[core] Parse release_year from release_date (#8524)

Closes #7263
Authored by: seproDev

README.md

@@ -1309,6 +1309,7 @@ The available fields are:
  - `upload_date` (string): Video upload date in UTC (YYYYMMDD)
  - `release_timestamp` (numeric): UNIX timestamp of the moment the video was released
  - `release_date` (string): The date (YYYYMMDD) when the video was released in UTC
+ - `release_year` (numeric): Year (YYYY) when the video or album was released
  - `modified_timestamp` (numeric): UNIX timestamp of the moment the video was last modified
  - `modified_date` (string): The date (YYYYMMDD) when the video was last modified in UTC
  - `uploader_id` (string): Nickname or id of the video uploader
@@ -1382,7 +1383,6 @@ Available for the media that is a track or a part of a music album:
  - `album_type` (string): Type of the album
  - `album_artist` (string): List of all artists appeared on the album
  - `disc_number` (numeric): Number of the disc or other physical medium the track belongs to
- - `release_year` (numeric): Year (YYYY) when the album was released
 
 Available only when using `--download-sections` and for `chapter:` prefix when using `--split-chapters` for videos with internal chapters:
 

test/helper.py

@@ -10,7 +10,7 @@ import types
 import yt_dlp.extractor
 from yt_dlp import YoutubeDL
 from yt_dlp.compat import compat_os_name
-from yt_dlp.utils import preferredencoding, write_string
+from yt_dlp.utils import preferredencoding, try_call, write_string
 
 if 'pytest' in sys.modules:
     import pytest
@@ -223,6 +223,10 @@ def sanitize_got_info_dict(got_dict):
     if test_info_dict.get('display_id') == test_info_dict.get('id'):
         test_info_dict.pop('display_id')
 
+    # release_year may be generated from release_date
+    if try_call(lambda: test_info_dict['release_year'] == int(test_info_dict['release_date'][:4])):
+        test_info_dict.pop('release_year')
+
     # Check url for flat entries
     if got_dict.get('_type', 'video') != 'video' and got_dict.get('url'):
         test_info_dict['url'] = got_dict['url']

yt_dlp/YoutubeDL.py

@@ -2589,6 +2589,9 @@ class YoutubeDL:
                     upload_date = datetime.datetime.fromtimestamp(info_dict[ts_key], datetime.timezone.utc)
                     info_dict[date_key] = upload_date.strftime('%Y%m%d')
 
+        if not info_dict.get('release_year'):
+            info_dict['release_year'] = traverse_obj(info_dict, ('release_date', {lambda x: int(x[:4])}))
+
         live_keys = ('is_live', 'was_live')
         live_status = info_dict.get('live_status')
         if live_status is None:

yt_dlp/extractor/archiveorg.py

@@ -52,7 +52,6 @@ class ArchiveOrgIE(InfoExtractor):
             'creator': 'SRI International',
             'uploader': 'laura@archive.org',
             'thumbnail': r're:https://archive\.org/download/.*\.jpg',
-            'release_year': 1968,
             'display_id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect.cdr',
             'track': 'XD300-23 68HighlightsAResearchCntAugHumanIntellect',
 
@@ -134,7 +133,6 @@ class ArchiveOrgIE(InfoExtractor):
             'album': '1977-05-08 - Barton Hall - Cornell University',
             'release_date': '19770508',
             'display_id': 'gd1977-05-08d01t07.flac',
-            'release_year': 1977,
             'track_number': 7,
         },
     }, {

yt_dlp/extractor/common.py

@@ -286,6 +286,9 @@ class InfoExtractor:
                     If it is not clear whether to use timestamp or this, use the former
     release_date:   The date (YYYYMMDD) when the video was released in UTC.
                     If not explicitly set, calculated from release_timestamp
+    release_year:   Year (YYYY) as integer when the video or album was released.
+                    To be used if no exact release date is known.
+                    If not explicitly set, calculated from release_date.
     modified_timestamp: UNIX timestamp of the moment the video was last modified.
     modified_date:   The date (YYYYMMDD) when the video was last modified in UTC.
                     If not explicitly set, calculated from modified_timestamp
@@ -427,7 +430,6 @@ class InfoExtractor:
                     and compilations).
     disc_number:    Number of the disc or other physical medium the track belongs to,
                     as an integer.
-    release_year:   Year (YYYY) when the album was released.
     composer:       Composer of the piece
 
     The following fields should only be set for clips that should be cut from the original video:

yt_dlp/extractor/harpodeon.py

@@ -1,5 +1,5 @@
 from .common import InfoExtractor
-from ..utils import unified_strdate
+from ..utils import int_or_none
 
 
 class HarpodeonIE(InfoExtractor):
@@ -14,7 +14,7 @@ class HarpodeonIE(InfoExtractor):
             'title': 'The Smoking Out of Bella Butts',
             'description': 'md5:47e16bdb41fc8a79c83ab83af11c8b77',
             'creator': 'Vitagraph Company of America',
-            'release_date': '19150101'
+            'release_year': 1915,
         }
     }, {
         'url': 'https://www.harpodeon.com/preview/The_Smoking_Out_of_Bella_Butts/268068288',
@@ -25,7 +25,7 @@ class HarpodeonIE(InfoExtractor):
             'title': 'The Smoking Out of Bella Butts',
             'description': 'md5:47e16bdb41fc8a79c83ab83af11c8b77',
             'creator': 'Vitagraph Company of America',
-            'release_date': '19150101'
+            'release_year': 1915,
         }
     }, {
         'url': 'https://www.harpodeon.com/preview/Behind_the_Screen/421838710',
@@ -36,7 +36,7 @@ class HarpodeonIE(InfoExtractor):
             'title': 'Behind the Screen',
             'description': 'md5:008972a3dc51fba3965ee517d2ba9155',
             'creator': 'Lone Star Corporation',
-            'release_date': '19160101'
+            'release_year': 1916,
         }
     }]
 
@@ -66,5 +66,5 @@ class HarpodeonIE(InfoExtractor):
             'http_headers': {'Referer': url},
             'description': self._html_search_meta('description', webpage, fatal=False),
             'creator': creator,
-            'release_date': unified_strdate(f'{release_year}0101')
+            'release_year': int_or_none(release_year),
         }

yt_dlp/extractor/monstercat.py

@@ -24,7 +24,6 @@ class MonstercatIE(InfoExtractor):
             'title': 'The Secret Language of Trees',
             'id': '742779548009',
             'thumbnail': 'https://www.monstercat.com/release/742779548009/cover',
-            'release_year': 2023,
             'release_date': '20230711',
             'album': 'The Secret Language of Trees',
             'album_artist': 'BT',
@@ -71,7 +70,6 @@ class MonstercatIE(InfoExtractor):
             'thumbnail': f'https://www.monstercat.com/release/{url_id}/cover',
             'album_artist': try_call(
                 lambda: get_element_by_class('h-normal text-uppercase mb-desktop-medium mb-smallish', html)),
-            'release_year': int_or_none(date[:4]) if date else None,
             'release_date': date,
         }
 

yt_dlp/extractor/youtube.py

@@ -2072,7 +2072,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'track': 'Voyeur Girl',
                 'album': 'it\'s too much love to know my dear',
                 'release_date': '20190313',
-                'release_year': 2019,
                 'alt_title': 'Voyeur Girl',
                 'view_count': int,
                 'playable_in_embed': True,