X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fkuwo.py;h=fa233377d67ee83bf71db61f14d0e934111174a3;hb=12bbd32ad0993d512ef798d5a56891d82fb29d12;hp=82d5f3f95058f1995d19661b6af08890b3b6102e;hpb=8726e046296d3f03f586c527f55bd03cffdbc363;p=youtube-dl diff --git a/youtube_dl/extractor/kuwo.py b/youtube_dl/extractor/kuwo.py index 82d5f3f95..fa233377d 100644 --- a/youtube_dl/extractor/kuwo.py +++ b/youtube_dl/extractor/kuwo.py @@ -9,35 +9,11 @@ from ..utils import ( get_element_by_id, clean_html, ExtractorError, + remove_start, ) -class KuwoIE(InfoExtractor): - IE_NAME = 'kuwo:song' - _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P[0-9]+?)/' - _TESTS = [{ - 'url': 'http://www.kuwo.cn/yinyue/635632/', - 'info_dict': { - 'id': '635632', - 'ext': 'ape', - 'title': '爱我别走', - 'creator': '张震岳', - 'upload_date': '20080122', - 'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c' - }, - }, { - 'url': 'http://www.kuwo.cn/yinyue/6446136/', - 'info_dict': { - 'id': '6446136', - 'ext': 'mp3', - 'title': '心', - 'creator': 'IU', - 'upload_date': '20150518', - }, - 'params': { - 'format': 'mp3-320' - }, - }] +class KuwoBaseIE(InfoExtractor): _FORMATS = [ {'format': 'ape', 'ext': 'ape', 'preference': 100}, {'format': 'mp3-320', 'ext': 'mp3', 'br': '320kmp3', 'abr': 320, 'preference': 80}, @@ -51,9 +27,9 @@ class KuwoIE(InfoExtractor): formats = [] for file_format in self._FORMATS: song_url = self._download_webpage( - "http://antiserver.kuwo.cn/anti.s?format=%s&br=%s&rid=MUSIC_%s&type=convert_url&response=url" % + '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"], + song_id, note='Download %s url info' % file_format['format'], ) if song_url.startswith('http://') or song_url.startswith('https://'): formats.append({ @@ -66,6 +42,35 @@ class KuwoIE(InfoExtractor): self._sort_formats(formats) return formats + +class KuwoIE(KuwoBaseIE): + IE_NAME = 'kuwo:song' + IE_DESC = '酷我音乐' + _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P\d+?)/' + _TESTS = [{ + 'url': 'http://www.kuwo.cn/yinyue/635632/', + 'info_dict': { + 'id': '635632', + 'ext': 'ape', + 'title': '爱我别走', + 'creator': '张震岳', + 'upload_date': '20080122', + 'description': 'md5:ed13f58e3c3bf3f7fd9fbc4e5a7aa75c' + }, + }, { + 'url': 'http://www.kuwo.cn/yinyue/6446136/', + 'info_dict': { + 'id': '6446136', + 'ext': 'mp3', + 'title': '心', + 'creator': 'IU', + 'upload_date': '20150518', + }, + 'params': { + 'format': 'mp3-320' + }, + }] + def _real_extract(self, url): song_id = self._match_id(url) webpage = self._download_webpage( @@ -73,30 +78,30 @@ class KuwoIE(InfoExtractor): errnote='Unable to get song detail info') song_name = self._html_search_regex( - r'

', webpage, 'song name') + r']+title="([^"]+)">', webpage, 'song name') singer_name = self._html_search_regex( - r'
.+?title="(.+?)".+?
', webpage, 'singer name', - flags=re.DOTALL, default=None) - lrc_content = clean_html(get_element_by_id("lrcContent", webpage)) + r']+class="s_img">\s*]+title="([^>]+)"', + webpage, 'singer name', fatal=False) + 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) album_id = self._html_search_regex( - r'

.+?]+class="album"[^<]+]+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('-', '') @@ -112,7 +117,8 @@ class KuwoIE(InfoExtractor): 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'http://www\.kuwo\.cn/album/(?P\d+?)/' _TEST = { 'url': 'http://www.kuwo.cn/album/502294/', 'info_dict': { @@ -131,15 +137,15 @@ class KuwoAlbumIE(InfoExtractor): errnote='Unable to get album info') album_name = self._html_search_regex( - r'

.+?

', webpage, - 'album name', flags=re.DOTALL) - album_intro = clean_html( - re.sub(r'^.+简介：', '', get_element_by_id("intro", webpage).strip())) + r']+class="comm"[^<]+]+title="([^"]+)"', webpage, + 'album name') + album_intro = remove_start( + 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'

', + 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) @@ -147,13 +153,14 @@ 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'http://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', + 'description': 're:\d{4}第\d{2}期', }, 'playlist_mincount': 10, } @@ -165,21 +172,21 @@ class KuwoChartIE(InfoExtractor): errnote='Unable to get chart info') chart_name = self._html_search_regex( - r'

(.+?)

', webpage, 'chart name') + r']+class="unDis">([^<]+)', webpage, 'chart name') chart_desc = self._html_search_regex( - r'

([0-9]{4}第[0-9]{2}期)

', webpage, 'chart desc') + 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'.+?', 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) class KuwoSingerIE(InfoExtractor): IE_NAME = 'kuwo:singer' + IE_DESC = '酷我音乐 - 歌手' _VALID_URL = r'http://www\.kuwo\.cn/mingxing/(?P[^/]+)' _TESTS = [{ 'url': 'http://www.kuwo.cn/mingxing/bruno+mars/', @@ -195,6 +202,7 @@ class KuwoSingerIE(InfoExtractor): 'title': 'Ali', }, 'playlist_mincount': 95, + 'skip': 'Regularly stalls travis build', # See https://travis-ci.org/rg3/youtube-dl/jobs/78878540 }] def _real_extract(self, url): @@ -204,11 +212,11 @@ class KuwoSingerIE(InfoExtractor): errnote='Unable to get singer info') singer_name = self._html_search_regex( - r'
[\n\s\t]*?

(.+?)\s*

([^<]+)]+href="(http://www\.kuwo\.cn/yinyue/\d+)/', webpage) ][:10 if first_page_only else None]) - if first_page_only or not re.search(r'下一页', webpage): + if first_page_only or not re.search(r']+href="[^"]+">下一页', webpage): break return self.playlist_result(entries, singer_id, singer_name) @@ -230,7 +237,8 @@ class KuwoSingerIE(InfoExtractor): 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'http://yinyue\.kuwo\.cn/yy/cinfo_(?P\d+?).htm' _TEST = { 'url': 'http://yinyue.kuwo.cn/yy/cinfo_86375.htm', 'info_dict': { @@ -248,27 +256,27 @@ class KuwoCategoryIE(InfoExtractor): errnote='Unable to get category info') category_name = self._html_search_regex( - r'

[^<>]+?

', webpage, 'category name') - - category_desc = re.sub( - r'^.+简介：', '', get_element_by_id("intro", webpage).strip()) - + r']+title="([^<>]+?)">[^<>]+?

', webpage, 'category name') + + category_desc = remove_start( + get_element_by_id('intro', webpage).strip(), + '%s简介：' % category_name) + jsonm = self._parse_json(self._html_search_regex( - r'var jsonm = (\{.+?\});', webpage, 'category songs'), category_id) + 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) -class KuwoMvIE(KuwoIE): +class KuwoMvIE(KuwoBaseIE): IE_NAME = 'kuwo:mv' - _VALID_URL = r'http://www\.kuwo\.cn/mv/(?P[0-9]+?)/' - _TESTS = [{ + IE_DESC = '酷我音乐 - MV' + _VALID_URL = r'http://www\.kuwo\.cn/mv/(?P\d+?)/' + _TEST = { 'url': 'http://www.kuwo.cn/mv/6480076/', 'info_dict': { 'id': '6480076', @@ -276,8 +284,8 @@ class KuwoMvIE(KuwoIE): 'title': '我们家MV', 'creator': '2PM', }, - }] - _FORMATS = KuwoIE._FORMATS + [ + } + _FORMATS = KuwoBaseIE._FORMATS + [ {'format': 'mkv', 'ext': 'mkv', 'preference': 250}, {'format': 'mp4', 'ext': 'mp4', 'preference': 200}, ] @@ -289,13 +297,13 @@ class KuwoMvIE(KuwoIE): errnote='Unable to get mv detail info: %s' % song_id) mobj = re.search( - r'

[^<>]+[^<>]+

', + r']+title="(?P[^"]+)">[^<]+]+title="(?P[^"]+)"', webpage) if mobj: 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)