From 70e7967202efa0acb6202ceedf87049ba72b94e0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 11 Jun 2017 20:50:33 +0700 Subject: [PATCH] [newgrounds:playlist] Add extractor (closes #10611) --- youtube_dl/extractor/extractors.py | 5 ++- youtube_dl/extractor/newgrounds.py | 56 +++++++++++++++++++++++++++++- 2 files changed, 59 insertions(+), 2 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index e1907314d..7e45232dd 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -636,7 +636,10 @@ from .neteasemusic import ( NetEaseMusicProgramIE, NetEaseMusicDjRadioIE, ) -from .newgrounds import NewgroundsIE +from .newgrounds import ( + NewgroundsIE, + NewgroundsPlaylistIE, +) from .newstube import NewstubeIE from .nextmedia import ( NextMediaIE, diff --git a/youtube_dl/extractor/newgrounds.py b/youtube_dl/extractor/newgrounds.py index ae4fe95ef..dc183caec 100644 --- a/youtube_dl/extractor/newgrounds.py +++ b/youtube_dl/extractor/newgrounds.py @@ -1,7 +1,12 @@ from __future__ import unicode_literals +import re + from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + extract_attributes, + int_or_none, +) class NewgroundsIE(InfoExtractor): @@ -82,3 +87,52 @@ class NewgroundsIE(InfoExtractor): 'uploader': uploader, 'formats': formats, } + + +class NewgroundsPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:collection|[^/]+/search/[^/]+)/(?P[^/?#&]+)' + _TESTS = [{ + 'url': 'https://www.newgrounds.com/collection/cats', + 'info_dict': { + 'id': 'cats', + 'title': 'Cats', + }, + 'playlist_mincount': 46, + }, { + 'url': 'http://www.newgrounds.com/portal/search/author/ZONE-SAMA', + 'info_dict': { + 'id': 'ZONE-SAMA', + 'title': 'Portal Search: ZONE-SAMA', + }, + 'playlist_mincount': 47, + }, { + 'url': 'http://www.newgrounds.com/audio/search/title/cats', + 'only_matching': True, + }] + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + title = self._search_regex( + r'([^>]+)', webpage, 'title', default=None) + + # cut left menu + webpage = self._search_regex( + r'(?s)]+\bclass=["\']column wide(.+)', + webpage, 'wide column', default=webpage) + + entries = [] + for a, path, media_id in re.findall( + r'(]+\bhref=["\']/?((?:portal/view|audio/listen)/(\d+))[^>]+>)', + webpage): + a_class = extract_attributes(a).get('class') + if a_class not in ('item-portalsubmission', 'item-audiosubmission'): + continue + entries.append( + self.url_result( + 'https://www.newgrounds.com/%s' % path, + ie=NewgroundsIE.ie_key(), video_id=media_id)) + + return self.playlist_result(entries, playlist_id, title)