From: remitamine Date: Sat, 28 Nov 2015 17:10:37 +0000 (+0100) Subject: [acast] Add new extractor X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=50e12e9df186b475d0e500f61426d9e72d5b4320;p=youtube-dl [acast] Add new extractor --- diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 947b83683..f7594832f 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -3,6 +3,10 @@ from __future__ import unicode_literals from .abc import ABCIE from .abc7news import Abc7NewsIE from .academicearth import AcademicEarthCourseIE +from .acast import ( + ACastIE, + ACastChannelIE, +) from .addanime import AddAnimeIE from .adobetv import ( AdobeTVIE, diff --git a/youtube_dl/extractor/acast.py b/youtube_dl/extractor/acast.py new file mode 100644 index 000000000..c2719ca32 --- /dev/null +++ b/youtube_dl/extractor/acast.py @@ -0,0 +1,66 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..compat import compat_str +from ..utils import int_or_none + + +class ACastBaseIE(InfoExtractor): + _API_BASE_URL = 'https://www.acast.com/api/' + + +class ACastIE(ACastBaseIE): + IE_NAME = 'acast' + _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P[^/]+)/(?P[^/#?]+)' + _TEST = { + 'url': 'https://www.acast.com/gardenersquestiontime/liverpool', + 'md5': '9e9cd59c3a8a7d8d5407605f51093050', + 'info_dict': { + 'id': '43da2262-ade7-420c-8564-f6367da7c010', + 'ext': 'mp3', + 'title': 'Liverpool', + 'timestamp': 1446163200000, + 'description': 'md5:170432c9956eec0670d7080a75000d5b', + 'duration': 2520, + } + } + + def _real_extract(self, url): + channel, display_id = re.match(self._VALID_URL, url).groups() + cast_data = self._download_json(self._API_BASE_URL + 'channels/%s/acasts/%s/playback' % (channel, display_id), display_id) + + return { + 'id': compat_str(cast_data['id']), + 'display_id': display_id, + 'url': cast_data['blings'][0]['audio'], + 'title': cast_data['name'], + 'description': cast_data.get('description'), + 'thumbnail': cast_data.get('image'), + 'timestamp': int_or_none(cast_data.get('publishingDate')), + 'duration': int_or_none(cast_data.get('duration')), + } + + +class ACastChannelIE(ACastBaseIE): + IE_NAME = 'acast:channel' + _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P[^/#?]+)' + _TEST = { + 'url': 'https://www.acast.com/gardenersquestiontime', + 'info_dict': { + 'id': '9d8f6f73-6b9d-4d16-9399-52bf88f8f611', + 'title': 'Gardeners\' Question Time', + 'description': 'md5:c7ef18049da6a52b63d371b3edccce90', + }, + 'playlist_mincount': 5, + } + + def _real_extract(self, url): + display_id = self._match_id(url) + channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id) + casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id) + entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts] + + return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description'))