X-Git-Url: http://git.cielonegro.org/gitweb.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fqqmusic.py;h=7513acba90bc10346dbc361bd8b5d017c08cbca0;hb=5d1bd3b907d22eab7c47b8b408c07a26dbc358ea;hp=1654a641f00db6833056571394b4dbe0b2856150;hpb=ac9ed061ec08ad360a0422ddb68060bdcc72baa2;p=youtube-dl.git diff --git a/youtube_dl/extractor/qqmusic.py b/youtube_dl/extractor/qqmusic.py index 1654a641f..7513acba9 100644 --- a/youtube_dl/extractor/qqmusic.py +++ b/youtube_dl/extractor/qqmusic.py @@ -2,47 +2,63 @@ 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, clean_html, + ExtractorError, ) -from ..compat import compat_urllib_request class QQMusicIE(InfoExtractor): IE_NAME = 'qqmusic' IE_DESC = 'QQ音乐' - _VALID_URL = r'http://y.qq.com/#type=song&mid=(?P[0-9A-Za-z]+)' + _VALID_URL = r'https?://y\.qq\.com/n/yqq/song/(?P[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': 're:^https?://.*\.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': 're:^https?://.*\.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 = { @@ -112,15 +128,27 @@ class QQMusicIE(InfoExtractor): 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): @@ -135,7 +163,8 @@ class QQPlaylistBaseIE(InfoExtractor): for item in re.findall(r'class="data"[^<>]*>([^<>]+)[0-9A-Za-z]+)' + _VALID_URL = r'https?://y\.qq\.com/n/yqq/singer/(?P[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, } @@ -174,7 +203,7 @@ class QQMusicSingerIE(QQPlaylistBaseIE): singer_desc = None if singer_id: - req = compat_urllib_request.Request( + req = sanitized_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) req.add_header( 'Referer', 'http://s.plcloud.music.qq.com/xhr_proxy_utf8.html') @@ -189,10 +218,10 @@ class QQMusicSingerIE(QQPlaylistBaseIE): class QQMusicAlbumIE(QQPlaylistBaseIE): IE_NAME = 'qqmusic:album' IE_DESC = 'QQ音乐 - 专辑' - _VALID_URL = r'http://y.qq.com/#type=album&mid=(?P[0-9A-Za-z]+)' + _VALID_URL = r'https?://y\.qq\.com/n/yqq/album/(?P[0-9A-Za-z]+)\.html' _TESTS = [{ - 'url': 'http://y.qq.com/#type=album&mid=000gXCTb2AhRR1', + 'url': 'https://y.qq.com/n/yqq/album/000gXCTb2AhRR1.html', 'info_dict': { 'id': '000gXCTb2AhRR1', 'title': '我们都是这样长大的', @@ -200,7 +229,7 @@ class QQMusicAlbumIE(QQPlaylistBaseIE): }, 'playlist_count': 4, }, { - 'url': 'http://y.qq.com/#type=album&mid=002Y5a3b3AlCu3', + 'url': 'https://y.qq.com/n/yqq/album/002Y5a3b3AlCu3.html', 'info_dict': { 'id': '002Y5a3b3AlCu3', 'title': '그리고...', @@ -218,7 +247,7 @@ class QQMusicAlbumIE(QQPlaylistBaseIE): entries = [ self.url_result( - 'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid'] + 'https://y.qq.com/n/yqq/song/' + song['songmid'] + ".html", 'QQMusic', song['songmid'] ) for song in album['list'] ] album_name = album.get('name') @@ -232,20 +261,20 @@ class QQMusicAlbumIE(QQPlaylistBaseIE): class QQMusicToplistIE(QQPlaylistBaseIE): IE_NAME = 'qqmusic:toplist' IE_DESC = 'QQ音乐 - 排行榜' - _VALID_URL = r'http://y\.qq\.com/#type=toplist&p=(?P(top|global)_[0-9]+)' + _VALID_URL = r'https?://y\.qq\.com/n/yqq/toplist/(?P[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：' @@ -253,7 +282,7 @@ class QQMusicToplistIE(QQPlaylistBaseIE): }, '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', @@ -264,7 +293,9 @@ class QQMusicToplistIE(QQPlaylistBaseIE): def _real_extract(self, url): list_id = self._match_id(url) - list_type, num_id = list_id.split("_") + # 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' @@ -273,7 +304,7 @@ class QQMusicToplistIE(QQPlaylistBaseIE): 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'] ] @@ -286,17 +317,26 @@ class QQMusicToplistIE(QQPlaylistBaseIE): class QQMusicPlaylistIE(QQPlaylistBaseIE): IE_NAME = 'qqmusic:playlist' IE_DESC = 'QQ音乐 - 歌单' - _VALID_URL = r'http://y\.qq\.com/#type=taoge&id=(?P[0-9]+)' + _VALID_URL = r'https?://y\.qq\.com/n/yqq/playlist/(?P[0-9]+)\.html' - _TEST = { - 'url': 'http://y.qq.com/#type=taoge&id=3462654915', + _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) @@ -304,14 +344,21 @@ class QQMusicPlaylistIE(QQPlaylistBaseIE): 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)['cdlist'][0] - + 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( - 'http://y.qq.com/#type=song&mid=' + song['songmid'], 'QQMusic', song['songmid'] - ) for song in list_json['songlist'] + 'https://y.qq.com/n/yqq/song/' + song['songmid'] + ".html", 'QQMusic', song['songmid'] + ) for song in cdlist['songlist'] ] - list_name = list_json.get('dissname') - list_description = clean_html(unescapeHTML(list_json.get('desc'))) + list_name = cdlist.get('dissname') + list_description = clean_html(unescapeHTML(cdlist.get('desc'))) return self.playlist_result(entries, list_id, list_name, list_description)