From c96eca426b6b4c963fafd3f3268ea1f39b3e2857 Mon Sep 17 00:00:00 2001 From: Philip Huppert Date: Mon, 5 Oct 2015 00:41:20 +0200 Subject: [PATCH] [mixcloud] Added support for user uploads, playlists, favorites and listens. Fixes #3750 and #5272 --- youtube_dl/extractor/extractors.py | 6 +- youtube_dl/extractor/mixcloud.py | 200 ++++++++++++++++++++++++++++- 2 files changed, 203 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 04c6508f1..b06b717f5 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -411,7 +411,11 @@ 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 index 9638cc9e6..20e64bab5 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -3,18 +3,22 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..compat import compat_urllib_parse_unquote +from ..compat import ( + compat_urllib_parse_unquote, + compat_urllib_request +) from ..utils import ( ExtractorError, HEADRequest, NO_DEFAULT, parse_count, str_to_int, + clean_html ) 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 = [{ @@ -115,3 +119,195 @@ class MixcloudIE(InfoExtractor): 'view_count': view_count, 'like_count': like_count, } + + +class MixcloudUserIE(InfoExtractor): + """ + Information extractor for Mixcloud users. + It can retrieve a list of a user's uploads, favorites or listens. + """ + + _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P[^/]+)/(?Puploads|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', + }, + 'playlist_mincount': 244 + }, { + 'url': 'http://www.mixcloud.com/dholbach/listens/', + 'info_dict': { + 'id': 'dholbach/listens', + 'title': 'Daniel Holbach (listens)', + 'description': 'md5:327af72d1efeb404a8216c27240d1370', + }, + 'playlist_mincount': 846 + }] + + def _fetch_tracks(self, base_url, video_id, dl_note=None, dl_errnote=None): + # retrieve all fragments of a list of tracks with fake AJAX calls + track_urls = [] + current_page = 1 + while True: + # fake a AJAX request to retrieve a list fragment + page_url = base_url + "?page=%d&list=main&_ajax=1" % current_page + req = compat_urllib_request.Request(page_url, headers={"X-Requested-With": "XMLHttpRequest"}, method="GET") + resp = self._download_webpage(req, video_id, note=dl_note + " (page %d)" % current_page, errnote=dl_errnote) + + # extract all track URLs from fragment + urls = re.findall(r'm-play-button m-url="(?P[^"]+)"', resp) + # clean up URLs + urls = map(clean_html, urls) + # create absolute URLs + urls = map(lambda u: "https://www.mixcloud.com" + u, urls) + track_urls.extend(urls) + + # advance to next fragment, if any + if " m-next-page-url=" in resp: + current_page += 1 + else: + break + + return track_urls + + def _handle_track_urls(self, urls): + return map(lambda u: self.url_result(u, "Mixcloud"), urls) + + def _get_user_description(self, page_content): + return self._html_search_regex( + r'
.*?

(?P.*?)

', + page_content, + "user description", + group="description", + fatal=False, + default="") + + def _get_username(self, page_content): + return self._og_search_title(page_content) + + 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) + + # download the user's profile to retrieve some metadata + 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._get_username(profile) + description = self._get_user_description(profile) + + # retrieve all page fragments of uploads, favorites or listens + track_urls = self._fetch_tracks( + "https://www.mixcloud.com/%s/%s/" % (user_id, list_type), + video_id, + dl_note="Downloading list of %s" % list_type, + dl_errnote="Unable to download list of %s" % list_type) + + # let MixcloudIE handle each track URL + entries = self._handle_track_urls(track_urls) + + return { + '_type': 'playlist', + 'entries': entries, + 'title': "%s (%s)" % (username, list_type), + 'id': video_id, + "description": description + } + + +class MixcloudPlaylistIE(MixcloudUserIE): + """ + Information extractor for Mixcloud playlists. + """ + + _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/(?P[^/]+)/playlists/(?P[^/]+)/?$' + IE_NAME = 'mixcloud:playlist' + + _TESTS = [{ + 'url': 'https://www.mixcloud.com/RedBullThre3style/playlists/tokyo-finalists-2015/', + 'info_dict': { + 'id': 'RedBullThre3style/playlists/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/playlists/jazzcat-on-ness-radio', + 'title': 'Jazzcat on Ness Radio', + 'description': 'md5:c2c51a1f1b8bb5442f2ca67c3dc4af27', + }, + 'playlist_mincount': 23 + }] + + def _get_playlist_title(self, page_content): + return self._html_search_regex( + r'(?P.*?)</span>', + page_content, + "playlist title", + group="title", + fatal=True + ) + + 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/playlists/%s" % (user_id, playlist_id) + + # download the playlist page to retrieve some metadata + 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._get_playlist_title(profile) + + # retrieve all page fragments of playlist + track_urls = self._fetch_tracks( + "https://www.mixcloud.com/%s/playlists/%s/" % (user_id, playlist_id), + video_id, + dl_note="Downloading tracklist of %s" % playlist_title, + dl_errnote="Unable to tracklist of %s" % playlist_title) + + # let MixcloudIE handle each track + entries = self._handle_track_urls(track_urls) + + return { + '_type': 'playlist', + 'entries': entries, + 'title': playlist_title, + 'id': video_id, + "description": description + }