X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fkuwo.py;h=cc5b2a1c177addf3465f2e9b2f65569f7617053b;hb=067aa17edf5a46a8cbc4d6b90864eddf051fa2bc;hp=928f7f62d257ef062e39561ae8e4c53589e56f14;hpb=a9684c0dbf3879478fd223ce7594d58be7dffa4f;p=youtube-dl diff --git a/youtube_dl/extractor/kuwo.py b/youtube_dl/extractor/kuwo.py index 928f7f62d..cc5b2a1c1 100644 --- a/youtube_dl/extractor/kuwo.py +++ b/youtube_dl/extractor/kuwo.py @@ -2,13 +2,14 @@ from __future__ import unicode_literals import re -import itertools from .common import InfoExtractor +from ..compat import compat_urlparse from ..utils import ( get_element_by_id, clean_html, ExtractorError, + InAdvancePagedList, remove_start, ) @@ -23,14 +24,26 @@ class KuwoBaseIE(InfoExtractor): {'format': 'aac', 'ext': 'aac', 'abr': 48, 'preference': 10} ] - def _get_formats(self, song_id): + def _get_formats(self, song_id, tolerate_ip_deny=False): formats = [] for file_format in self._FORMATS: + query = { + 'format': file_format['ext'], + 'br': file_format.get('br', ''), + 'rid': 'MUSIC_%s' % song_id, + 'type': 'convert_url', + 'response': 'url' + } + song_url = self._download_webpage( - "http://antiserver.kuwo.cn/anti.s?format=%s&br=%s&rid=MUSIC_%s&type=convert_url&response=url" % - (file_format['ext'], file_format.get('br', ''), song_id), - song_id, note="Download %s url info" % file_format["format"], + 'http://antiserver.kuwo.cn/anti.s', + song_id, note='Download %s url info' % file_format['format'], + query=query, headers=self.geo_verification_headers(), ) + + if song_url == 'IPDeny' and not tolerate_ip_deny: + raise ExtractorError('This song is blocked in this region', expected=True) + if song_url.startswith('http://') or song_url.startswith('https://'): formats.append({ 'url': song_url, @@ -39,13 +52,14 @@ class KuwoBaseIE(InfoExtractor): 'preference': file_format['preference'], 'abr': file_format.get('abr'), }) - self._sort_formats(formats) + return formats class KuwoIE(KuwoBaseIE): IE_NAME = 'kuwo:song' - _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P[0-9]+?)/' + IE_DESC = '酷我音乐' + _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/yinyue/(?P\d+)' _TESTS = [{ 'url': 'http://www.kuwo.cn/yinyue/635632/', 'info_dict': { @@ -56,51 +70,59 @@ class KuwoIE(KuwoBaseIE): 'upload_date': '20080122', 'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c' }, + 'skip': 'this song has been offline because of copyright issues', }, { 'url': 'http://www.kuwo.cn/yinyue/6446136/', 'info_dict': { 'id': '6446136', 'ext': 'mp3', 'title': '心', + 'description': 'md5:5d0e947b242c35dc0eb1d2fce9fbf02c', 'creator': 'IU', 'upload_date': '20150518', }, 'params': { - 'format': 'mp3-320' + 'format': 'mp3-320', }, + }, { + 'url': 'http://www.kuwo.cn/yinyue/3197154?catalog=yueku2016', + 'only_matching': True, }] def _real_extract(self, url): song_id = self._match_id(url) - webpage = self._download_webpage( + webpage, urlh = self._download_webpage_handle( url, song_id, note='Download song detail info', errnote='Unable to get song detail info') + if song_id not in urlh.geturl() or '对不起，该歌曲由于版权问题已被下线，将返回网站首页' in webpage: + raise ExtractorError('this song has been offline because of copyright issues', expected=True) song_name = self._html_search_regex( - r']+title="([^"]+)">', webpage, 'song name') - singer_name = self._html_search_regex( - r']+class="s_img">\s*]+title="([^>]+)"', - webpage, 'singer name', default=None) - lrc_content = clean_html(get_element_by_id("lrcContent", webpage)) + r']+id="lrcName">([^<]+)

