mirror of https://github.com/yt-dlp/yt-dlp.git
Merge 4cf46e29c1 into 351dc0bc33
This commit is contained in:
coletdjnz
GitHub
commit
c6cd36ec91
|
|
@ -5,6 +5,7 @@ import os
|
|||
import sys
|
||||
import unittest
|
||||
import warnings
|
||||
import datetime as dt
|
||||
|
||||
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||||
|
||||
|
|
@ -27,6 +28,7 @@ from yt_dlp.utils import (
|
|||
ExtractorError,
|
||||
InAdvancePagedList,
|
||||
LazyList,
|
||||
NO_DEFAULT,
|
||||
OnDemandPagedList,
|
||||
Popen,
|
||||
age_restricted,
|
||||
|
|
@ -768,6 +770,11 @@ class TestUtil(unittest.TestCase):
|
|||
|
||||
def test_parse_iso8601(self):
|
||||
self.assertEqual(parse_iso8601('2014-03-23T23:04:26+0100'), 1395612266)
|
||||
self.assertEqual(parse_iso8601('2014-03-23T23:04:26-07:00'), 1395641066)
|
||||
self.assertEqual(parse_iso8601('2014-03-23T23:04:26', timezone=dt.timedelta(hours=-7)), 1395641066)
|
||||
self.assertEqual(parse_iso8601('2014-03-23T23:04:26', timezone=NO_DEFAULT), None)
|
||||
# default does not override timezone in date_str
|
||||
self.assertEqual(parse_iso8601('2014-03-23T23:04:26-07:00', timezone=dt.timedelta(hours=-10)), 1395641066)
|
||||
self.assertEqual(parse_iso8601('2014-03-23T22:04:26+0000'), 1395612266)
|
||||
self.assertEqual(parse_iso8601('2014-03-23T22:04:26Z'), 1395612266)
|
||||
self.assertEqual(parse_iso8601('2014-03-23T22:04:26.1234Z'), 1395612266)
|
||||
|
|
|
|||
|
|
@ -1325,6 +1325,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
|
||||
'uploader_id': '@PhilippHagemeister',
|
||||
'heatmap': 'count:100',
|
||||
'timestamp': 1349198244,
|
||||
}
|
||||
},
|
||||
{
|
||||
|
|
@ -1368,6 +1369,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
|
||||
'uploader_id': '@PhilippHagemeister',
|
||||
'heatmap': 'count:100',
|
||||
'timestamp': 1349198244,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
|
|
@ -1454,6 +1456,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'comment_count': int,
|
||||
'channel_is_verified': True,
|
||||
'heatmap': 'count:100',
|
||||
'timestamp': 1401991663,
|
||||
},
|
||||
},
|
||||
{
|
||||
|
|
@ -1513,6 +1516,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader': 'Projekt Melody',
|
||||
'uploader_url': 'https://www.youtube.com/@ProjektMelody',
|
||||
'uploader_id': '@ProjektMelody',
|
||||
'timestamp': 1577508724,
|
||||
},
|
||||
},
|
||||
{
|
||||
|
|
@ -1618,6 +1622,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader_url': 'https://www.youtube.com/@Olympics',
|
||||
'uploader_id': '@Olympics',
|
||||
'channel_is_verified': True,
|
||||
'timestamp': 1440707674,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': 'requires avconv',
|
||||
|
|
@ -1651,6 +1656,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader': '孫ᄋᄅ',
|
||||
'uploader_url': 'https://www.youtube.com/@AllenMeow',
|
||||
'uploader_id': '@AllenMeow',
|
||||
'timestamp': 1299776999,
|
||||
},
|
||||
},
|
||||
# url_encoded_fmt_stream_map is empty string
|
||||
|
|
@ -1794,6 +1800,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
},
|
||||
}],
|
||||
'params': {'skip_download': True},
|
||||
'skip': 'Not multifeed anymore',
|
||||
},
|
||||
{
|
||||
# Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
|
||||
|
|
@ -1902,6 +1909,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader': 'The Berkman Klein Center for Internet & Society',
|
||||
'uploader_id': '@BKCHarvard',
|
||||
'uploader_url': 'https://www.youtube.com/@BKCHarvard',
|
||||
'timestamp': 1422422076,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
|
|
@ -1937,6 +1945,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader_id': '@BernieSanders',
|
||||
'channel_is_verified': True,
|
||||
'heatmap': 'count:100',
|
||||
'timestamp': 1447987198,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
|
|
@ -2000,6 +2009,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader_id': '@Vsauce',
