Mirrors/yt-dlp
2
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-14 23:32:33 +00:00
Code Issues Projects Releases Packages Wiki Activity

[Newgrounds] Improve extractor and fix playlist (#627)

Browse source 
Authored by: u-spec-png
This commit is contained in:
SsSsS 2021-08-04 15:48:54 +00:00 committed by GitHub
parent bb36a55c41
commit 36576d7c4c
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 49 additions and 44 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

93
yt_dlp/extractor/newgrounds.py
View file

@ -4,9 +4,9 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError,
extract_attributes, extract_attributes,
int_or_none, int_or_none,
parse_count,
parse_duration, parse_duration,
parse_filesize, parse_filesize,
unified_timestamp, unified_timestamp,
@ -14,18 +14,19 @@ from ..utils import (
class NewgroundsIE(InfoExtractor): class NewgroundsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>[0-9]+)' _VALID_URL = r'https?://(?:www\.)?newgrounds\.com/(?:audio/listen|portal/view)/(?P<id>\d+)(?:/format/flash)?'
_TESTS = [{ _TESTS = [{
'url': 'https://www.newgrounds.com/audio/listen/549479', 'url': 'https://www.newgrounds.com/audio/listen/549479',
'md5': 'fe6033d297591288fa1c1f780386f07a', 'md5': 'fe6033d297591288fa1c1f780386f07a',
'info_dict': { 'info_dict': {
'id': '549479', 'id': '549479',
'ext': 'mp3', 'ext': 'mp3',
'title': 'Burn7 - B7 - BusMode', 'title': 'B7 - BusMode',
'uploader': 'Burn7', 'uploader': 'Burn7',
'timestamp': 1378878540, 'timestamp': 1378878540,
'upload_date': '20130911', 'upload_date': '20130911',
'duration': 143, 'duration': 143,
'description': 'md5:6d885138814015dfd656c2ddb00dacfc',
}, },
}, { }, {
'url': 'https://www.newgrounds.com/portal/view/1', 'url': 'https://www.newgrounds.com/portal/view/1',
@ -33,10 +34,11 @@ class NewgroundsIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '1', 'id': '1',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Brian-Beaton - Scrotum 1', 'title': 'Scrotum 1',
'uploader': 'Brian-Beaton', 'uploader': 'Brian-Beaton',
'timestamp': 955064100, 'timestamp': 955064100,
'upload_date': '20000406', 'upload_date': '20000406',
'description': 'Scrotum plays "catch."',
}, },
}, { }, {
# source format unavailable, additional mp4 formats # source format unavailable, additional mp4 formats
@ -44,14 +46,39 @@ class NewgroundsIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '689400', 'id': '689400',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Bennettthesage - ZTV News Episode 8', 'title': 'ZTV News Episode 8',
'uploader': 'BennettTheSage', 'uploader': 'ZONE-SAMA',
'timestamp': 1487965140, 'timestamp': 1487965140,
'upload_date': '20170224', 'upload_date': '20170224',
'description': 'ZTV News Episode 8 (February 2017)',
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
}, {
'url': 'https://www.newgrounds.com/portal/view/297383',
'md5': '2c11f5fd8cb6b433a63c89ba3141436c',
'info_dict': {
'id': '297383',
'ext': 'mp4',
'title': 'Metal Gear Awesome',
'uploader': 'Egoraptor',
'timestamp': 1140663240,
'upload_date': '20060223',
'description': 'Metal Gear is awesome is so is this movie.',
}
}, {
'url': 'https://www.newgrounds.com/portal/view/297383/format/flash',
'md5': '5d05585a9a0caca059f5abfbd3865524',
'info_dict': {
'id': '297383',
'ext': 'swf',
'title': 'Metal Gear Awesome',
'description': 'Metal Gear is awesome is so is this movie.',
'uploader': 'Egoraptor',
'upload_date': '20060223',
'timestamp': 1140663240,
}
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -73,38 +100,14 @@ class NewgroundsIE(InfoExtractor):
'format_id': 'source', 'format_id': 'source',
'quality': 1, '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 = media_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,
})
else: else:
video_id = int_or_none(self._search_regex( json_video = self._download_json('https://www.newgrounds.com/portal/video/' + media_id, media_id, headers={
