github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[newgrounds] fix: video download

Browse source
This commit is contained in:
insaneracist 2020-10-28 16:55:47 -07:00
parent cf553deceb
commit 139e10ad98
1 changed files with 69 additions and 34 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

61
youtube_dlc/extractor/newgrounds.py
View file

@ -4,6 +4,7 @@
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_duration, parse_duration,
@ -20,22 +21,22 @@ class NewgroundsIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '549479', 'id': '549479',
'ext': 'mp3', 'ext': 'mp3',
'title': 'B7 - BusMode', 'title': 'Burn7 - B7 - BusMode',
'uploader': 'Burn7', 'uploader': 'Burn7',
'timestamp': 1378878540, 'timestamp': 1378878540,
'upload_date': '20130911', 'upload_date': '20130911',
'duration': 143, 'duration': 143,
}, },
}, { }, {
'url': 'https://www.newgrounds.com/portal/view/673111', 'url': 'https://www.newgrounds.com/portal/view/1',
'md5': '3394735822aab2478c31b1004fe5e5bc', 'md5': 'fbfb40e2dc765a7e830cb251d370d981',
'info_dict': { 'info_dict': {
'id': '673111', 'id': '1',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Dancin', 'title': 'Brian-Beaton - Scrotum 1',
'uploader': 'Squirrelman82', 'uploader': 'Brian-Beaton',
'timestamp': 1460256780, 'timestamp': 955064100,
'upload_date': '20160410', 'upload_date': '20000406',
}, },
}, { }, {
# source format unavailable, additional mp4 formats # source format unavailable, additional mp4 formats
@ -43,7 +44,7 @@ class NewgroundsIE(InfoExtractor):
'info_dict': { 'info_dict': {
'id': '689400', 'id': '689400',
'ext': 'mp4', 'ext': 'mp4',
'title': 'ZTV News Episode 8', 'title': 'Bennettthesage - ZTV News Episode 8',
'uploader': 'BennettTheSage', 'uploader': 'BennettTheSage',
'timestamp': 1487965140, 'timestamp': 1487965140,
'upload_date': '20170224', 'upload_date': '20170224',
@ -55,15 +56,18 @@ class NewgroundsIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
media_id = self._match_id(url) media_id = self._match_id(url)
formats = []
uploader = None
webpage = self._download_webpage(url, media_id) webpage = self._download_webpage(url, media_id)
title = self._html_search_regex( title = self._html_search_regex(
r'<title>([^>]+)</title>', webpage, 'title') r'<title>([^>]+)</title>', webpage, 'title')
media_url = self._parse_json(self._search_regex( media_url_string = self._search_regex(
r'"url"\s*:\s*("[^"]+"),', webpage, ''), media_id) r'"url"\s*:\s*("[^"]+"),', webpage, 'media url', default=None, fatal=False)
if media_url_string:
media_url = self._parse_json(media_url_string, media_id)
formats = [{ formats = [{
'url': media_url, 'url': media_url,
'format_id': 'source', 'format_id': 'source',
@ -83,12 +87,40 @@ def _real_extract(self, url):
'format_id': '%dp' % resolution, 'format_id': '%dp' % resolution,
'height': resolution, 'height': resolution,
}) })
else:
video_id = int_or_none(self._search_regex(
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',
'Referer': url,
'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')
title = json_video.get('title')
media_formats = json_video.get('sources', [])
for media_format in media_formats:
media_sources = media_formats[media_format]
for source in media_sources:
formats.append({
'format_id': media_format,
'quality': int_or_none(media_format[:-1]),
'url': source.get('src')
})
self._check_formats(formats, media_id) self._check_formats(formats, media_id)
self._sort_formats(formats) self._sort_formats(formats)
if not uploader:
uploader = self._html_search_regex( uploader = self._html_search_regex(
(r'(?s)<h4[^>]*>(.+?)</h4>.*?<em>\s*Author\s*</em>', (r'(?s)<h4[^>]*>(.+?)</h4>.*?<em>\s*(?:Author|Artist)\s*</em>',
r'(?:Author|Writer)\s*<a[^>]+>([^<]+)'), webpage, 'uploader', r'(?:Author|Writer)\s*<a[^>]+>([^<]+)'), webpage, 'uploader',
fatal=False) fatal=False)
@ -109,6 +141,9 @@ def _real_extract(self, url):
if '<dd>Song' in webpage: if '<dd>Song' in webpage:
formats[0]['vcodec'] = 'none' formats[0]['vcodec'] = 'none'
if uploader:
title = "%s - %s" % (uploader, title)
return { return {
'id': media_id, 'id': media_id,
'title': title, 'title': title,