', webpage, 'song name') + singer_name = remove_start(self._html_search_regex( + r']+href="http://www\.kuwo\.cn/artist/content\?name=([^"]+)">', + webpage, 'singer name', fatal=False), '歌手') + lrc_content = clean_html(get_element_by_id('lrcContent', webpage)) if lrc_content == '暂无': # indicates no lyrics lrc_content = None formats = self._get_formats(song_id) + self._sort_formats(formats) album_id = self._html_search_regex( - r']+class="album"[^<]+]+href="http://www\.kuwo\.cn/album/(\d+)/"', - webpage, 'album id', default=None, fatal=False) + r']+href="http://www\.kuwo\.cn/album/(\d+)/"', + webpage, 'album id', fatal=False) publish_time = None if album_id is not None: album_info_page = self._download_webpage( - "http://www.kuwo.cn/album/%s/" % album_id, song_id, + 'http://www.kuwo.cn/album/%s/' % album_id, song_id, note='Download album detail info', errnote='Unable to get album detail info') publish_time = self._html_search_regex( r'发行时间：(\d{4}-\d{2}-\d{2})', album_info_page, - 'publish time', default=None) + 'publish time', fatal=False) if publish_time: publish_time = publish_time.replace('-', '') @@ -116,13 +138,14 @@ class KuwoIE(KuwoBaseIE): class KuwoAlbumIE(InfoExtractor): IE_NAME = 'kuwo:album' - _VALID_URL = r'http://www\.kuwo\.cn/album/(?P[0-9]+?)/' + IE_DESC = '酷我音乐 - 专辑' + _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/album/(?P\d+?)/' _TEST = { 'url': 'http://www.kuwo.cn/album/502294/', 'info_dict': { 'id': '502294', - 'title': 'M', - 'description': 'md5:6a7235a84cc6400ec3b38a7bdaf1d60c', + 'title': 'Made\xa0Series\xa0《M》', + 'description': 'md5:d463f0d8a0ff3c3ea3d6ed7452a9483f', }, 'playlist_count': 2, } @@ -138,13 +161,12 @@ class KuwoAlbumIE(InfoExtractor): r']+class="comm"[^<]+]+title="([^"]+)"', webpage, 'album name') album_intro = remove_start( - clean_html(get_element_by_id("intro", webpage)), + clean_html(get_element_by_id('intro', webpage)), '%s简介：' % album_name) entries = [ - self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id) - for song_id in re.findall( - r']+class="listen">]+href="http://www\.kuwo\.cn/yinyue/(\d+)/"', + self.url_result(song_url, 'Kuwo') for song_url in re.findall( + r']+class="listen">]+href="(http://www\.kuwo\.cn/yinyue/\d+/)"', webpage) ] return self.playlist_result(entries, album_id, album_name, album_intro) @@ -152,15 +174,14 @@ class KuwoAlbumIE(InfoExtractor): class KuwoChartIE(InfoExtractor): IE_NAME = 'kuwo:chart' - _VALID_URL = r'http://yinyue\.kuwo\.cn/billboard_(?P[^.]+).htm' + IE_DESC = '酷我音乐 - 排行榜' + _VALID_URL = r'https?://yinyue\.kuwo\.cn/billboard_(?P[^.]+).htm' _TEST = { 'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm', 'info_dict': { 'id': '香港中文龙虎榜', - 'title': '香港中文龙虎榜', - 'description': 're:[0-9]{4}第[0-9]{2}期', }, - 'playlist_mincount': 10, + 'playlist_mincount': 7, } def _real_extract(self, url): @@ -169,30 +190,24 @@ class KuwoChartIE(InfoExtractor): url, chart_id, note='Download chart info', errnote='Unable to get chart info') - chart_name = self._html_search_regex( - r']+class="unDis">([^<]+)', webpage, 'chart name') - - chart_desc = self._html_search_regex( - r']+class="tabDef">(\d{4}第\d{2}期)

', webpage, 'chart desc') - entries = [ - self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id) - for song_id in re.findall( - r']+href="http://www\.kuwo\.cn/yinyue/(\d+)/"', webpage) + self.url_result(song_url, 'Kuwo') for song_url in re.findall( + r']+href="(http://www\.kuwo\.cn/yinyue/\d+)', webpage) ] - return self.playlist_result(entries, chart_id, chart_name, chart_desc) + return self.playlist_result(entries, chart_id) class KuwoSingerIE(InfoExtractor): IE_NAME = 'kuwo:singer' - _VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P[^/]+)' + IE_DESC = '酷我音乐 - 歌手' + _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mingxing/(?P[^/]+)' _TESTS = [{ 'url': 'http://www.kuwo.cn/mingxing/bruno+mars/', 'info_dict': { 'id': 'bruno+mars', - 'title': 'Bruno Mars', + 'title': 'Bruno\xa0Mars', }, - 'playlist_count': 10, + 'playlist_mincount': 329, }, { 'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm', 'info_dict': { @@ -200,8 +215,11 @@ class KuwoSingerIE(InfoExtractor): 'title': 'Ali', }, 'playlist_mincount': 95, + 'skip': 'Regularly stalls travis build', # See https://travis-ci.org/ytdl-org/youtube-dl/jobs/78878540 }] + PAGE_SIZE = 15 + def _real_extract(self, url): singer_id = self._match_id(url) webpage = self._download_webpage( @@ -209,33 +227,37 @@ class KuwoSingerIE(InfoExtractor): errnote='Unable to get singer info') singer_name = self._html_search_regex( - r'
\s*

([^<]+)([^<]+)

