X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/ca4d08063804fb264eb0ae9cc57894198f66e1fb..af478477605bdf3f5d57562035885cfee905f379:/youtube_dl/extractor/mixcloud.py diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index 125d815..f3356db 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -1,4 +1,5 @@ -import json +from __future__ import unicode_literals + import re from .common import InfoExtractor @@ -10,17 +11,17 @@ from ..utils import ( class MixcloudIE(InfoExtractor): _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)' - IE_NAME = u'mixcloud' + 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/', + 'file': 'dholbach-cryptkeeper.mp3', + 'info_dict': { + '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', }, } @@ -42,18 +43,19 @@ class MixcloudIE(InfoExtractor): 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) + 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/') + api_url = 'http://api.mixcloud.com/%s/%s/' % (uploader, cloudcast_name) + info = self._download_json( + api_url, track_id, 'Downloading cloudcast info') + + 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._get_url(template_url) if final_song_url is None: