Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-22 16:44:32 +01:00
Code Issues Releases Wiki Activity

[qqmusic] Fix tests and cleanup

Browse Source
This commit is contained in:
Yen Chi Hsuan 2017-08-17 16:39:57 +08:00
parent d22b67f356
commit 25a6e769a1
1 changed files with 48 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

87
youtube_dl/extractor/qqmusic.py
View File

@ -7,11 +7,10 @@ import time
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
sanitized_Request,
strip_jsonp,
unescapeHTML,
clean_html, clean_html,
ExtractorError, ExtractorError,
strip_jsonp,
unescapeHTML,
) )
@ -21,14 +20,14 @@ class QQMusicIE(InfoExtractor):
_VALID_URL = r'https?://y\.qq\.com/n/yqq/song/(?P<id>[0-9A-Za-z]+)\.html' _VALID_URL = r'https?://y\.qq\.com/n/yqq/song/(?P<id>[0-9A-Za-z]+)\.html'
_TESTS = [{ _TESTS = [{
'url': 'https://y.qq.com/n/yqq/song/004295Et37taLD.html', 'url': 'https://y.qq.com/n/yqq/song/004295Et37taLD.html',
'md5': '9ce1c1c8445f561506d2e3cfb0255705', 'md5': '5f1e6cea39e182857da7ffc5ef5e6bb8',
'info_dict': { 'info_dict': {
'id': '004295Et37taLD', 'id': '004295Et37taLD',
'ext': 'mp3', 'ext': 'mp3',
'title': '可惜没如果', 'title': '可惜没如果',
'release_date': '20141227', 'release_date': '20141227',
'creator': '林俊杰', 'creator': '林俊杰',
'description': 'md5:d327722d0361576fde558f1ac68a7065', 'description': 'md5:d85afb3051952ecc50a1ee8a286d1eac',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
} }
}, { }, {
@ -53,7 +52,7 @@ class QQMusicIE(InfoExtractor):
'title': 'Shadows Over Transylvania', 'title': 'Shadows Over Transylvania',
'release_date': '19970225', 'release_date': '19970225',
'creator': 'Dark Funeral', 'creator': 'Dark Funeral',
'description': 'md5:ed14d5bd7ecec19609108052c25b2c11', 'description': 'md5:c9b20210587cbcd6836a1c597bab4525',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
}, },
'params': { 'params': {
@ -105,7 +104,7 @@ class QQMusicIE(InfoExtractor):
[r'albummid:\'([0-9a-zA-Z]+)\'', r'"albummid":"([0-9a-zA-Z]+)"'], [r'albummid:\'([0-9a-zA-Z]+)\'', r'"albummid":"([0-9a-zA-Z]+)"'],
detail_info_page, 'album mid', default=None) detail_info_page, 'album mid', default=None)
if albummid: if albummid:
thumbnail_url = "http://i.gtimg.cn/music/photo/mid_album_500/%s/%s/%s.jpg" \ thumbnail_url = 'http://i.gtimg.cn/music/photo/mid_album_500/%s/%s/%s.jpg' \
% (albummid[-2:-1], albummid[-1], albummid) % (albummid[-2:-1], albummid[-1], albummid)
guid = self.m_r_get_ruin() guid = self.m_r_get_ruin()
@ -158,8 +157,19 @@ class QQPlaylistBaseIE(InfoExtractor):
def get_singer_all_songs(self, singmid, num): def get_singer_all_songs(self, singmid, num):
return self._download_webpage( 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' % r'https://c.y.qq.com/v8/fcg-bin/fcg_v8_singer_track_cp.fcg', singmid,
(singmid, num), singmid) query={
'format': 'json',
'inCharset': 'utf8',
'outCharset': 'utf-8',
'platform': 'yqq',
'needNewCode': 0,
'singermid': singmid,
'order': 'listen',
'begin': 0,
'num': num,
'songstatus': 1,
})
def get_entries_from_page(self, singmid): def get_entries_from_page(self, singmid):
entries = [] entries = []
@ -176,7 +186,8 @@ class QQPlaylistBaseIE(InfoExtractor):
for item in json_obj_all_songs['data']['list']: for item in json_obj_all_songs['data']['list']:
if item['musicData'].get('songmid') is not None: if item['musicData'].get('songmid') is not None:
songmid = item['musicData']['songmid'] songmid = item['musicData']['songmid']
entries.append(self.url_result(r'https://y.qq.com/n/yqq/song/%s.html' % songmid, 'QQMusic', songmid)) entries.append(self.url_result(
r'https://y.qq.com/n/yqq/song/%s.html' % songmid, 'QQMusic', songmid))
return entries return entries
@ -192,7 +203,7 @@ class QQMusicSingerIE(QQPlaylistBaseIE):
'title': '林俊杰', 'title': '林俊杰',
'description': 'md5:870ec08f7d8547c29c93010899103751', 'description': 'md5:870ec08f7d8547c29c93010899103751',
}, },
'playlist_count': 12, 'playlist_mincount': 12,
} }
def _real_extract(self, url): def _real_extract(self, url):
@ -200,16 +211,16 @@ class QQMusicSingerIE(QQPlaylistBaseIE):
