From 480f2d89f6b461123e24a1288fddc287c3838d37 Mon Sep 17 00:00:00 2001 From: Lucas Date: Sun, 18 Aug 2019 23:39:06 +0200 Subject: [PATCH] Add base info extractor class --- youtube_dl/extractor/deezer.py | 36 ++++++++++++++++++++-------------- 1 file changed, 21 insertions(+), 15 deletions(-) diff --git a/youtube_dl/extractor/deezer.py b/youtube_dl/extractor/deezer.py index 0aff4074e..6a21f2ffa 100644 --- a/youtube_dl/extractor/deezer.py +++ b/youtube_dl/extractor/deezer.py @@ -10,27 +10,16 @@ from ..utils import ( orderedSet, ) -class DeezerPlaylistIE(InfoExtractor): - _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, - } +class DeezerBaseInfoExtractor(InfoExtractor): - def _real_extract(self, url): + 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) - playlist_id = mobj.group('id') + id = mobj.group('id') - webpage = self._download_webpage(url, playlist_id) + webpage = self._download_webpage(url, id) geoblocking_msg = self._html_search_regex( r'

(.*?)

', webpage, 'geoblocking message', default=None) @@ -43,6 +32,23 @@ class DeezerPlaylistIE(InfoExtractor): 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')