commit c77308269287c8d745f2254181cf42dceac26fde
parent 56f1750049ee04d78d1349617124349bb1309cba
Author: Yen Chi Hsuan <yan12125@gmail.com>
Date: Fri, 15 Apr 2016 14:33:04 +0800
Merge branch 'Phaeilo-mixcloud'
Diffstat:
2 files changed, 156 insertions(+), 4 deletions(-)
diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
@@ -412,7 +412,11 @@ from .minoto import MinotoIE
from .miomio import MioMioIE
from .mit import TechTVMITIE, MITIE, OCWMITIE
from .mitele import MiTeleIE
-from .mixcloud import MixcloudIE
+from .mixcloud import (
+ MixcloudIE,
+ MixcloudUserIE,
+ MixcloudPlaylistIE
+)
from .mlb import MLBIE
from .mnet import MnetIE
from .mpora import MporaIE
diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py
@@ -1,12 +1,18 @@
from __future__ import unicode_literals
+import functools
import re
from .common import InfoExtractor
-from ..compat import compat_urllib_parse_unquote
+from ..compat import (
+ compat_urllib_parse_unquote,
+ compat_urlparse,
+)
from ..utils import (
+ clean_html,
ExtractorError,
HEADRequest,
+ OnDemandPagedList,
NO_DEFAULT,
parse_count,
str_to_int,
@@ -14,14 +20,14 @@ from ..utils import (
class MixcloudIE(InfoExtractor):
- _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)'
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?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',
@@ -115,3 +121,145 @@ class MixcloudIE(InfoExtractor):
'view_count': view_count,
'like_count': like_count,
}
+
+
+class MixcloudPlaylistBaseIE(InfoExtractor):
+ _PAGE_SIZE = 24
+
+ def _fetch_tracks_page(self, path, video_id, page_name, current_page):
+ resp = self._download_webpage(
+ 'https://www.mixcloud.com/%s/' % path, video_id,
+ note='Download %s (page %d)' % (page_name, current_page + 1),
+ errnote='Unable to download %s' % page_name,
+ query={'page': (current_page + 1), 'list': 'main', '_ajax': '1'},
+ headers={'X-Requested-With': 'XMLHttpRequest'})
+
+ for url in re.findall(r'm-play-button m-url="(?P<url>[^"]+)"', resp):
+ yield self.url_result(
+ compat_urlparse.urljoin('https://www.mixcloud.com', clean_html(url)),
+ MixcloudIE.ie_key())
+
+ def _get_user_description(self, page_content):
+ return self._html_search_regex(
+ r'<div[^>]+class="description-text"[^>]*>(.+?)</div>',
+ page_content, 'user description', fatal=False)
+
+
+class MixcloudUserIE(MixcloudPlaylistBaseIE):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/(?P<type>uploads|favorites|listens)?/?$'
+ IE_NAME = 'mixcloud:user'
+
+ _TESTS = [{
+ 'url': 'http://www.mixcloud.com/dholbach/',
+ 'info_dict': {
+ 'id': 'dholbach_uploads',
+ 'title': 'Daniel Holbach (uploads)',
+ 'description': 'md5:327af72d1efeb404a8216c27240d1370',
+ },
+ 'playlist_mincount': 11,
+ }, {
+ 'url': 'http://www.mixcloud.com/dholbach/uploads/',
+ 'info_dict': {
+ 'id': 'dholbach_uploads',
+ 'title': 'Daniel Holbach (uploads)',
+ 'description': 'md5:327af72d1efeb404a8216c27240d1370',
+ },
+ 'playlist_mincount': 11,
+ }, {
+ 'url': 'http://www.mixcloud.com/dholbach/favorites/',
+ 'info_dict': {
+ 'id': 'dholbach_favorites',
+ 'title': 'Daniel Holbach (favorites)',
+ 'description': 'md5:327af72d1efeb404a8216c27240d1370',
+ },
+ 'params': {
+ 'playlist_items': '1-100',
+ },
+ 'playlist_mincount': 100,
+ }, {
+ 'url': 'http://www.mixcloud.com/dholbach/listens/',
+ 'info_dict': {
+ 'id': 'dholbach_listens',
+ 'title': 'Daniel Holbach (listens)',
+ 'description': 'md5:327af72d1efeb404a8216c27240d1370',
+ },
+ 'params': {
+ 'playlist_items': '1-100',
+ },
+ 'playlist_mincount': 100,
+ }]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ user_id = mobj.group('user')
+ list_type = mobj.group('type')
+
+ # if only a profile URL was supplied, default to download all uploads
+ if list_type is None:
+ list_type = 'uploads'
+
+ video_id = '%s_%s' % (user_id, list_type)
+
+ profile = self._download_webpage(
+ 'https://www.mixcloud.com/%s/' % user_id, video_id,
+ note='Downloading user profile',
+ errnote='Unable to download user profile')
+
+ username = self._og_search_title(profile)
+ description = self._get_user_description(profile)
+
+ entries = OnDemandPagedList(
+ functools.partial(
+ self._fetch_tracks_page,
+ '%s/%s' % (user_id, list_type), video_id, 'list of %s' % list_type),
+ self._PAGE_SIZE, use_cache=True)
+
+ return self.playlist_result(
+ entries, video_id, '%s (%s)' % (username, list_type), description)
+
+
+class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
+ _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/playlists/(?P<playlist>[^/]+)/?$'
+ IE_NAME = 'mixcloud:playlist'
+
+ _TESTS = [{
+ 'url': 'https://www.mixcloud.com/RedBullThre3style/playlists/tokyo-finalists-2015/',
+ 'info_dict': {
+ 'id': 'RedBullThre3style_tokyo-finalists-2015',
+ 'title': 'National Champions 2015',
+ 'description': 'md5:6ff5fb01ac76a31abc9b3939c16243a3',
+ },
+ 'playlist_mincount': 16,
+ }, {
+ 'url': 'https://www.mixcloud.com/maxvibes/playlists/jazzcat-on-ness-radio/',
+ 'info_dict': {
+ 'id': 'maxvibes_jazzcat-on-ness-radio',
+ 'title': 'Jazzcat on Ness Radio',
+ 'description': 'md5:7bbbf0d6359a0b8cda85224be0f8f263',
+ },
+ 'playlist_mincount': 23
+ }]
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ user_id = mobj.group('user')
+ playlist_id = mobj.group('playlist')
+ video_id = '%s_%s' % (user_id, playlist_id)
+
+ profile = self._download_webpage(
+ url, user_id,
+ note='Downloading playlist page',
+ errnote='Unable to download playlist page')
+
+ description = self._get_user_description(profile)
+ playlist_title = self._html_search_regex(
+ r'<span[^>]+class="[^"]*list-playlist-title[^"]*"[^>]*>(.*?)</span>',
+ profile, 'playlist title')
+
+ entries = OnDemandPagedList(
+ functools.partial(
+ self._fetch_tracks_page,
+ '%s/playlists/%s' % (user_id, playlist_id), video_id, 'tracklist'),
+ self._PAGE_SIZE)
+
+ return self.playlist_result(entries, video_id, playlist_title, description)