|
||||
'comment_count': int,
|
||||
'channel_is_verified': True,
|
||||
'timestamp': 1484761047,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
|
|
@ -2155,6 +2165,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader': 'l\'Or Vert asbl',
|
||||
'uploader_url': 'https://www.youtube.com/@ElevageOrVert',
|
||||
'uploader_id': '@ElevageOrVert',
|
||||
'timestamp': 1497343210,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
|
|
@ -2193,6 +2204,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader_id': '@Csharp-video-tutorialsBlogspot',
|
||||
'channel_is_verified': True,
|
||||
'heatmap': 'count:100',
|
||||
'timestamp': 1377976349,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
|
|
@ -2275,6 +2287,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader_id': '@CBSMornings',
|
||||
'comment_count': int,
|
||||
'channel_is_verified': True,
|
||||
'timestamp': 1405513526,
|
||||
}
|
||||
},
|
||||
{
|
||||
|
|
@ -2292,7 +2305,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'view_count': int,
|
||||
'channel': 'Walk around Japan',
|
||||
'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
|
||||
'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
|
||||
'thumbnail': 'https://i.ytimg.com/vi/cBvYw8_A0vQ/hqdefault.jpg',
|
||||
'age_limit': 0,
|
||||
'availability': 'public',
|
||||
'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
|
||||
|
|
@ -2302,6 +2315,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader': 'Walk around Japan',
|
||||
'uploader_url': 'https://www.youtube.com/@walkaroundjapan7124',
|
||||
'uploader_id': '@walkaroundjapan7124',
|
||||
'timestamp': 1605884416,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
|
|
@ -2396,6 +2410,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'comment_count': int,
|
||||
'channel_is_verified': True,
|
||||
'heatmap': 'count:100',
|
||||
'timestamp': 1395685455,
|
||||
}, 'params': {'format': 'mhtml', 'skip_download': True}
|
||||
}, {
|
||||
# Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
|
||||
|
|
@ -2425,9 +2440,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader_url': 'https://www.youtube.com/@LeonNguyen',
|
||||
'uploader_id': '@LeonNguyen',
|
||||
'heatmap': 'count:100',
|
||||
'timestamp': 1641170939,
|
||||
}
|
||||
}, {
|
||||
# Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
|
||||
# todo: remove compat opt? no longer works
|
||||
'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
|
||||
'info_dict': {
|
||||
'id': '2NUZ8W2llS4',
|
||||
|
|
@ -2487,38 +2504,41 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'comment_count': int,
|
||||
'channel_is_verified': True,
|
||||
'heatmap': 'count:100',
|
||||
'timestamp': 1641172509,
|
||||
}
|
||||
},
|
||||
{ # continuous livestream. Microformat upload date should be preferred.
|
||||
# Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
|
||||
'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
|
||||
{ # continuous livestream.
|
||||
# Upload date was 2022-07-12T05:12:29-07:00, while stream start is 2022-07-12T15:59:30+00:00
|
||||
'url': 'https://www.youtube.com/watch?v=jfKfPfyJRdk',
|
||||
'info_dict': {
|
||||
'id': 'kgx4WGK0oNU',
|
||||
'title': r're:jazz\/lofi hip hop radio🌱chill beats to relax\/study to \[LIVE 24\/7\] \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
|
||||
'id': 'jfKfPfyJRdk',
|
||||
'ext': 'mp4',
|
||||
'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
|
||||
'availability': 'public',
|
||||
'age_limit': 0,
|
||||
'release_timestamp': 1637975704,
|
||||
'upload_date': '20210619',
|
||||
'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
|
||||
'live_status': 'is_live',
|
||||
'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
|
||||
'channel': 'Abao in Tokyo',
|
||||
'channel_follower_count': int,
|
||||
'release_date': '20211127',
|
||||
'tags': 'count:39',
|
||||
'categories': ['People & Blogs'],
|
||||
