X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=inline;f=youtube_dl%2Fextractor%2Fmixcloud.py;h=5f64e7bd0d98b74aea2a4350a51f057b4d0280ba;hb=ad3bc6acd5d6724875b9fa59f9b5cdb9b904ec91;hp=e2baf44d7e15032022e6b304ace2bf8ef11a09b2;hpb=dc65dcbb6d709ef6e38f336fe77c14767d6c8f9d;p=youtube-dl diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index e2baf44d7..5f64e7bd0 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -1,29 +1,34 @@ -import json +from __future__ import unicode_literals + import re -import socket from .common import InfoExtractor from ..utils import ( - compat_http_client, - compat_urllib_error, - compat_urllib_request, - unified_strdate, + compat_urllib_parse, + ExtractorError, + int_or_none, + parse_iso8601, ) class MixcloudIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)' - IE_NAME = u'mixcloud' + _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)' + 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', + 'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/', + 'info_dict': { + 'id': 'dholbach-cryptkeeper', + 'ext': 'mp3', + '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', + 'upload_date': '20111115', + 'timestamp': 1321359578, + 'thumbnail': 're:https?://.*\.jpg', + 'view_count': int, + 'like_count': int, }, } @@ -31,39 +36,71 @@ class MixcloudIE(InfoExtractor): """Returns 1st active url from list""" for url in url_list: try: - compat_urllib_request.urlopen(url) + # We only want to know if the request succeed + # don't download the whole file + self._request_webpage(url, None, False) return url - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error): + except ExtractorError: url = None return None + def _get_url(self, template_url): + return self.check_urls(template_url % i for i in range(30)) + 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/') + preview_url = self._search_regex( + r'\s(?:data-preview-url|m-preview)="(.+?)"', webpage, 'preview url') + song_url = preview_url.replace('/previews/', '/c/originals/') template_url = re.sub(r'(stream\d*)', 'stream%d', song_url) - final_song_url = self.check_urls(template_url % i for i in range(30)) + 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('Unable to extract track url') + + PREFIX = ( + r'