github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[orf:radio] Clean description and improve extraction

Browse source
This commit is contained in:
Sergey M․ 2020-01-11 02:18:36 +07:00
parent 9ba179c1fa
commit aca2fd222f
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 28 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

46
youtube_dl/extractor/orf.py
View file

@ -6,12 +6,14 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str from ..compat import compat_str
from ..utils import ( from ..utils import (
clean_html,
determine_ext, determine_ext,
float_or_none, float_or_none,
HEADRequest, HEADRequest,
int_or_none, int_or_none,
orderedSet, orderedSet,
remove_end, remove_end,
str_or_none,
strip_jsonp, strip_jsonp,
unescapeHTML, unescapeHTML,
unified_strdate, unified_strdate,
@ -162,30 +164,37 @@ def _real_extract(self, url):
show_id = mobj.group('show') show_id = mobj.group('show')
data = self._download_json( data = self._download_json(
'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s' % (station, show_id, show_date), 'http://audioapi.orf.at/%s/api/json/current/broadcast/%s/%s'
show_id % (station, show_id, show_date), show_id)
)
def extract_entry_dict(info, title, subtitle): entries = []
return { for info in data['streams']:
'id': info['loopStreamId'].replace('.mp3', ''), loop_stream_id = str_or_none(info.get('loopStreamId'))
'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, info['loopStreamId']), if not loop_stream_id:
continue
title = str_or_none(data.get('title'))
if not title:
continue
start = int_or_none(info.get('start'), scale=1000)
end = int_or_none(info.get('end'), scale=1000)
duration = end - start if end and start else None
entries.append({
'id': loop_stream_id.replace('.mp3', ''),
'url': 'http://loopstream01.apa.at/?channel=%s&id=%s' % (station, loop_stream_id),
'title': title, 'title': title,
'description': subtitle, 'description': clean_html(data.get('subtitle')),
'duration': (info['end'] - info['start']) / 1000, 'duration': duration,
'timestamp': info['start'] / 1000, 'timestamp': start,
'ext': 'mp3', 'ext': 'mp3',
'series': data.get('programTitle') 'series': data.get('programTitle'),
} })
entries = [extract_entry_dict(t, data['title'], data['subtitle']) for t in data['streams']]
return { return {
'_type': 'playlist', '_type': 'playlist',
'id': show_id, 'id': show_id,
'title': data['title'], 'title': data.get('title'),
'description': data['subtitle'], 'description': clean_html(data.get('subtitle')),
'entries': entries 'entries': entries,
} }
@ -206,7 +215,8 @@ class ORFFM4IE(ORFRadioIE):
'timestamp': 1483819257, 'timestamp': 1483819257,
'upload_date': '20170107', 'upload_date': '20170107',
}, },
'skip': 'Shows from ORF radios are only available for 7 days.' 'skip': 'Shows from ORF radios are only available for 7 days.',
'only_matching': True,
} }