'channel_id': 'UCSJ4gkVC6NrvII8umztf0Ow',
|
||||
'like_count': int,
|
||||
'view_count': int,
|
||||
'playable_in_embed': True,
|
||||
'description': 'md5:2ef1d002cad520f65825346e2084e49d',
|
||||
'uploader': 'Lofi Girl',
|
||||
'categories': ['Music'],
|
||||
'concurrent_view_count': int,
|
||||
'uploader': 'Abao in Tokyo',
|
||||
'uploader_url': 'https://www.youtube.com/@abaointokyo',
|
||||
'uploader_id': '@abaointokyo',
|
||||
'playable_in_embed': True,
|
||||
'timestamp': 1657627949,
|
||||
'release_date': '20220712',
|
||||
'channel_url': 'https://www.youtube.com/channel/UCSJ4gkVC6NrvII8umztf0Ow',
|
||||
'description': 'md5:13a6f76df898f5674f9127139f3df6f7',
|
||||
'age_limit': 0,
|
||||
'thumbnail': 'https://i.ytimg.com/vi/jfKfPfyJRdk/maxresdefault.jpg',
|
||||
'release_timestamp': 1657641570,
|
||||
'uploader_url': 'https://www.youtube.com/@LofiGirl',
|
||||
'channel_follower_count': int,
|
||||
'channel_is_verified': True,
|
||||
'title': r're:^lofi hip hop radio 📚 - beats to relax/study to',
|
||||
'view_count': int,
|
||||
'live_status': 'is_live',
|
||||
'tags': 'count:32',
|
||||
'channel': 'Lofi Girl',
|
||||
'availability': 'public',
|
||||
'upload_date': '20220712',
|
||||
'uploader_id': '@LofiGirl',
|
||||
},
|
||||
'params': {'skip_download': True}
|
||||
'params': {'skip_download': True},
|
||||
}, {
|
||||
'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
|
||||
'info_dict': {
|
||||
|
|
@ -2544,6 +2564,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader_id': '@lesmiscore',
|
||||
'uploader': 'Lesmiscore',
|
||||
'uploader_url': 'https://www.youtube.com/@lesmiscore',
|
||||
'timestamp': 1648005313,
|
||||
}
|
||||
}, {
|
||||
# Prefer primary title+description language metadata by default
|
||||
|
|
@ -2571,6 +2592,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader_url': 'https://www.youtube.com/@coletdjnz',
|
||||
'uploader_id': '@coletdjnz',
|
||||
'uploader': 'cole-dlp-test-acc',
|
||||
'timestamp': 1662677394,
|
||||
},
|
||||
'params': {'skip_download': True}
|
||||
}, {
|
||||
|
|
@ -2584,7 +2606,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'duration': 5,
|
||||
'live_status': 'not_live',
|
||||
'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
|
||||
'upload_date': '20220728',
|
||||
'upload_date': '20220729',
|
||||
'view_count': int,
|
||||
'categories': ['People & Blogs'],
|
||||
'thumbnail': r're:^https?://.*\.jpg',
|
||||
|
|
@ -2597,6 +2619,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader_url': 'https://www.youtube.com/@coletdjnz',
|
||||
'uploader_id': '@coletdjnz',
|
||||
'uploader': 'cole-dlp-test-acc',
|
||||
'timestamp': 1659073275,
|
||||
'like_count': int,
|
||||
},
|
||||
'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
|
||||
'expected_warnings': [r'Preferring "fr" translated fields'],
|
||||
|
|
@ -2662,6 +2686,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader': 'Projekt Melody',
|
||||
'uploader_id': '@ProjektMelody',
|
||||
'uploader_url': 'https://www.youtube.com/@ProjektMelody',
|
||||
'timestamp': 1577508724,
|
||||
},
|
||||
'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
|
||||
},
|
||||
|
|
@ -2696,6 +2721,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader_id': '@sana_natori',
|
||||
'channel_is_verified': True,
|
||||
'heatmap': 'count:100',
|
||||
'timestamp': 1671798112,
|
||||
},
|
||||
},
|
||||
{
|
||||
|
|
@ -2765,6 +2791,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader_url': 'https://www.youtube.com/@ChristopherSykesDocumentaries',
|
||||
'uploader_id': '@ChristopherSykesDocumentaries',
|
||||
'heatmap': 'count:100',
|
||||
'timestamp': 1211825920,
|
||||
},
|
||||
'params': {
|
||||
'skip_download': True,
|
||||
|
|
@ -4562,19 +4589,35 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||
'uploader_id': channel_handle,
|
||||
'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
|
||||
})
