from __future__ import unicode_literals import json import re from .common import InfoExtractor from ..utils import ( ExtractorError, int_or_none, orderedSet, ) class DeezerBaseInfoExtractor(InfoExtractor): def get_data(self, url): if 'test' not in self._downloader.params: self._downloader.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!') mobj = re.match(self._VALID_URL, url) id = mobj.group('id') webpage = self._download_webpage(url, id) geoblocking_msg = self._html_search_regex( r'

(.*?)

', webpage, 'geoblocking message', default=None) if geoblocking_msg is not None: raise ExtractorError( 'Deezer said: %s' % geoblocking_msg, expected=True) data_json = self._search_regex( (r'__DZR_APP_STATE__\s*=\s*({.+?})\s*', r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n'), webpage, 'data JSON') data = json.loads(data_json) return id, webpage, data class DeezerPlaylistIE(DeezerBaseInfoExtractor): _VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?playlist/(?P[0-9]+)' _TEST = { 'url': 'http://www.deezer.com/playlist/176747451', 'info_dict': { 'id': '176747451', 'title': 'Best!', 'uploader': 'anonymous', 'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$', }, 'playlist_count': 29, } def _real_extract(self, url): playlist_id, webpage, data = self.get_data(url) playlist_title = data.get('DATA').get('TITLE') playlist_uploader = data.get('DATA').get('PARENT_USERNAME') playlist_thumbnail = self._search_regex( r'[0-9]+)' _TEST = { 'url': 'https://www.deezer.com/fr/album/67505622', 'info_dict': { 'id': '67505622', 'title': 'Last Week', 'uploader': 'Home Brew', 'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$', }, 'playlist_count': 7, } def _real_extract(self, url): album_id, webpage, data = self.get_data(url) album_title = data.get('DATA').get('ALB_TITLE') album_uploader = data.get('DATA').get('ART_NAME') album_thumbnail = self._search_regex( r'