[extractor/youtube] Add `no-youtube-prefer-utc-upload-date` compat option (#4771)

This option reverts https://github.com/yt-dlp/yt-dlp/commit/992f9a730b49fd36fc422be8d802f98ebcdce418 and https://github.com/yt-dlp/yt-dlp/commit/17322130a954577bb03b833d5c435638e51e19f2 to prefer the non-UTC upload date in microformats.

Authored by: coletdjnz, pukkandan

diff --git a/README.md b/README.md
index 896508965254c10ae1badd5790b1cac9fc0ca4a0..83ab309c6c2a92a9b55e9d7c1c7fad6963be4d22 100644 (file)
--- a/README.md
+++ b/README.md
@@ -141,6 +141,7 @@ ### Differences in default behavior
 * Live chats (if available) are considered as subtitles. Use `--sub-langs all,-live_chat` to download all subtitles except live chat. You can also use `--compat-options no-live-chat` to prevent any live chat/danmaku from downloading
 * Youtube channel URLs are automatically redirected to `/video`. Append a `/featured` to the URL to download only the videos in the home page. If the channel does not have a videos tab, we try to download the equivalent `UU` playlist instead. For all other tabs, if the channel does not show the requested tab, an error will be raised. Also, `/live` URLs raise an error if there are no live videos instead of silently downloading the entire channel. You may use `--compat-options no-youtube-channel-redirect` to revert all these redirections
 * Unavailable videos are also listed for youtube playlists. Use `--compat-options no-youtube-unavailable-videos` to remove this
+* The upload dates extracted from YouTube are in UTC [when available](https://github.com/yt-dlp/yt-dlp/blob/89e4d86171c7b7c997c77d4714542e0383bf0db0/yt_dlp/extractor/youtube.py#L3898-L3900). Use `--compat-options no-youtube-prefer-utc-upload-date` to prefer the non-UTC upload date.
 * If `ffmpeg` is used as the downloader, the downloading and merging of formats happen in a single step when possible. Use `--compat-options no-direct-merge` to revert this
 * Thumbnail embedding in `mp4` is done with mutagen if possible. Use `--compat-options embed-thumbnail-atomicparsley` to force the use of AtomicParsley instead
 * Some private fields such as filenames are removed by default from the infojson. Use `--no-clean-infojson` or `--compat-options no-clean-infojson` to revert this

diff --git a/yt_dlp/extractor/youtube.py b/yt_dlp/extractor/youtube.py
index ee9cce16e7f69f8f2df5f210ac0fb70069cf648c..b1eda0d07fb1e9c15f8f9c47823bcc75909a3ed9 100644 (file)
--- a/yt_dlp/extractor/youtube.py
+++ b/yt_dlp/extractor/youtube.py
@@ -2159,6 +2159,35 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'comment_count': int,
                 'channel_follower_count': int
             }
+        }, {
+            # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
+            'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
+            'info_dict': {
+                'id': '2NUZ8W2llS4',
+                'ext': 'mp4',
+                'title': 'The NP that test your phone performance 🙂',
+                'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
+                'uploader': 'Leon Nguyen',
+                'uploader_id': 'VNSXIII',
+                'uploader_url': 'http://www.youtube.com/user/VNSXIII',
+                'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
+                'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
+                'duration': 21,
+                'view_count': int,
+                'age_limit': 0,
+                'categories': ['Gaming'],
+                'tags': 'count:23',
+                'playable_in_embed': True,
+                'live_status': 'not_live',
+                'upload_date': '20220102',
+                'like_count': int,
+                'availability': 'public',
+                'channel': 'Leon Nguyen',
+                'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
+                'comment_count': int,
+                'channel_follower_count': int
+            },
+            'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
         }, {
             # date text is premiered video, ensure upload date in UTC (published 1641172509)
             'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
@@ -3920,7 +3949,12 @@ def process_language(container, base_url, lang_code, sub_name, query):
         upload_date = (
             unified_strdate(get_first(microformats, 'uploadDate'))
             or unified_strdate(search_meta('uploadDate')))
-        if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
+        if not upload_date or (
+            not info.get('is_live')
+            and not info.get('was_live')
+            and info.get('live_status') != 'is_upcoming'
+            and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
+        ):
             upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date
         info['upload_date'] = upload_date
 

diff --git a/yt_dlp/options.py b/yt_dlp/options.py
index da6b1d25b000027b4df6f2bfa5f9e1d8d2b8ed67..0fbf1f028b1ab9fb2f596f6280b45da92d7a1bde 100644 (file)
--- a/yt_dlp/options.py
+++ b/yt_dlp/options.py
@@ -444,6 +444,7 @@ def _alias_callback(option, opt_str, value, parser, opts, nargs):
                 'multistreams', 'no-live-chat', 'playlist-index', 'list-formats', 'no-direct-merge',
                 'no-youtube-channel-redirect', 'no-youtube-unavailable-videos', 'no-attach-info-json', 'embed-metadata',
                 'embed-thumbnail-atomicparsley', 'seperate-video-versions', 'no-clean-infojson', 'no-keep-subs', 'no-certifi',
+                'no-youtube-prefer-utc-upload-date'
             }, 'aliases': {
                 'youtube-dl': ['all', '-multistreams'],
                 'youtube-dlc': ['all', '-no-youtube-channel-redirect', '-no-live-chat'],