X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/bddc9fc577d16b1428924bf8a5c37ef1d9295f14..67afe88251ff8b1fcb43246c9a4bb1a0ea0185a2:/youtube_dl/extractor/mixcloud.py diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py index 8245b55..425a4cc 100644 --- a/youtube_dl/extractor/mixcloud.py +++ b/youtube_dl/extractor/mixcloud.py @@ -1,115 +1,107 @@ -import json +from __future__ import unicode_literals + import re -import socket from .common import InfoExtractor +from ..compat import ( + compat_urllib_parse, +) from ..utils import ( - compat_http_client, - compat_str, - compat_urllib_error, - compat_urllib_request, - ExtractorError, + HEADRequest, + str_to_int, ) class MixcloudIE(InfoExtractor): - _WORKING = False # New API, but it seems good http://www.mixcloud.com/developers/documentation/ - _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([\w\d-]+)/([\w\d-]+)' - IE_NAME = u'mixcloud' - - def report_download_json(self, file_id): - """Report JSON download.""" - self.to_screen(u'Downloading json') - - def get_urls(self, jsonData, fmt, bitrate='best'): - """Get urls from 'audio_formats' section in json""" + _VALID_URL = r'^(?:https?://)?(?:www\.)?mixcloud\.com/([^/]+)/([^/]+)' + IE_NAME = 'mixcloud' + + _TESTS = [{ + 'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/', + 'info_dict': { + 'id': 'dholbach-cryptkeeper', + 'ext': 'mp3', + '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', + '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, + }, + }] + + def _check_url(self, url, track_id, ext): try: - bitrate_list = jsonData[fmt] - if bitrate is None or bitrate == 'best' or bitrate not in bitrate_list: - bitrate = max(bitrate_list) # select highest - - url_list = jsonData[fmt][bitrate] - except TypeError: # we have no bitrate info. - url_list = jsonData[fmt] - return url_list - - def check_urls(self, url_list): - """Returns 1st active url from list""" - for url in url_list: - try: - compat_urllib_request.urlopen(url) - return url - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error): - url = None - - return None - - def _print_formats(self, formats): - print('Available formats:') - for fmt in formats.keys(): - for b in formats[fmt]: - try: - ext = formats[fmt][b][0] - print('%s\t%s\t[%s]' % (fmt, b, ext.split('.')[-1])) - except TypeError: # we have no bitrate info - ext = formats[fmt][0] - print('%s\t%s\t[%s]' % (fmt, '??', ext.split('.')[-1])) - break + # 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 def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError(u'Invalid URL: %s' % url) - # extract uploader & filename from url - uploader = mobj.group(1).decode('utf-8') - file_id = uploader + "-" + mobj.group(2).decode('utf-8') - - # construct API request - file_url = 'http://www.mixcloud.com/api/1/cloudcast/' + '/'.join(url.split('/')[-3:-1]) + '.json' - # retrieve .json file with links to files - request = compat_urllib_request.Request(file_url) - try: - self.report_download_json(file_url) - jsonData = compat_urllib_request.urlopen(request).read() - except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: - raise ExtractorError(u'Unable to retrieve file: %s' % compat_str(err)) - - # parse JSON - json_data = json.loads(jsonData) - player_url = json_data['player_swf_url'] - formats = dict(json_data['audio_formats']) - - req_format = self._downloader.params.get('format', None) - - if self._downloader.params.get('listformats', None): - self._print_formats(formats) - return - - if req_format is None or req_format == 'best': - for format_param in formats.keys(): - url_list = self.get_urls(formats, format_param) - # check urls - file_url = self.check_urls(url_list) - if file_url is not None: - break # got it! - else: - if req_format not in formats: - raise ExtractorError(u'Format is not available') - - url_list = self.get_urls(formats, req_format) - file_url = self.check_urls(url_list) - format_param = req_format - - return [{ - 'id': file_id.decode('utf-8'), - 'url': file_url.decode('utf-8'), - 'uploader': uploader.decode('utf-8'), - 'upload_date': None, - 'title': json_data['name'], - 'ext': file_url.split('.')[-1].decode('utf-8'), - 'format': (format_param is None and u'NA' or format_param.decode('utf-8')), - 'thumbnail': json_data['thumbnail_url'], - 'description': json_data['description'], - 'player_url': player_url.decode('utf-8'), - }] + uploader = mobj.group(1) + cloudcast_name = mobj.group(2) + track_id = compat_urllib_parse.unquote('-'.join((uploader, cloudcast_name))) + + webpage = self._download_webpage(url, track_id) + + preview_url = self._search_regex( + r'\s(?:data-preview-url|m-preview)="([^"]+)"', webpage, 'preview url') + song_url = preview_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') + + PREFIX = ( + r'm-play-on-spacebar[^>]+' + 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 = str_to_int(self._search_regex( + r'\bbutton-favorite\b[^>]+m-ajax-toggle-count="([^"]+)"', + webpage, 'like count', fatal=False)) + view_count = str_to_int(self._search_regex( + [r'([0-9,.]+)'], + webpage, 'play count', fatal=False)) + + return { + 'id': track_id, + 'title': title, + 'url': song_url, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, + 'uploader_id': uploader_id, + 'view_count': view_count, + 'like_count': like_count, + }