From 6e999fbc120dfdbd8ec5ca056105420fd7cbffe8 Mon Sep 17 00:00:00 2001 From: Sergey M․ Date: Sun, 11 Jun 2017 19:44:44 +0700 Subject: [newgrounds] Improve formats and uploader extraction (closes #13346) --- youtube_dl/extractor/newgrounds.py | 48 ++++++++++++++++++++++++++++++++++---- 1 file changed, 43 insertions(+), 5 deletions(-) (limited to 'youtube_dl/extractor/newgrounds.py') diff --git a/youtube_dl/extractor/newgrounds.py b/youtube_dl/extractor/newgrounds.py index 9bea610c8..ae4fe95ef 100644 --- a/youtube_dl/extractor/newgrounds.py +++ b/youtube_dl/extractor/newgrounds.py @@ -1,6 +1,7 @@ from __future__ import unicode_literals from .common import InfoExtractor +from ..utils import int_or_none class NewgroundsIE(InfoExtractor): @@ -23,24 +24,61 @@ class NewgroundsIE(InfoExtractor): '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') - uploader = self._html_search_regex( - r'Author\s*]+>([^<]+)', webpage, 'uploader', fatal=False) + 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, + }) - music_url = self._parse_json(self._search_regex( - r'"url":("[^"]+"),', webpage, ''), media_id) + 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, - 'url': music_url, 'uploader': uploader, + 'formats': formats, } -- cgit 1.4.1 From 70e7967202efa0acb6202ceedf87049ba72b94e0 Mon Sep 17 00:00:00 2001 From: Sergey M․ Date: Sun, 11 Jun 2017 20:50:33 +0700 Subject: [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(-) (limited to 'youtube_dl/extractor/newgrounds.py') 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) -- cgit 1.4.1 From 28a4d6cce89d159f9fe701e6cf716c7e3ffa4415 Mon Sep 17 00:00:00 2001 From: Sergey M․ Date: Sun, 11 Jun 2017 21:27:32 +0700 Subject: [newgrounds] Extract more metadata (closes #13232) --- youtube_dl/extractor/newgrounds.py | 38 +++++++++++++++++++++++++++++++++----- 1 file changed, 33 insertions(+), 5 deletions(-) (limited to 'youtube_dl/extractor/newgrounds.py') diff --git a/youtube_dl/extractor/newgrounds.py b/youtube_dl/extractor/newgrounds.py index dc183caec..0e26f8399 100644 --- a/youtube_dl/extractor/newgrounds.py +++ b/youtube_dl/extractor/newgrounds.py @@ -6,6 +6,9 @@ from .common import InfoExtractor from ..utils import ( extract_attributes, int_or_none, + parse_duration, + parse_filesize, + unified_timestamp, ) @@ -19,7 +22,10 @@ class NewgroundsIE(InfoExtractor): 'ext': 'mp3', 'title': 'B7 - BusMode', 'uploader': 'Burn7', - } + 'timestamp': 1378878540, + 'upload_date': '20130911', + 'duration': 143, + }, }, { 'url': 'https://www.newgrounds.com/portal/view/673111', 'md5': '3394735822aab2478c31b1004fe5e5bc', @@ -28,6 +34,8 @@ class NewgroundsIE(InfoExtractor): 'ext': 'mp4', 'title': 'Dancin', 'uploader': 'Squirrelman82', + 'timestamp': 1460256780, + 'upload_date': '20160410', }, }, { # source format unavailable, additional mp4 formats @@ -37,6 +45,8 @@ class NewgroundsIE(InfoExtractor): 'ext': 'mp4', 'title': 'ZTV News Episode 8', 'uploader': 'BennettTheSage', + 'timestamp': 1487965140, + 'upload_date': '20170224', }, 'params': { 'skip_download': True, @@ -51,11 +61,11 @@ class NewgroundsIE(InfoExtractor): title = self._html_search_regex( r'([^>]+)', webpage, 'title') - video_url = self._parse_json(self._search_regex( + media_url = self._parse_json(self._search_regex( r'"url"\s*:\s*("[^"]+"),', webpage, ''), media_id) formats = [{ - 'url': video_url, + 'url': media_url, 'format_id': 'source', 'quality': 1, }] @@ -64,7 +74,7 @@ class NewgroundsIE(InfoExtractor): r'max_resolution["\']\s*:\s*(\d+)', webpage, 'max resolution', default=None)) if max_resolution: - url_base = video_url.rpartition('.')[0] + url_base = media_url.rpartition('.')[0] for resolution in (360, 720, 1080): if resolution > max_resolution: break @@ -77,14 +87,32 @@ class NewgroundsIE(InfoExtractor): self._check_formats(formats, media_id) self._sort_formats(formats) - uploader = self._html_search_regex( + uploader = self._search_regex( r'(?:Author|Writer)\s*]+>([^<]+)', webpage, 'uploader', fatal=False) + timestamp = unified_timestamp(self._search_regex( + r'
Uploaded
\s*
([^<]+)', webpage, 'timestamp', + default=None)) + duration = parse_duration(self._search_regex( + r'
Song\s*
.+?
([^<]+)', webpage, 'duration', + default=None)) + + filesize_approx = parse_filesize(self._html_search_regex( + r'
Song\s*
(.+?)
', webpage, 'filesize', + default=None)) + if len(formats) == 1: + formats[0]['filesize_approx'] = filesize_approx + + if '
Song' in webpage: + formats[0]['vcodec'] = 'none' + return { 'id': media_id, 'title': title, 'uploader': uploader, + 'timestamp': timestamp, + 'duration': duration, 'formats': formats, } -- cgit 1.4.1