From 3001a84dca08612e72aa2116941868636e800f32 Mon Sep 17 00:00:00 2001 From: u-spec-png <54671367+u-spec-png@users.noreply.github.com> Date: Mon, 4 Oct 2021 18:58:02 +0000 Subject: [PATCH] [Newgrounds] Add age_limit and fix duration (#1156) Authored by: u-spec-png --- yt_dlp/extractor/newgrounds.py | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/yt_dlp/extractor/newgrounds.py b/yt_dlp/extractor/newgrounds.py index 3c49008a0..bbbd9e8ee 100644 --- a/yt_dlp/extractor/newgrounds.py +++ b/yt_dlp/extractor/newgrounds.py @@ -42,6 +42,7 @@ class NewgroundsIE(InfoExtractor): 'timestamp': 955064100, 'upload_date': '20000406', 'description': 'Scrotum plays "catch."', + 'age_limit': 17, }, }, { # source format unavailable, additional mp4 formats @@ -54,6 +55,7 @@ class NewgroundsIE(InfoExtractor): 'timestamp': 1487965140, 'upload_date': '20170224', 'description': 'ZTV News Episode 8 (February 2017)', + 'age_limit': 17, }, 'params': { 'skip_download': True, @@ -69,6 +71,7 @@ class NewgroundsIE(InfoExtractor): 'timestamp': 1140663240, 'upload_date': '20060223', 'description': 'Metal Gear is awesome is so is this movie.', + 'age_limit': 13, } }, { 'url': 'https://www.newgrounds.com/portal/view/297383/format/flash', @@ -81,8 +84,15 @@ class NewgroundsIE(InfoExtractor): 'uploader': 'Egoraptor', 'upload_date': '20060223', 'timestamp': 1140663240, + 'age_limit': 13, } }] + _AGE_LIMIT = { + 'e': 0, + 't': 13, + 'm': 17, + 'a': 18, + } def _real_extract(self, url): media_id = self._match_id(url) @@ -127,12 +137,16 @@ def _real_extract(self, url): r'(?:Author|Writer)\s*]+>([^<]+)'), webpage, 'uploader', fatal=False) + age_limit = self._html_search_regex( + r']+>', webpage, 'age_limit', default='e') + age_limit = self._AGE_LIMIT.get(age_limit) + timestamp = unified_timestamp(self._html_search_regex( (r'
\s*Uploaded\s*
\s*
([^<]+
\s*
[^<]+)', r'
\s*Uploaded\s*
\s*
([^<]+)'), webpage, 'timestamp', default=None)) duration = parse_duration(self._html_search_regex( - r'"duration"\s*:\s*["\']?([\d]+)["\']?,', webpage, + r'"duration"\s*:\s*["\']?(\d+)["\']?', webpage, 'duration', default=None)) view_count = parse_count(self._html_search_regex( @@ -164,6 +178,7 @@ def _real_extract(self, url): 'formats': formats, 'thumbnail': self._og_search_thumbnail(webpage), 'description': self._og_search_description(webpage), + 'age_limit': age_limit, 'view_count': view_count, }