', webpage, 'singer name') + + artist_id = self._html_search_regex( + r'data-artistid="(\d+)"', webpage, 'artist id') - entries = [] - first_page_only = False if re.search(r'/music(?:_[0-9]+)?\.htm', url) else True - for page_num in itertools.count(1): + page_count = int(self._html_search_regex( + r'data-page="(\d+)"', webpage, 'page count')) + + def page_func(page_num): webpage = self._download_webpage( - 'http://www.kuwo.cn/mingxing/%s/music_%d.htm' % (singer_id, page_num), - singer_id, note='Download song list page #%d' % page_num, - errnote='Unable to get song list page #%d' % page_num) - - entries.extend([ - self.url_result("http://www.kuwo.cn/yinyue/%s/" % song_id, 'Kuwo', song_id) - for song_id in re.findall( - r']+class="m_name">]+href="http://www\.kuwo\.cn/yinyue/([0-9]+)/', + 'http://www.kuwo.cn/artist/contentMusicsAjax', + singer_id, note='Download song list page #%d' % (page_num + 1), + errnote='Unable to get song list page #%d' % (page_num + 1), + query={'artistId': artist_id, 'pn': page_num, 'rn': self.PAGE_SIZE}) + + return [ + self.url_result(compat_urlparse.urljoin(url, song_url), 'Kuwo') + for song_url in re.findall( + r']+class="name">]+href="(/yinyue/\d+)', webpage) - ][:10 if first_page_only else None]) + ] - if first_page_only or not re.search(r']+href="[^"]+">下一页', webpage): - break + entries = InAdvancePagedList(page_func, page_count, self.PAGE_SIZE) return self.playlist_result(entries, singer_id, singer_name) class KuwoCategoryIE(InfoExtractor): IE_NAME = 'kuwo:category' - _VALID_URL = r'http://yinyue\.kuwo\.cn/yy/cinfo_(?P[0-9]+?).htm' + IE_DESC = '酷我音乐 - 分类' + _VALID_URL = r'https?://yinyue\.kuwo\.cn/yy/cinfo_(?P\d+?).htm' _TEST = { 'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm', 'info_dict': { @@ -243,7 +265,7 @@ class KuwoCategoryIE(InfoExtractor): 'title': '八十年代精选', 'description': '这些都是属于八十年代的回忆！', }, - 'playlist_count': 30, + 'playlist_mincount': 24, } def _real_extract(self, url): @@ -256,16 +278,16 @@ class KuwoCategoryIE(InfoExtractor): r']+title="([^<>]+?)">[^<>]+?', webpage, 'category name') category_desc = remove_start( - get_element_by_id("intro", webpage).strip(), + get_element_by_id('intro', webpage).strip(), '%s简介：' % category_name) + if category_desc == '暂无': + category_desc = None jsonm = self._parse_json(self._html_search_regex( r'var\s+jsonm\s*=\s*([^;]+);', webpage, 'category songs'), category_id) entries = [ - self.url_result( - "http://www.kuwo.cn/yinyue/%s/" % song['musicrid'], - 'Kuwo', song['musicrid']) + self.url_result('http://www.kuwo.cn/yinyue/%s/' % song['musicrid'], 'Kuwo') for song in jsonm['musiclist'] ] return self.playlist_result(entries, category_id, category_name, category_desc) @@ -273,15 +295,22 @@ class KuwoCategoryIE(InfoExtractor): class KuwoMvIE(KuwoBaseIE): IE_NAME = 'kuwo:mv' - _VALID_URL = r'http://www\.kuwo\.cn/mv/(?P[0-9]+?)/' + IE_DESC = '酷我音乐 - MV' + _VALID_URL = r'https?://(?:www\.)?kuwo\.cn/mv/(?P\d+?)/' _TEST = { 'url': 'http://www.kuwo.cn/mv/6480076/', 'info_dict': { 'id': '6480076', - 'ext': 'mkv', - 'title': '我们家MV', + 'ext': 'mp4', + 'title': 'My HouseMV', 'creator': '2PM', }, + # In this video, music URLs (anti.s) are blocked outside China and + # USA, while the MV URL (mvurl) is available globally, so force the MV + # URL for consistent results in different countries + 'params': { + 'format': 'mv', + }, } _FORMATS = KuwoBaseIE._FORMATS + [ {'format': 'mkv', 'ext': 'mkv', 'preference': 250}, @@ -301,9 +330,19 @@ class KuwoMvIE(KuwoBaseIE): song_name = mobj.group('song') singer_name = mobj.group('singer') else: - raise ExtractorError("Unable to find song or singer names") + raise ExtractorError('Unable to find song or singer names') - formats = self._get_formats(song_id) + formats = self._get_formats(song_id, tolerate_ip_deny=True) + + mv_url = self._download_webpage( + 'http://www.kuwo.cn/yy/st/mvurl?rid=MUSIC_%s' % song_id, + song_id, note='Download %s MV URL' % song_id) + formats.append({ + 'url': mv_url, + 'format_id': 'mv', + }) + + self._sort_formats(formats) return { 'id': song_id,