Skip to content

Commit

Permalink
[CI] auto update yt_dlp to upstream commit a6783a3b9905e547f6c1d4df9d…
Browse files Browse the repository at this point in the history 
…7c7999feda8afa
  • Loading branch information
@github-actions
github-actions[bot] committed Nov 1, 2024
1 parent 71b4d73 commit 565eff4
Show file tree
Hide file tree
Showing 2 changed files with 102 additions and 58 deletions.
158 changes: 101 additions & 57 deletions lib/yt_dlp/extractor/yle_areena.py
View file
Original file line number Diff line number Diff line change
@@ -1,12 +1,13 @@
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import (
ExtractorError,
int_or_none,
parse_iso8601,
smuggle_url,
traverse_obj,
unified_strdate,
url_or_none,
)
from ..utils.traversal import traverse_obj


class YleAreenaIE(InfoExtractor):
Expand All @@ -15,9 +16,9 @@ class YleAreenaIE(InfoExtractor):
_TESTS = [
{
'url': 'https://areena.yle.fi/1-4371942',
'md5': '932edda0ecf5dfd6423804182d32f8ac',
'md5': 'd87e9a1e74e67e009990ddd413e426b4',
'info_dict': {
'id': '0_a3tjk92c',
'id': '1-4371942',
'ext': 'mp4',
'title': 'Pouchit',
'description': 'md5:01071d7056ceec375f63960f90c35366',
Expand All @@ -26,37 +27,27 @@ class YleAreenaIE(InfoExtractor):
'season_number': 1,
'episode': 'Episode 2',
'episode_number': 2,
'thumbnail': 'http://cfvod.kaltura.com/p/1955031/sp/195503100/thumbnail/entry_id/0_a3tjk92c/version/100061',
'uploader_id': '[email protected]',
'duration': 1435,
'view_count': int,
'upload_date': '20181204',
'release_date': '20190106',
'timestamp': 1543916210,
'subtitles': {'fin': [{'url': r're:^https?://', 'ext': 'srt'}]},
'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
'age_limit': 7,
'webpage_url': 'https://areena.yle.fi/1-4371942',
'release_date': '20190105',
'release_timestamp': 1546725660,
'duration': 1435,
},
},
{
'url': 'https://areena.yle.fi/1-2158940',
'md5': 'cecb603661004e36af8c5188b5212b12',
'md5': '6369ddc5e07b5fdaeda27a495184143c',
'info_dict': {
'id': '1_l38iz9ur',
'id': '1-2158940',
'ext': 'mp4',
'title': 'Albi haluaa vessan',
'description': 'md5:15236d810c837bed861fae0e88663c33',
'description': 'Albi haluaa vessan.',
'series': 'Albi Lumiukko',
'thumbnail': 'http://cfvod.kaltura.com/p/1955031/sp/195503100/thumbnail/entry_id/1_l38iz9ur/version/100021',
'uploader_id': '[email protected]',
'duration': 319,
'view_count': int,
'upload_date': '20211202',
'release_date': '20211215',
'timestamp': 1638448202,
'subtitles': {},
'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
'age_limit': 0,
'webpage_url': 'https://areena.yle.fi/1-2158940',
'release_date': '20211215',
'release_timestamp': 1639555200,
'duration': 319,
},
},
{
Expand All @@ -67,72 +58,125 @@ class YleAreenaIE(InfoExtractor):
'title': 'HKO & Mälkki & Tanner',
'description': 'md5:b4f1b1af2c6569b33f75179a86eea156',
'series': 'Helsingin kaupunginorkesterin konsertteja',
'thumbnail': r're:^https?://.+\.jpg$',
'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
'release_date': '20230120',
'release_timestamp': 1674242079,
'duration': 8004,
},
'params': {
'skip_download': 'm3u8',
},
},
{
'url': 'https://areena.yle.fi/1-72251830',
'info_dict': {
'id': '1-72251830',
'ext': 'mp4',
'title': r're:Pentulive 2024 | Pentulive \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
'description': 'md5:1f118707d9093bf894a34fbbc865397b',
'series': 'Pentulive',
'thumbnail': r're:https://images\.cdn\.yle\.fi/image/upload/.+\.jpg',
'live_status': 'is_live',
'release_date': '20241025',
'release_timestamp': 1729875600,
},
'params': {
'skip_download': 'livestream',
},
},
{
'url': 'https://areena.yle.fi/podcastit/1-71022852',
'info_dict': {
'id': '1-71022852',
'ext': 'mp3',
'title': 'Värityspäivä',
'description': 'md5:c3a02b0455ec71d32cbe09d32ec161e2',
'series': 'Murun ja Paukun ikioma kaupunki',
'episode': 'Episode 1',
'episode_number': 1,
'release_date': '20240607',
'release_timestamp': 1717736400,
'duration': 442,
},
},
]

def _real_extract(self, url):
video_id, is_podcast = self._match_valid_url(url).group('id', 'podcast')
info = self._search_json_ld(self._download_webpage(url, video_id), video_id, default={})
json_ld = self._search_json_ld(self._download_webpage(url, video_id), video_id, default={})
video_data = self._download_json(
f'https://player.api.yle.fi/v1/preview/{video_id}.json?app_id=player_static_prod&app_key=8930d72170e48303cf5f3867780d549b',
video_id, headers={
'origin': 'https://areena.yle.fi',
'referer': 'https://areena.yle.fi/',
'content-type': 'application/json',
})
})['data']

# Example title: 'K1, J2: Pouchit | Modernit miehet'
season_number, episode_number, episode, series = self._search_regex(
r'K(?P<season_no>\d+),\s*J(?P<episode_no>\d+):?\s*\b(?P<episode>[^|]+)\s*|\s*(?P<series>.+)',
info.get('title') or '', 'episode metadata', group=('season_no', 'episode_no', 'episode', 'series'),
json_ld.get('title') or '', 'episode metadata', group=('season_no', 'episode_no', 'episode', 'series'),
default=(None, None, None, None))
description = traverse_obj(video_data, ('data', 'ongoing_ondemand', 'description', 'fin'), expected_type=str)
description = traverse_obj(video_data, ('ongoing_ondemand', 'description', 'fin', {str}))

subtitles = {}
for sub in traverse_obj(video_data, ('data', 'ongoing_ondemand', 'subtitles', ...)):
if url_or_none(sub.get('uri')):
subtitles.setdefault(sub.get('language') or 'und', []).append({
'url': sub['uri'],
'ext': 'srt',
'name': sub.get('kind'),
})
for sub in traverse_obj(video_data, ('ongoing_ondemand', 'subtitles', lambda _, v: url_or_none(v['uri']))):
subtitles.setdefault(sub.get('language') or 'und', []).append({
'url': sub['uri'],
'ext': 'srt',
'name': sub.get('kind'),
})

if is_podcast:
info_dict = {
'url': video_data['data']['ongoing_ondemand']['media_url'],
}
elif kaltura_id := traverse_obj(video_data, ('data', 'ongoing_ondemand', 'kaltura', 'id', {str})):
info_dict = {
info_dict, metadata = {}, {}
if is_podcast and traverse_obj(video_data, ('ongoing_ondemand', 'media_url', {url_or_none})):
metadata = video_data['ongoing_ondemand']
info_dict['url'] = metadata['media_url']
elif traverse_obj(video_data, ('ongoing_event', 'manifest_url', {url_or_none})):
metadata = video_data['ongoing_event']
metadata.pop('duration', None) # Duration is not accurate for livestreams
info_dict['live_status'] = 'is_live'
elif traverse_obj(video_data, ('ongoing_ondemand', 'manifest_url', {url_or_none})):
metadata = video_data['ongoing_ondemand']
# XXX: Has all externally-hosted Kaltura content been moved to native hosting?
elif kaltura_id := traverse_obj(video_data, ('ongoing_ondemand', 'kaltura', 'id', {str})):
metadata = video_data['ongoing_ondemand']
info_dict.update({
'_type': 'url_transparent',
'url': smuggle_url(f'kaltura:1955031:{kaltura_id}', {'source_url': url}),
'ie_key': KalturaIE.ie_key(),
}
})
elif traverse_obj(video_data, ('gone', {dict})):
self.raise_no_formats('The content is no longer available', expected=True, video_id=video_id)
metadata = video_data['gone']
else:
formats, subs = self._extract_m3u8_formats_and_subtitles(
video_data['data']['ongoing_ondemand']['manifest_url'], video_id, 'mp4', m3u8_id='hls')
raise ExtractorError('Unable to extract content')

if not info_dict.get('url') and metadata.get('manifest_url'):
info_dict['formats'], subs = self._extract_m3u8_formats_and_subtitles(
metadata['manifest_url'], video_id, 'mp4', m3u8_id='hls')
self._merge_subtitles(subs, target=subtitles)
info_dict = {'formats': formats}

return {
**info_dict,
**traverse_obj(json_ld, {
'title': 'title',
'thumbnails': ('thumbnails', ..., {'url': 'url'}),
}),
'id': video_id,
'title': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'title', 'fin'), expected_type=str)
or episode or info.get('title')),
'title': episode,
'description': description,
'series': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'series', 'title', 'fin'), expected_type=str)
or series),
'series': series,
'season_number': (int_or_none(self._search_regex(r'Kausi (\d+)', description, 'season number', default=None))
or int_or_none(season_number)),
'episode_number': (traverse_obj(video_data, ('data', 'ongoing_ondemand', 'episode_number'), expected_type=int_or_none)
or int_or_none(episode_number)),
'thumbnails': traverse_obj(info, ('thumbnails', ..., {'url': 'url'})),
'age_limit': traverse_obj(video_data, ('data', 'ongoing_ondemand', 'content_rating', 'age_restriction'), expected_type=int_or_none),
'episode_number': int_or_none(episode_number),
'subtitles': subtitles or None,
'release_date': unified_strdate(traverse_obj(video_data, ('data', 'ongoing_ondemand', 'start_time'), expected_type=str)),
**traverse_obj(metadata, {
'title': ('title', 'fin', {str}),
'description': ('description', 'fin', {str}),
'series': ('series', 'title', 'fin', {str}),
'episode_number': ('episode_number', {int_or_none}),
'age_limit': ('content_rating', 'age_restriction', {int_or_none}),
'release_timestamp': ('start_time', {parse_iso8601}),
'duration': ('duration', 'duration_in_seconds', {int_or_none}),
}),
**info_dict,
}
2 changes: 1 addition & 1 deletion lib/yt_dlp_version
View file
Original file line number Diff line number Diff line change
@@ -1 +1 @@
428ffb75aa3534b275cf54de42693a4d261519da
a6783a3b9905e547f6c1d4df9d7c7999feda8afa

0 comments on commit 565eff4

Please sign in to comment.