1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00
youtube-dl/youtube_dl/extractor/mixcloud.py

79 lines
2.8 KiB
Python
Raw Normal View History

2014-01-17 03:06:18 +00:00
from __future__ import unicode_literals
2013-06-23 19:59:15 +00:00
import re
from .common import InfoExtractor
from ..utils import (
unified_strdate,
ExtractorError,
2013-06-23 19:59:15 +00:00
)
class MixcloudIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)'
2014-01-17 03:06:18 +00:00
IE_NAME = 'mixcloud'
2013-06-23 19:59:15 +00:00
_TEST = {
2014-01-17 03:06:18 +00:00
'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',
},
}
2013-06-23 19:59:15 +00:00
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)
2013-06-23 19:59:15 +00:00
return url
except ExtractorError:
2013-06-23 19:59:15 +00:00
url = None
return None
def _get_url(self, template_url):
return self.check_urls(template_url % i for i in range(30))
2013-06-23 19:59:15 +00:00
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))
2014-01-17 03:05:15 +00:00
webpage = self._download_webpage(url, track_id)
2014-01-17 03:05:15 +00:00
api_url = 'http://api.mixcloud.com/%s/%s/' % (uploader, cloudcast_name)
info = self._download_json(
2014-01-17 03:06:18 +00:00
api_url, track_id, 'Downloading cloudcast info')
2014-01-17 03:05:15 +00:00
preview_url = self._search_regex(
2014-01-17 03:06:18 +00:00
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:
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')
return {
'id': track_id,
'title': info['name'],
'url': final_song_url,
'description': info.get('description'),
'thumbnail': info['pictures'].get('extra_large'),
'uploader': info['user']['name'],
'uploader_id': info['user']['username'],
'upload_date': unified_strdate(info['created_time']),
'view_count': info['play_count'],
}