X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9dc487f48b50767cf540fa36c3de2c386fd74c04..HEAD:/youtube_dl/extractor/mixcloud.py diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index 560fe18..9759560 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -1,47 +1,60 @@ from __future__ import unicode_literals -import base64 -import functools import itertools import re from .common import InfoExtractor from ..compat import ( + compat_b64decode, compat_chr, compat_ord, + compat_str, compat_urllib_parse_unquote, - compat_urlparse, + compat_zip ) from ..utils import ( - clean_html, - ExtractorError, - OnDemandPagedList, - parse_count, - str_to_int, + int_or_none, + parse_iso8601, + strip_or_none, + try_get, ) -class MixcloudIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)' +class MixcloudBaseIE(InfoExtractor): + def _call_api(self, object_type, object_fields, display_id, username, slug=None): + lookup_key = object_type + 'Lookup' + return self._download_json( + 'https://www.mixcloud.com/graphql', display_id, query={ + 'query': '''{ + %s(lookup: {username: "%s"%s}) { + %s + } +}''' % (lookup_key, username, ', slug: "%s"' % slug if slug else '', object_fields) + })['data'][lookup_key] + + +class MixcloudIE(MixcloudBaseIE): + _VALID_URL = r'https?://(?:(?:www|beta|m)\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)' IE_NAME = 'mixcloud' _TESTS = [{ 'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/', 'info_dict': { - 'id': 'dholbach-cryptkeeper', + 'id': 'dholbach_cryptkeeper', 'ext': 'm4a', 'title': 'Cryptkeeper', 'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.', 'uploader': 'Daniel Holbach', 'uploader_id': 'dholbach', - 'thumbnail': 're:https?://.*\.jpg', + 'thumbnail': r're:https?://.*\.jpg', 'view_count': int, - 'like_count': int, + 'timestamp': 1321359578, + 'upload_date': '20111115', }, }, { 'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/', 'info_dict': { - 'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat', + 'id': 'gillespeterson_caribou-7-inch-vinyl-mix-chat', 'ext': 'mp3', 'title': 'Caribou 7 inch Vinyl Mix & Chat', 'description': 'md5:2b8aec6adce69f9d41724647c65875e8', @@ -49,110 +62,210 @@ class MixcloudIE(InfoExtractor): 'uploader_id': 'gillespeterson', 'thumbnail': 're:https?://.*', 'view_count': int, - 'like_count': int, + 'timestamp': 1422987057, + 'upload_date': '20150203', }, + }, { + 'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/', + 'only_matching': True, }] + _DECRYPTION_KEY = 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD' - # See https://www.mixcloud.com/media/js2/www_js_2.9e23256562c080482435196ca3975ab5.js @staticmethod - def _decrypt_play_info(play_info): - KEY = 'pleasedontdownloadourmusictheartistswontgetpaid' - - play_info = base64.b64decode(play_info.encode('ascii')) - + def _decrypt_xor_cipher(key, ciphertext): + """Encrypt/Decrypt XOR cipher. Both ways are possible because it's XOR.""" return ''.join([ - compat_chr(compat_ord(ch) ^ compat_ord(KEY[idx % len(KEY)])) - for idx, ch in enumerate(play_info)]) + compat_chr(compat_ord(ch) ^ compat_ord(k)) + for ch, k in compat_zip(ciphertext, itertools.cycle(key))]) def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - uploader = mobj.group(1) - cloudcast_name = mobj.group(2) - track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name))) - - webpage = self._download_webpage(url, track_id) - - message = self._html_search_regex( - r'(?s)]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)', - webpage, 'error message', default=None) - - encrypted_play_info = self._search_regex( - r'm-play-info="([^"]+)"', webpage, 'play info') - play_info = self._parse_json( - self._decrypt_play_info(encrypted_play_info), track_id) - - if message and 'stream_url' not in play_info: - raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True) - - song_url = play_info['stream_url'] - - PREFIX = ( - r'm-play-on-spacebar[^>]+' - r'(?:\s+[a-zA-Z0-9-]+(?:="[^"]+")?)*?