X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/63a6927374492ef47c8fd6de67d0760ace4dd0ed..647c9744516f7b5be3611b67e02201fb0146a638:/youtube_dl/extractor/mixcloud.py?ds=sidebyside diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index 125d815..bf5353e 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -1,76 +1,398 @@ -import json +from __future__ import unicode_literals + +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 ( - unified_strdate, + clean_html, ExtractorError, + int_or_none, + OnDemandPagedList, + str_to_int, + try_get, + urljoin, ) class MixcloudIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)' - IE_NAME = u'mixcloud' + _VALID_URL = r'https?://(?:(?:www|beta|m)\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)' + IE_NAME = 'mixcloud' - _TEST = { - u'url': u'http://www.mixcloud.com/dholbach/cryptkeeper/', - u'file': u'dholbach-cryptkeeper.mp3', - u'info_dict': { - u'title': u'Cryptkeeper', - u'description': u'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.', - u'uploader': u'Daniel Holbach', - u'uploader_id': u'dholbach', - u'upload_date': u'20111115', + _TESTS = [{ + 'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/', + 'info_dict': { + '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': r're:https?://.*\.jpg', + 'view_count': int, }, - } - - def check_urls(self, url_list): - """Returns 1st active url from list""" - for url in url_list: - try: - # We only want to know if the request succeed - # don't download the whole file - self._request_webpage(url, None, False) - return url - except ExtractorError: - url = None - - return None + }, { + 'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/', + 'info_dict': { + 'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat', + 'ext': 'mp3', + 'title': 'Caribou 7 inch Vinyl Mix & Chat', + 'description': 'md5:2b8aec6adce69f9d41724647c65875e8', + 'uploader': 'Gilles Peterson Worldwide', + 'uploader_id': 'gillespeterson', + 'thumbnail': 're:https?://.*', + 'view_count': int, + }, + }, { + 'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/', + 'only_matching': True, + }] - def _get_url(self, template_url): - return self.check_urls(template_url % i for i in range(30)) + @staticmethod + 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(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 = '-'.join((uploader, cloudcast_name)) - api_url = 'http://api.mixcloud.com/%s/%s/' % (uploader, cloudcast_name) + track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name))) + webpage = self._download_webpage(url, track_id) - json_data = self._download_webpage(api_url, track_id, - u'Downloading cloudcast info') - info = json.loads(json_data) - - preview_url = self._search_regex(r'data-preview-url="(.+?)"', webpage, u'preview url') - song_url = preview_url.replace('/previews/', '/cloudcasts/originals/') - template_url = re.sub(r'(stream\d*)', 'stream%d', song_url) - final_song_url = self._get_url(template_url) - if final_song_url is None: - self.to_screen('Trying with m4a extension') - template_url = template_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/') - final_song_url = self._get_url(template_url) - if final_song_url is None: - raise ExtractorError(u'Unable to extract track url') + + # Legacy path + encrypted_play_info = self._search_regex( + r'm-play-info="([^"]+)"', webpage, 'play info', default=None) + + if encrypted_play_info is not None: + # Decode + encrypted_play_info = compat_b64decode(encrypted_play_info) + else: + # New path + full_info_json = self._parse_json(self._html_search_regex( + r'', + webpage, 'play info'), 'play info') + for item in full_info_json: + item_data = try_get( + item, lambda x: x['cloudcast']['data']['cloudcastLookup'], + dict) + if try_get(item_data, lambda x: x['streamInfo']['url']): + info_json = item_data + break + else: + raise ExtractorError('Failed to extract matching stream info') + + message = self._html_search_regex( + r'(?s)