|
||||
|
||||
# We only want timestamp IF it has time precision AND a timezone
|
||||
# Currently the uploadDate in microformats appears to be in US/Pacific timezone.
|
||||
timestamp = (
|
||||
parse_iso8601(get_first(microformats, 'uploadDate'), timezone=NO_DEFAULT)
|
||||
or parse_iso8601(search_meta('uploadDate'), timezone=NO_DEFAULT)
|
||||
)
|
||||
upload_date = (
|
||||
dt.datetime.fromtimestamp(timestamp, dt.timezone.utc).strftime('%Y%m%d') if timestamp else
|
||||
(
|
||||
unified_strdate(get_first(microformats, 'uploadDate'))
|
||||
or unified_strdate(search_meta('uploadDate'))
|
||||
))
|
||||
|
||||
# In the case we cannot get the timestamp:
|
||||
# The upload date for scheduled, live and past live streams / premieres in microformats
|
||||
# may be different from the stream date. Although not in UTC, we will prefer it in this case.
|
||||
# See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
|
||||
upload_date = (
|
||||
unified_strdate(get_first(microformats, 'uploadDate'))
|
||||
or unified_strdate(search_meta('uploadDate')))
|
||||
if not upload_date or (
|
||||
live_status in ('not_live', None)
|
||||
not timestamp
|
||||
and live_status in ('not_live', None)
|
||||
and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
|
||||
):
|
||||
# this should be in UTC, as configured in the cookie/client context
|
||||
upload_date = strftime_or_none(
|
||||
self._parse_time_text(self._get_text(vpir, 'dateText'))) or upload_date
|
||||
|
||||
info['upload_date'] = upload_date
|
||||
info['timestamp'] = timestamp
|
||||
|
||||
if upload_date and live_status not in ('is_live', 'post_live', 'is_upcoming'):
|
||||
# Newly uploaded videos' HLS formats are potentially problematic and need to be checked
|
||||
|
|
|
|||
|
|
@ -1134,7 +1134,7 @@ def is_path_like(f):
|
|||
return isinstance(f, (str, bytes, os.PathLike))
|
||||
|
||||
|
||||
def extract_timezone(date_str):
|
||||
def extract_timezone(date_str, default=None):
|
||||
m = re.search(
|
||||
r'''(?x)
|
||||
^.{8,}? # >=8 char non-TZ prefix, if present
|
||||
|
|
@ -1146,21 +1146,25 @@ def extract_timezone(date_str):
|
|||
(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2}) # hh[:]mm
|
||||
$)
|
||||
''', date_str)
|
||||
timezone = None
|
||||
|
||||
if not m:
|
||||
m = re.search(r'\d{1,2}:\d{1,2}(?:\.\d+)?(?P<tz>\s*[A-Z]+)$', date_str)
|
||||
timezone = TIMEZONE_NAMES.get(m and m.group('tz').strip())
|
||||
if timezone is not None:
|
||||
date_str = date_str[:-len(m.group('tz'))]
|
||||
timezone = dt.timedelta(hours=timezone or 0)
|
||||
timezone = dt.timedelta(hours=timezone)
|
||||
else:
|
||||
date_str = date_str[:-len(m.group('tz'))]
|
||||
if not m.group('sign'):
|
||||
timezone = dt.timedelta()
|
||||
else:
|
||||
if m.group('sign'):
|
||||
sign = 1 if m.group('sign') == '+' else -1
|
||||
timezone = dt.timedelta(
|
||||
hours=sign * int(m.group('hours')),
|
||||
minutes=sign * int(m.group('minutes')))
|
||||
|
||||
if timezone is None and default is not NO_DEFAULT:
|
||||
timezone = default or dt.timedelta()
|
||||
|
||||
return timezone, date_str
|
||||
|
||||
|
||||
|
|
@ -1172,10 +1176,9 @@ def parse_iso8601(date_str, delimiter='T', timezone=None):
|
|||
|
||||
date_str = re.sub(r'\.[0-9]+', '', date_str)
|
||||
|
||||
if timezone is None:
|
||||
timezone, date_str = extract_timezone(date_str)
|
||||
timezone, date_str = extract_timezone(date_str, timezone)
|
||||
|
||||
with contextlib.suppress(ValueError):
|
||||
with contextlib.suppress(ValueError, TypeError):
|
||||
date_format = f'%Y-%m-%d{delimiter}%H:%M:%S'
|
||||
dt_ = dt.datetime.strptime(date_str, date_format) - timezone
|
||||
return calendar.timegm(dt_.timetuple())
|
||||
|
|
|
|||
Loading…
Reference in New Issue