\s+') - title = self._html_search_regex( - PREFIX + r'm-title="([^"]+)"', webpage, 'title') - thumbnail = self._proto_relative_url(self._html_search_regex( - PREFIX + r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail', - fatal=False)) - uploader = self._html_search_regex( - PREFIX + r'm-owner-name="([^"]+)"', - webpage, 'uploader', fatal=False) - uploader_id = self._search_regex( - r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False) - description = self._og_search_description(webpage) - like_count = parse_count(self._search_regex( - r'\bbutton-favorite[^>]+>.*?]+class=["\']toggle-number[^>]+>\s*([^<]+)', - webpage, 'like count', default=None)) - view_count = str_to_int(self._search_regex( - [r'([0-9,.]+)'], - webpage, 'play count', default=None)) + username, slug = re.match(self._VALID_URL, url).groups() + username, slug = compat_urllib_parse_unquote(username), compat_urllib_parse_unquote(slug) + track_id = '%s_%s' % (username, slug) + + cloudcast = self._call_api('cloudcast', '''audioLength + comments(first: 100) { + edges { + node { + comment + created + user { + displayName + username + } + } + } + totalCount + } + description + favorites { + totalCount + } + featuringArtistList + isExclusive + name + owner { + displayName + url + username + } + picture(width: 1024, height: 1024) { + url + } + plays + publishDate + reposts { + totalCount + } + streamInfo { + dashUrl + hlsUrl + url + } + tags { + tag { + name + } + }''', track_id, username, slug) + + title = cloudcast['name'] + + stream_info = cloudcast['streamInfo'] + formats = [] + + for url_key in ('url', 'hlsUrl', 'dashUrl'): + format_url = stream_info.get(url_key) + if not format_url: + continue + decrypted = self._decrypt_xor_cipher( + self._DECRYPTION_KEY, compat_b64decode(format_url)) + if url_key == 'hlsUrl': + formats.extend(self._extract_m3u8_formats( + decrypted, track_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls', fatal=False)) + elif url_key == 'dashUrl': + formats.extend(self._extract_mpd_formats( + decrypted, track_id, mpd_id='dash', fatal=False)) + else: + formats.append({ + 'format_id': 'http', + 'url': decrypted, + 'downloader_options': { + # Mixcloud starts throttling at >~5M + 'http_chunk_size': 5242880, + }, + }) + + if not formats and cloudcast.get('isExclusive'): + self.raise_login_required() + + self._sort_formats(formats) + + comments = [] + for edge in (try_get(cloudcast, lambda x: x['comments']['edges']) or []): + node = edge.get('node') or {} + text = strip_or_none(node.get('comment')) + if not text: + continue + user = node.get('user') or {} + comments.append({ + 'author': user.get('displayName'), + 'author_id': user.get('username'), + 'text': text, + 'timestamp': parse_iso8601(node.get('created')), + }) + + tags = [] + for t in cloudcast.get('tags'): + tag = try_get(t, lambda x: x['tag']['name'], compat_str) + if not tag: + tags.append(tag) + + get_count = lambda x: int_or_none(try_get(cloudcast, lambda y: y[x]['totalCount'])) + + owner = cloudcast.get('owner') or {} return { 'id': track_id, 'title': title, - 'url': song_url, - 'description': description, - 'thumbnail': thumbnail, - 'uploader': uploader, - 'uploader_id': uploader_id, - 'view_count': view_count, - 'like_count': like_count, + 'formats': formats, + 'description': cloudcast.get('description'), + 'thumbnail': try_get(cloudcast, lambda x: x['picture']['url'], compat_str), + 'uploader': owner.get('displayName'), + 'timestamp': parse_iso8601(cloudcast.get('publishDate')), + 'uploader_id': owner.get('username'), + 'uploader_url': owner.get('url'), + 'duration': int_or_none(cloudcast.get('audioLength')), + 'view_count': int_or_none(cloudcast.get('plays')), + 'like_count': get_count('favorites'), + 'repost_count': get_count('reposts'), + 'comment_count': get_count('comments'), + 'comments': comments, + 'tags': tags, + 'artist': ', '.join(cloudcast.get('featuringArtistList') or []) or None, } -class MixcloudPlaylistBaseIE(InfoExtractor): - _PAGE_SIZE = 24 +class MixcloudPlaylistBaseIE(MixcloudBaseIE): + def _get_cloudcast(self, node): + return node - def _find_urls_in_page(self, page): - for url in re.findall(r'm-play-button m-url="(?P[^"]+)"', page): - yield self.url_result( - compat_urlparse.urljoin('https://www.mixcloud.com', clean_html(url)), - MixcloudIE.ie_key()) + def _get_playlist_title(self, title, slug): + return title - def _fetch_tracks_page(self, path, video_id, page_name, current_page, real_page_number=None): - real_page_number = real_page_number or current_page + 1 - return self._download_webpage( - 'https://www.mixcloud.com/%s/' % path, video_id, - note='Download %s (page %d)' % (page_name, current_page + 1), - errnote='Unable to download %s' % page_name, - query={'page': real_page_number, 'list': 'main', '_ajax': '1'}, - headers={'X-Requested-With': 'XMLHttpRequest'}) - - def _tracks_page_func(self, page, video_id, page_name, current_page): - resp = self._fetch_tracks_page(page, video_id, page_name, current_page) - - for item in self._find_urls_in_page(resp): - yield item + def _real_extract(self, url): + username, slug = re.match(self._VALID_URL, url).groups() + username = compat_urllib_parse_unquote(username) + if not slug: + slug = 'uploads' + else: + slug = compat_urllib_parse_unquote(slug) + playlist_id = '%s_%s' % (username, slug) + + is_playlist_type = self._ROOT_TYPE == 'playlist' + playlist_type = 'items' if is_playlist_type else slug + list_filter = '' + + has_next_page = True + entries = [] + while has_next_page: + playlist = self._call_api( + self._ROOT_TYPE, '''%s + %s + %s(first: 100%s) { + edges { + node { + %s + } + } + pageInfo { + endCursor + hasNextPage + } + }''' % (self._TITLE_KEY, self._DESCRIPTION_KEY, playlist_type, list_filter, self._NODE_TEMPLATE), + playlist_id, username, slug if is_playlist_type else None) + + items = playlist.get(playlist_type) or {} + for edge in items.get('edges', []): + cloudcast = self._get_cloudcast(edge.get('node') or {}) + cloudcast_url = cloudcast.get('url') + if not cloudcast_url: + continue + entries.append(self.url_result( + cloudcast_url, MixcloudIE.ie_key(), cloudcast.get('slug'))) + + page_info = items['pageInfo'] + has_next_page = page_info['hasNextPage'] + list_filter = ', after: "%s"' % page_info['endCursor'] - def _get_user_description(self, page_content): - return self._html_search_regex( - r']+class="description-text"[^>]*>(.+?)', - page_content, 'user description', fatal=False) + return self.playlist_result( + entries, playlist_id, + self._get_playlist_title(playlist[self._TITLE_KEY], slug), + playlist.get(self._DESCRIPTION_KEY)) class MixcloudUserIE(MixcloudPlaylistBaseIE): - _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P[^/]+)/(?Puploads|favorites|listens)?/?$' + _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P[^/]+)/(?Puploads|favorites|listens|stream)?/?$' IE_NAME = 'mixcloud:user' _TESTS = [{ @@ -160,160 +273,79 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE): 'info_dict': { 'id': 'dholbach_uploads', 'title': 'Daniel Holbach (uploads)', - 'description': 'md5:327af72d1efeb404a8216c27240d1370', + 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', }, - 'playlist_mincount': 11, + 'playlist_mincount': 36, }, { 'url': 'http://www.mixcloud.com/dholbach/uploads/', 'info_dict': { 'id': 'dholbach_uploads', 'title': 'Daniel Holbach (uploads)', - 'description': 'md5:327af72d1efeb404a8216c27240d1370', + 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', }, - 'playlist_mincount': 11, + 'playlist_mincount': 36, }, { 'url': 'http://www.mixcloud.com/dholbach/favorites/', 'info_dict': { 'id': 'dholbach_favorites', 'title': 'Daniel Holbach (favorites)', - 'description': 'md5:327af72d1efeb404a8216c27240d1370', - }, - 'params': { - 'playlist_items': '1-100', + 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', }, - 'playlist_mincount': 100, + # 'params': { + # 'playlist_items': '1-100', + # }, + 'playlist_mincount': 396, }, { 'url': 'http://www.mixcloud.com/dholbach/listens/', 'info_dict': { 'id': 'dholbach_listens', 'title': 'Daniel Holbach (listens)', - 'description': 'md5:327af72d1efeb404a8216c27240d1370', + 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789', }, - 'params': { - 'playlist_items': '1-100', + # 'params': { + # 'playlist_items': '1-100', + # }, + 'playlist_mincount': 1623, + 'skip': 'Large list', + }, { + 'url': 'https://www.mixcloud.com/FirstEar/stream/', + 'info_dict': { + 'id': 'FirstEar_stream', + 'title': 'First Ear (stream)', + 'description': 'Curators of good music\r\n\r\nfirstearmusic.com', }, - 'playlist_mincount': 100, + 