from __future__ import unicode_literals import re from .common import InfoExtractor from ..utils import ( extract_attributes, int_or_none, ) class NewgroundsIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P[0-9]+)' _TESTS = [{ 'url': 'https://www.newgrounds.com/audio/listen/549479', 'md5': 'fe6033d297591288fa1c1f780386f07a', 'info_dict': { 'id': '549479', 'ext': 'mp3', 'title': 'B7 - BusMode', 'uploader': 'Burn7', } }, { 'url': 'https://www.newgrounds.com/portal/view/673111', 'md5': '3394735822aab2478c31b1004fe5e5bc', 'info_dict': { 'id': '673111', 'ext': 'mp4', 'title': 'Dancin', 'uploader': 'Squirrelman82', }, }, { # source format unavailable, additional mp4 formats 'url': 'http://www.newgrounds.com/portal/view/689400', 'info_dict': { 'id': '689400', 'ext': 'mp4', 'title': 'ZTV News Episode 8', 'uploader': 'BennettTheSage', }, 'params': { 'skip_download': True, }, }] def _real_extract(self, url): media_id = self._match_id(url) webpage = self._download_webpage(url, media_id) title = self._html_search_regex( r'([^>]+)', webpage, 'title') video_url = self._parse_json(self._search_regex( r'"url"\s*:\s*("[^"]+"),', webpage, ''), media_id) formats = [{ 'url': video_url, 'format_id': 'source', 'quality': 1, }] max_resolution = int_or_none(self._search_regex( r'max_resolution["\']\s*:\s*(\d+)', webpage, 'max resolution', default=None)) if max_resolution: url_base = video_url.rpartition('.')[0] for resolution in (360, 720, 1080): if resolution > max_resolution: break formats.append({ 'url': '%s.%dp.mp4' % (url_base, resolution), 'format_id': '%dp' % resolution, 'height': resolution, }) self._check_formats(formats, media_id) self._sort_formats(formats) uploader = self._html_search_regex( r'(?:Author|Writer)\s*]+>([^<]+)', webpage, 'uploader', fatal=False) return { 'id': media_id, 'title': title, '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)