X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/d9d7cd0e85dc712461d9185db9df9d6c900a573b..1f17a37b9b95db09a420a1f52cf18723ce4eb8b5:/youtube_dl/extractor/mixcloud.py?ds=sidebyside diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index 0efbe66..a56b769 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -1,22 +1,27 @@ 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, + int_or_none, OnDemandPagedList, str_to_int, + try_get, + urljoin, ) @@ -53,16 +58,12 @@ class MixcloudIE(InfoExtractor): 'only_matching': True, }] - # 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) @@ -72,38 +73,119 @@ class MixcloudIE(InfoExtractor): webpage = self._download_webpage(url, track_id) + # 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)