'playlist_mincount': 271, }] - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - user_id = mobj.group('user') - list_type = mobj.group('type') - - # if only a profile URL was supplied, default to download all uploads - if list_type is None: - list_type = 'uploads' - - video_id = '%s_%s' % (user_id, list_type) - - profile = self._download_webpage( - 'https://www.mixcloud.com/%s/' % user_id, video_id, - note='Downloading user profile', - errnote='Unable to download user profile') + _TITLE_KEY = 'displayName' + _DESCRIPTION_KEY = 'biog' + _ROOT_TYPE = 'user' + _NODE_TEMPLATE = '''slug + url''' - username = self._og_search_title(profile) - description = self._get_user_description(profile) - - entries = OnDemandPagedList( - functools.partial( - self._tracks_page_func, - '%s/%s' % (user_id, list_type), video_id, 'list of %s' % list_type), - self._PAGE_SIZE, use_cache=True) - - return self.playlist_result( - entries, video_id, '%s (%s)' % (username, list_type), description) + def _get_playlist_title(self, title, slug): + return '%s (%s)' % (title, slug) class MixcloudPlaylistIE(MixcloudPlaylistBaseIE): - _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P[^/]+)/playlists/(?P[^/]+)/?$' + _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P[^/]+)/playlists/(?P[^/]+)/?$' IE_NAME = 'mixcloud:playlist' _TESTS = [{ - 'url': 'https://www.mixcloud.com/RedBullThre3style/playlists/tokyo-finalists-2015/', - 'info_dict': { - 'id': 'RedBullThre3style_tokyo-finalists-2015', - 'title': 'National Champions 2015', - 'description': 'md5:6ff5fb01ac76a31abc9b3939c16243a3', - }, - 'playlist_mincount': 16, - }, { 'url': 'https://www.mixcloud.com/maxvibes/playlists/jazzcat-on-ness-radio/', 'info_dict': { 'id': 'maxvibes_jazzcat-on-ness-radio', - 'title': 'Jazzcat on Ness Radio', - 'description': 'md5:7bbbf0d6359a0b8cda85224be0f8f263', + 'title': 'Ness Radio sessions', }, - 'playlist_mincount': 23 + 'playlist_mincount': 59, }] - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - user_id = mobj.group('user') - playlist_id = mobj.group('playlist') - video_id = '%s_%s' % (user_id, playlist_id) - - profile = self._download_webpage( - url, user_id, - note='Downloading playlist page', - errnote='Unable to download playlist page') - - description = self._get_user_description(profile) - playlist_title = self._html_search_regex( - r']+class="[^"]*list-playlist-title[^"]*"[^>]*>(.*?)', - profile, 'playlist title') - - entries = OnDemandPagedList( - functools.partial( - self._tracks_page_func, - '%s/playlists/%s' % (user_id, playlist_id), video_id, 'tracklist'), - self._PAGE_SIZE) - - return self.playlist_result(entries, video_id, playlist_title, description) - - -class MixcloudStreamIE(MixcloudPlaylistBaseIE): - _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P[^/]+)/stream/?$' - IE_NAME = 'mixcloud:stream' - - _TEST = { - 'url': 'https://www.mixcloud.com/FirstEar/stream/', - 'info_dict': { - 'id': 'FirstEar', - 'title': 'First Ear', - 'description': 'Curators of good music\nfirstearmusic.com', - }, - 'playlist_mincount': 192, - } - - def _real_extract(self, url): - user_id = self._match_id(url) - - webpage = self._download_webpage(url, user_id) - - entries = [] - prev_page_url = None - - def _handle_page(page): - entries.extend(self._find_urls_in_page(page)) - return self._search_regex( - r'm-next-page-url="([^"]+)"', page, - 'next page URL', default=None) - - next_page_url = _handle_page(webpage) - - for idx in itertools.count(0): - if not next_page_url or prev_page_url == next_page_url: - break - - prev_page_url = next_page_url - current_page = int(self._search_regex( - r'\?page=(\d+)', next_page_url, 'next page number')) - - next_page_url = _handle_page(self._fetch_tracks_page( - '%s/stream' % user_id, user_id, 'stream', idx, - real_page_number=current_page)) - - username = self._og_search_title(webpage) - description = self._get_user_description(webpage) - - return self.playlist_result(entries, user_id, username, description) + _TITLE_KEY = 'name' + _DESCRIPTION_KEY = 'description' + _ROOT_TYPE = 'playlist' + _NODE_TEMPLATE = '''cloudcast { + slug + url + }''' + + def _get_cloudcast(self, node): + return node.get('cloudcast') or {}