Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-08 09:10:09 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #5891 from ping/qqmusic-toplist-fix

Browse Source 
[qqmusic] Fix toplist extraction
This commit is contained in:
Yen Chi Hsuan 2015-06-05 00:50:59 +08:00
commit 168db222c6
1 changed files with 23 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
youtube_dl/extractor/qqmusic.py
View File

@ -9,7 +9,6 @@
from ..utils import ( from ..utils import (
strip_jsonp, strip_jsonp,
unescapeHTML, unescapeHTML,
js_to_json,
) )
from ..compat import compat_urllib_request from ..compat import compat_urllib_request
@ -181,60 +180,48 @@ class QQMusicToplistIE(QQPlaylistBaseIE):
_VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)' _VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P<id>(top|global)_[0-9]+)'
_TESTS = [{ _TESTS = [{
'url': 'http://y.qq.com/#type=toplist&p=global_12', 'url': 'http://y.qq.com/#type=toplist&p=global_123',
'info_dict': { 'info_dict': {
'id': 'global_12', 'id': 'global_123',
'title': 'itunes榜', 'title': '美国iTunes榜',
}, },
'playlist_count': 10, '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': { 'info_dict': {
'id': 'top_6', 'id': 'top_3',
'title': 'QQ音乐巅峰榜·欧美', '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, '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': { 'info_dict': {
'id': 'global_5', 'id': 'global_106',
'title': '韩国mnet排行榜', 'title': '韩国Mnet榜',
}, },
'playlist_count': 50, '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): def _real_extract(self, url):
list_id = self._match_id(url) list_id = self._match_id(url)
list_type, num_id = list_id.split("_") list_type, num_id = list_id.split("_")
list_page = self._download_webpage( toplist_json = self._download_json(
"http://y.qq.com/y/static/toplist/index/%s.html" % list_id, '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') list_id, 'Download toplist page')
entries = [] entries = [
if list_type == 'top': self.url_result(
jsonp_url = "http://y.qq.com/y/static/toplist/json/top/%s/1.js" % num_id 'http://y.qq.com/#type=song&mid=' + song['data']['songmid'], 'QQMusic', song['data']['songmid']
else: ) for song in toplist_json['songlist']
jsonp_url = "http://y.qq.com/y/static/toplist/json/global/%s/1_1.js" % num_id ]
toplist_json = self._download_json( list_name = toplist_json['topinfo']['ListName']
jsonp_url, list_id, note='Retrieve toplist json', list_description = toplist_json['topinfo']['info']
errnote='Unable to get toplist json', transform_source=self.strip_qq_jsonp) return self.playlist_result(entries, list_id, list_name, list_description)
for song in toplist_json['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'<h2 id="top_name">([^\']+)</h2>', list_page, 'top list name',
default=None)
return self.playlist_result(entries, list_id, list_name)