r'data-movie-id=\\"([0-9]+)\\"', webpage, ''))
if not video_id:
raise ExtractorError('Could not extract media data')
url_video_data = 'https://www.newgrounds.com/portal/video/%s' % video_id
headers = {
'Accept': 'application/json', 'Accept': 'application/json',
'Referer': url, 'Referer': url,
'X-Requested-With': 'XMLHttpRequest' 'X-Requested-With': 'XMLHttpRequest'
} })
json_video = self._download_json(url_video_data, video_id, headers=headers, fatal=False)
if not json_video:
raise ExtractorError('Could not fetch media data')
uploader = json_video.get('author') uploader = json_video.get('author')
title = json_video.get('title')
media_formats = json_video.get('sources', []) media_formats = json_video.get('sources', [])
for media_format in media_formats: for media_format in media_formats:
media_sources = media_formats[media_format] media_sources = media_formats[media_format]
@ -115,9 +118,6 @@ class NewgroundsIE(InfoExtractor):
'url': source.get('src') 'url': source.get('src')
}) })
self._check_formats(formats, media_id)
self._sort_formats(formats)
if not uploader: if not uploader:
uploader = self._html_search_regex( uploader = self._html_search_regex(
(r'(?s)<h4[^>]*>(.+?)</h4>.*?<em>\s*(?:Author|Artist)\s*</em>', (r'(?s)<h4[^>]*>(.+?)</h4>.*?<em>\s*(?:Author|Artist)\s*</em>',
@ -132,6 +132,9 @@ class NewgroundsIE(InfoExtractor):
r'(?s)<dd>\s*Song\s*</dd>\s*<dd>.+?</dd>\s*<dd>([^<]+)', webpage, r'(?s)<dd>\s*Song\s*</dd>\s*<dd>.+?</dd>\s*<dd>([^<]+)', webpage,
'duration', default=None)) 'duration', default=None))
view_count = parse_count(self._html_search_regex(r'(?s)<dt>\s*Views\s*</dt>\s*<dd>([\d\.,]+)</dd>', webpage,
'view_count', fatal=False, default=None))
filesize_approx = parse_filesize(self._html_search_regex( filesize_approx = parse_filesize(self._html_search_regex(
r'(?s)<dd>\s*Song\s*</dd>\s*<dd>(.+?)</dd>', webpage, 'filesize', r'(?s)<dd>\s*Song\s*</dd>\s*<dd>(.+?)</dd>', webpage, 'filesize',
default=None)) default=None))
@ -140,9 +143,8 @@ class NewgroundsIE(InfoExtractor):
if '<dd>Song' in webpage: if '<dd>Song' in webpage:
formats[0]['vcodec'] = 'none' formats[0]['vcodec'] = 'none'
self._check_formats(formats, media_id)
if uploader: self._sort_formats(formats)
title = "%s - %s" % (uploader, title)
return { return {
'id': media_id, 'id': media_id,
@ -151,6 +153,9 @@ class NewgroundsIE(InfoExtractor):
'timestamp': timestamp, 'timestamp': timestamp,
'duration': duration, 'duration': duration,
'formats': formats, 'formats': formats,
'thumbnail': self._og_search_thumbnail(webpage),
'description': self._og_search_description(webpage),
'view_count': view_count,
} }
@ -162,14 +167,14 @@ class NewgroundsPlaylistIE(InfoExtractor):
'id': 'cats', 'id': 'cats',
'title': 'Cats', 'title': 'Cats',
}, },
'playlist_mincount': 46, 'playlist_mincount': 45,
}, { }, {
'url': 'http://www.newgrounds.com/portal/search/author/ZONE-SAMA', 'url': 'https://www.newgrounds.com/collection/dogs',
'info_dict': { 'info_dict': {
'id': 'ZONE-SAMA', 'id': 'dogs',
'title': 'Portal Search: ZONE-SAMA', 'title': 'Dogs',
}, },
'playlist_mincount': 47, 'playlist_mincount': 26,
}, { }, {
'url': 'http://www.newgrounds.com/audio/search/title/cats', 'url': 'http://www.newgrounds.com/audio/search/title/cats',
'only_matching': True, 'only_matching': True,
@ -190,7 +195,7 @@ class NewgroundsPlaylistIE(InfoExtractor):
entries = [] entries = []
for a, path, media_id in re.findall( for a, path, media_id in re.findall(
r'(<a[^>]+\bhref=["\']/?((?:portal/view|audio/listen)/(\d+))[^>]+>)', r'(<a[^>]+\bhref=["\'][^"\']+((?:portal/view|audio/listen)/(\d+))[^>]+>)',
webpage): webpage):
a_class = extract_attributes(a).get('class') a_class = extract_attributes(a).get('class')
if a_class not in ('item-portalsubmission', 'item-audiosubmission'): if a_class not in ('item-portalsubmission', 'item-audiosubmission'):