yqq/singer/')
singer_desc_page = self._download_xml(
req, mid, 'Donwload singer description XML')
class QQMusicAlbumIE(QQPlaylistBaseIE):
IE_NAME = 'qqmusic:album'
- _VALID_URL = r'http://y.qq.com/#type=album&mid=(?P<id>[0-9A-Za-z]+)'
+ IE_DESC = 'QQ音乐 - 专辑'
+ _VALID_URL = r'https?://y\.qq\.com/n/yqq/album/(?P<id>[0-9A-Za-z]+)\.html'
- _TEST = {
- 'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1&play=0',
+ _TESTS = [{
+ 'url': 'https://y.qq.com/n/yqq/album/000gXCTb2AhRR1.html',
'info_dict': {
'id': '000gXCTb2AhRR1',
'title': '我们都是这样长大的',
- 'description': 'md5:d216c55a2d4b3537fe4415b8767d74d6',
+ 'description': 'md5:179c5dce203a5931970d306aa9607ea6',
},
'playlist_count': 4,
- }
+ }, {
+ 'url': 'https://y.qq.com/n/yqq/album/002Y5a3b3AlCu3.html',
+ 'info_dict': {
+ 'id': '002Y5a3b3AlCu3',
+ 'title': '그리고...',
+ 'description': 'md5:a48823755615508a95080e81b51ba729',
+ },
+ 'playlist_count': 8,
+ }]
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 = 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']
- 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)
+ entries = [
+ self.url_result(
+ 'https://y.qq.com/n/yqq/song/' + song['songmid'] + '.html', 'QQMusic', song['songmid']
+ ) for song in album['list']
+ ]
+ album_name = album.get('name')
+ album_detail = album.get('desc')
+ if album_detail is not None:
+ album_detail = album_detail.strip()
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]+)'
+ IE_DESC = 'QQ音乐 - 排行榜'
+ _VALID_URL = r'https?://y\.qq\.com/n/yqq/toplist/(?P<id>[0-9]+)\.html'
_TESTS = [{
- 'url': 'http://y.qq.com/#type=toplist&p=global_123',
+ 'url': 'https://y.qq.com/n/yqq/toplist/123.html',
'info_dict': {
'id': 'global_123',
'title': '美国iTunes榜',
},
'playlist_count': 10,
}, {
- 'url': 'http://y.qq.com/#type=toplist&p=top_3',
+ 'url': 'https://y.qq.com/n/yqq/toplist/3.html',
'info_dict': {
'id': 'top_3',
- 'title': 'QQ音乐巅峰榜·欧美',
+ 'title': '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：'
},
'playlist_count': 100,
}, {
- 'url': 'http://y.qq.com/#type=toplist&p=global_106',
+ 'url': 'https://y.qq.com/n/yqq/toplist/106.html',
'info_dict': {
'id': 'global_106',
'title': '韩国Mnet榜',
def _real_extract(self, url):
list_id = self._match_id(url)
- list_type, num_id = list_id.split("_")
+ list_type = 'toplist'
+ num_id = 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'
entries = [
self.url_result(
- 'http://y.qq.com/#type=song&mid=' + song['data']['songmid'], 'QQMusic', song['data']['songmid']
+ 'https://y.qq.com/n/yqq/song/' + song['data']['songmid'] + '.html', 'QQMusic',
+ song['data']['songmid']
) for song in toplist_json['songlist']
]
list_name = topinfo.get('ListName')
list_description = topinfo.get('info')
return self.playlist_result(entries, list_id, list_name, list_description)
+
+
+class QQMusicPlaylistIE(QQPlaylistBaseIE):
+ IE_NAME = 'qqmusic:playlist'
+ IE_DESC = 'QQ音乐 - 歌单'
+ _VALID_URL = r'https?://y\.qq\.com/n/yqq/playlist/(?P<id>[0-9]+)\.html'
+
+ _TESTS = [{
+ 'url': 'http://y.qq.com/n/yqq/playlist/3462654915.html',
+ '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': '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,
+ }]
+
+ 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]
+ entries = [
+ self.url_result(
+ 'https://y.qq.com/n/yqq/song/' + song['songmid'] + '.html', 'QQMusic', song['songmid']
+ ) for song in cdlist['songlist']
+ ]
+
+ list_name = cdlist.get('dissname')
+ list_description = clean_html(unescapeHTML(cdlist.get('desc')))
+ return self.playlist_result(entries, list_id, list_name, list_description)
projects / youtube-dl / blobdiff