X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fmixcloud.py;h=a56b7690f8703cb873cba7d59cb097afee1b8121;hb=70d35d166c1cfb14af20fb6d45ed820b6249f941;hp=84f29155841007f3088a86470040407073726067;hpb=d5c418f29fcce3d62bba7f6228b76b69b5b731ce;p=youtube-dl diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index 84f291558..a56b7690f 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -1,35 +1,45 @@ from __future__ import unicode_literals -import re +import functools import itertools +import re from .common import InfoExtractor from ..compat import ( - compat_urllib_parse, + compat_b64decode, + compat_chr, + compat_ord, + compat_str, + compat_urllib_parse_unquote, + compat_urlparse, + compat_zip ) from ..utils import ( + clean_html, ExtractorError, - HEADRequest, + int_or_none, + OnDemandPagedList, str_to_int, + try_get, + urljoin, ) class MixcloudIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)' + _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', - 'ext': 'mp3', + '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, }, }, { 'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/', @@ -40,110 +50,339 @@ class MixcloudIE(InfoExtractor): 'description': 'md5:2b8aec6adce69f9d41724647c65875e8', 'uploader': 'Gilles Peterson Worldwide', 'uploader_id': 'gillespeterson', - 'thumbnail': 're:https?://.*/images/', + 'thumbnail': 're:https?://.*', 'view_count': int, - 'like_count': int, }, + }, { + 'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/', + 'only_matching': True, }] - def _get_url(self, track_id, template_url, server_number): - boundaries = (1, 30) - for nr in server_numbers(server_number, boundaries): - url = template_url % nr - try: - # We only want to know if the request succeed - # don't download the whole file - self._request_webpage( - HEADRequest(url), track_id, - 'Checking URL %d/%d ...' % (nr, boundaries[-1])) - return url - except ExtractorError: - pass - return None + @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 = compat_urllib_parse.unquote('-'.join((uploader, cloudcast_name))) + track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name))) webpage = self._download_webpage(url, track_id) - preview_url = self._search_regex( - r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url') - song_url = preview_url.replace('/previews/', '/c/originals/') - server_number = int(self._search_regex(r'stream(\d+)', song_url, 'server number')) - template_url = re.sub(r'(stream\d*)', 'stream%d', song_url) - final_song_url = self._get_url(track_id, template_url, server_number) - 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(track_id, template_url, server_number) - if final_song_url is None: - raise ExtractorError('Unable to extract track 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 = str_to_int(self._search_regex( - r'\bbutton-favorite\b[^>]+m-ajax-toggle-count="([^"]+)"', - webpage, 'like count', fatal=False)) - view_count = str_to_int(self._search_regex( - [r'([0-9,.]+)'], - webpage, 'play count', fatal=False)) + # 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)