entries = self.get_entries_from_page(mid) entries = self.get_entries_from_page(mid)
singer_page = self._download_webpage(url, mid, 'Download singer page') 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_name = self._html_search_regex(
r"singername\s*:\s*'(.*?)'", singer_page, 'singer name', default=None)
singer_desc = None singer_desc = None
if mid: 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', 'https://y.qq.com/n/yqq/singer/')
singer_desc_page = self._download_xml( singer_desc_page = self._download_xml(
req, mid, 'Donwload singer description XML') '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/'})
singer_desc = singer_desc_page.find('./data/info/desc').text singer_desc = singer_desc_page.find('./data/info/desc').text
@ -267,26 +278,25 @@ class QQMusicToplistIE(QQPlaylistBaseIE):
_TESTS = [{ _TESTS = [{
'url': 'https://y.qq.com/n/yqq/toplist/123.html', 'url': 'https://y.qq.com/n/yqq/toplist/123.html',
'info_dict': { 'info_dict': {
'id': 'global_123', 'id': '123',
'title': '美国iTunes榜', 'title': '美国iTunes榜',
'description': 'md5:89db2335fdbb10678dee2d43fe9aba08',
}, },
'playlist_count': 10, 'playlist_count': 100,
}, { }, {
'url': 'https://y.qq.com/n/yqq/toplist/3.html', 'url': 'https://y.qq.com/n/yqq/toplist/3.html',
'info_dict': { 'info_dict': {
'id': 'top_3', 'id': '3',
'title': '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' 'description': 'md5:5a600d42c01696b26b71f8c4d43407da',
'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': 'https://y.qq.com/n/yqq/toplist/106.html', 'url': 'https://y.qq.com/n/yqq/toplist/106.html',
'info_dict': { 'info_dict': {
'id': 'global_106', 'id': '106',
'title': '韩国Mnet榜', 'title': '韩国Mnet榜',
'description': 'md5:cb84b325215e1d21708c615cac82a6e7',
}, },
'playlist_count': 50, 'playlist_count': 50,
}] }]
@ -298,16 +308,14 @@ class QQMusicToplistIE(QQPlaylistBaseIE):
num_id = list_id num_id = list_id
toplist_json = self._download_json( toplist_json = self._download_json(
'http://i.y.qq.com/v8/fcg-bin/fcg_v8_toplist_cp.fcg?type=%s&topid=%s&format=json' 'http://i.y.qq.com/v8/fcg-bin/fcg_v8_toplist_cp.fcg', list_id,
% (list_type, num_id), note='Download toplist page',
list_id, 'Download toplist page') query={'type': 'toplist', 'topid': list_id, 'format': 'json'})
entries = [ entries = [self.url_result(
self.url_result(
'https://y.qq.com/n/yqq/song/' + song['data']['songmid'] + '.html', 'QQMusic', 'https://y.qq.com/n/yqq/song/' + song['data']['songmid'] + '.html', 'QQMusic',
song['data']['songmid'] song['data']['songmid'])
) for song in toplist_json['songlist'] for song in toplist_json['songlist']]
]
topinfo = toplist_json.get('topinfo', {}) topinfo = toplist_json.get('topinfo', {})
list_name = topinfo.get('ListName') list_name = topinfo.get('ListName')
@ -343,8 +351,9 @@ class QQMusicPlaylistIE(QQPlaylistBaseIE):
list_id = self._match_id(url) list_id = self._match_id(url)
list_json = self._download_json( 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' 'http://i.y.qq.com/qzone-music/fcg-bin/fcg_ucc_getcdinfo_byids_cp.fcg',
% list_id, list_id, 'Download list page', list_id, 'Download list page',
query={'type': 1, 'json': 1, 'utf8': 1, 'onlysong': 0, 'disstid': list_id},
transform_source=strip_jsonp) transform_source=strip_jsonp)
if not len(list_json.get('cdlist', [])): if not len(list_json.get('cdlist', [])):
if list_json.get('code'): if list_json.get('code'):
@ -354,11 +363,9 @@ class QQMusicPlaylistIE(QQPlaylistBaseIE):
raise ExtractorError('Unable to get playlist info') raise ExtractorError('Unable to get playlist info')
cdlist = list_json['cdlist'][0] cdlist = list_json['cdlist'][0]
entries = [ entries = [self.url_result(
self.url_result( 'https://y.qq.com/n/yqq/song/' + song['songmid'] + '.html', 'QQMusic', song['songmid'])
'https://y.qq.com/n/yqq/song/' + song['songmid'] + '.html', 'QQMusic', song['songmid'] for song in cdlist['songlist']]
) for song in cdlist['songlist']
]
list_name = cdlist.get('dissname') list_name = cdlist.get('dissname')
list_description = clean_html(unescapeHTML(cdlist.get('desc'))) list_description = clean_html(unescapeHTML(cdlist.get('desc')))