youtube-dl/youtube_dl/extractor/mixcloud.py

118 lines
4.4 KiB
Python
Raw Normal View History

2014-01-17 12:06:18 +09:00
from __future__ import unicode_literals
2013-06-24 04:59:15 +09:00
import re
from .common import InfoExtractor
from ..compat import compat_urllib_parse_unquote
from ..utils import (
ExtractorError,
HEADRequest,
NO_DEFAULT,
parse_count,
str_to_int,
2013-06-24 04:59:15 +09:00
)
class MixcloudIE(InfoExtractor):
_VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
2014-01-17 12:06:18 +09:00
IE_NAME = 'mixcloud'
2013-06-24 04:59:15 +09:00
_TESTS = [{
2014-01-17 12:06:18 +09:00
'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
'info_dict': {
'id': 'dholbach-cryptkeeper',
'ext': 'mp3',
2014-01-17 12:06:18 +09:00
'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',
2014-05-13 16:42:38 +09:00
'thumbnail': 're:https?://.*\.jpg',
'view_count': int,
'like_count': int,
},
}, {
'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
'info_dict': {
'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
'ext': 'mp3',
'title': 'Caribou 7 inch Vinyl Mix & Chat',
'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
'uploader': 'Gilles Peterson Worldwide',
'uploader_id': 'gillespeterson',
'thumbnail': 're:https?://.*/images/',
'view_count': int,
'like_count': int,
},
}]
2013-06-24 04:59:15 +09:00
def _check_url(self, url, track_id, ext):
try:
# We only want to know if the request succeed
# don't download the whole file
self._request_webpage(
HEADRequest(url), track_id,
'Trying %s URL' % ext)
return True
except ExtractorError:
return False
2013-06-24 04:59:15 +09:00
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)))
2014-01-17 12:05:15 +09:00
webpage = self._download_webpage(url, track_id)
message = self._html_search_regex(
r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)',
webpage, 'error message', default=None)
2014-01-17 12:05:15 +09:00
preview_url = self._search_regex(
r'\s(?:data-preview-url|m-preview)="([^"]+)"',
webpage, 'preview url', default=None if message else NO_DEFAULT)
if message:
raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
song_url = re.sub(r'audiocdn(\d+)', r'stream\1', preview_url)
song_url = song_url.replace('/previews/', '/c/originals/')
if not self._check_url(song_url, track_id, 'mp3'):
song_url = song_url.replace('.mp3', '.m4a').replace('originals/', 'm4a/64/')
if not self._check_url(song_url, track_id, 'm4a'):
raise ExtractorError('Unable to extract track url')
2014-05-13 16:42:38 +09:00
PREFIX = (
r'm-play-on-spacebar[^>]+'
2014-05-13 16:42:38 +09:00
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 = parse_count(self._search_regex(
r'\bbutton-favorite[^>]+>.*?<span[^>]+class=["\']toggle-number[^>]+>\s*([^<]+)',
2014-05-13 16:42:38 +09:00
webpage, 'like count', fatal=False))
view_count = str_to_int(self._search_regex(
[r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
r'/listeners/?">([0-9,.]+)</a>'],
2014-05-13 16:42:38 +09:00
webpage, 'play count', fatal=False))
return {
'id': track_id,
2014-05-13 16:42:38 +09:00
'title': title,
'url': song_url,
2014-05-13 16:42:38 +09:00
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
'uploader_id': uploader_id,
'view_count': view_count,
'like_count': like_count,
}