From da2e1f53e07bb24405bb9e27c58fa52fe0b58087 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Fri, 12 Sep 2014 07:25:58 +0200 Subject: [PATCH] [deezer] Add simple support --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/deezer.py | 80 ++++++++++++++++++++++++++++++++ 2 files changed, 81 insertions(+) create mode 100644 youtube_dl/extractor/deezer.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 6b29e9fdd4..eba7dc0a29 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -68,6 +68,7 @@ from .dailymotion import ( ) from .daum import DaumIE from .dbtv import DBTVIE +from .deezer import DeezerPlaylistIE from .dfb import DFBIE from .dotsub import DotsubIE from .dreisat import DreiSatIE diff --git a/youtube_dl/extractor/deezer.py b/youtube_dl/extractor/deezer.py new file mode 100644 index 0000000000..62c1815291 --- /dev/null +++ b/youtube_dl/extractor/deezer.py @@ -0,0 +1,80 @@ +from __future__ import unicode_literals + +import json +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + 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': 're:^https?://cdn-images.deezer.com/images/cover/.*\.jpg$', + }, + 'playlist_count': 30, + } + + def _real_extract(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') + + webpage = self._download_webpage(url, playlist_id) + data_json = self._search_regex( + r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n', webpage, 'data JSON') + data = json.loads(data_json) + + playlist_title = data.get('DATA', {}).get('TITLE') + playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME') + playlist_thumbnail = self._search_regex( + r'