etc
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp.git
0
0
Fork 0
Code Issues Projects Releases Wiki Activity

[extractor/drtv] Fix radio page extraction (#6552) 

Authored by: viktor-enzell
This commit is contained in:
viktor-enzell 2023-03-18 14:06:46 +01:00 committed by GitHub
parent 216bcb66d7
commit 9a06b7b189
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 39 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

58
yt_dlp/extractor/drtv.py
View File

@ -12,7 +12,6 @@
mimetype2ext, mimetype2ext,
str_or_none, str_or_none,
traverse_obj, traverse_obj,
try_get,
unified_timestamp, unified_timestamp,
update_url_query, update_url_query,
url_or_none, url_or_none,
@ -25,7 +24,7 @@ class DRTVIE(InfoExtractor):
_VALID_URL = r'''(?x) _VALID_URL = r'''(?x)
https?:// https?://
(?: (?:
(?:www\.)?dr\.dk/(?:tv/se|nyheder|(?:radio|lyd)(?:/ondemand)?)/(?:[^/]+/)*| (?:www\.)?dr\.dk/(?:tv/se|nyheder|(?P<radio>radio|lyd)(?:/ondemand)?)/(?:[^/]+/)*|
(?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/(?:se|episode|program)/ (?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/(?:se|episode|program)/
) )
(?P<id>[\da-z_-]+) (?P<id>[\da-z_-]+)
@ -80,7 +79,7 @@ class DRTVIE(InfoExtractor):
'description': 'md5:8c66dcbc1669bbc6f873879880f37f2a', 'description': 'md5:8c66dcbc1669bbc6f873879880f37f2a',
'timestamp': 1546628400, 'timestamp': 1546628400,
'upload_date': '20190104', 'upload_date': '20190104',
'duration': 3504.618, 'duration': 3504.619,
'formats': 'mincount:20', 'formats': 'mincount:20',
'release_year': 2017, 'release_year': 2017,
'season_id': 'urn:dr:mu:bundle:5afc03ad6187a4065ca5fd35', 'season_id': 'urn:dr:mu:bundle:5afc03ad6187a4065ca5fd35',
@ -101,14 +100,16 @@ class DRTVIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'title': 'Bonderøven 2019 (1:8)', 'title': 'Bonderøven 2019 (1:8)',
'description': 'md5:b6dcfe9b6f0bea6703e9a0092739a5bd', 'description': 'md5:b6dcfe9b6f0bea6703e9a0092739a5bd',
'timestamp': 1603188600, 'timestamp': 1654856100,
'upload_date': '20201020', 'upload_date': '20220610',
'duration': 2576.6, 'duration': 2576.6,
'season': 'Bonderøven 2019', 'season': 'Bonderøven 2019',
'season_id': 'urn:dr:mu:bundle:5c201667a11fa01ca4528ce5', 'season_id': 'urn:dr:mu:bundle:5c201667a11fa01ca4528ce5',
'release_year': 2019, 'release_year': 2019,
'season_number': 2019, 'season_number': 2019,
'series': 'Frank & Kastaniegaarden' 'series': 'Frank & Kastaniegaarden',
'episode_number': 1,
'episode': 'Episode 1',
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
@ -140,10 +141,26 @@ class DRTVIE(InfoExtractor):
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
'skip': 'this video has been removed',
}, {
'url': 'https://www.dr.dk/lyd/p4kbh/regionale-nyheder-kh4/regionale-nyheder-2023-03-14-10-30-9',
'info_dict': {
'ext': 'mp4',
'id': '14802310112',
'timestamp': 1678786200,
'duration': 120.043,
'season_id': 'urn:dr:mu:bundle:63a4f7c87140143504b6710f',
'series': 'P4 København regionale nyheder',
'upload_date': '20230314',
'release_year': 0,
'description': 'Hør seneste regionale nyheder fra P4 København.',
'season': 'Regionale nyheder',
'title': 'Regionale nyheder',
},
}] }]
def _real_extract(self, url): def _real_extract(self, url):
raw_video_id = self._match_id(url) raw_video_id, is_radio_url = self._match_valid_url(url).group('id', 'radio')
webpage = self._download_webpage(url, raw_video_id) webpage = self._download_webpage(url, raw_video_id)
@ -170,15 +187,17 @@ def _real_extract(self, url):
programcard_url = '%s/%s' % (_PROGRAMCARD_BASE, video_id) programcard_url = '%s/%s' % (_PROGRAMCARD_BASE, video_id)
else: else:
programcard_url = _PROGRAMCARD_BASE programcard_url = _PROGRAMCARD_BASE
page = self._parse_json( if is_radio_url:
self._search_regex( video_id = self._search_nextjs_data(
r'data\s*=\s*({.+?})\s*(?:;|</script)', webpage, webpage, raw_video_id)['props']['pageProps']['episode']['productionNumber']
'data'), '1')['cache']['page'] else:
page = page[list(page.keys())[0]] json_data = self._search_json(
item = try_get( r'window\.__data\s*=', webpage, 'data', raw_video_id)
page, (lambda x: x['item'], lambda x: x['entries'][0]['item']), video_id = traverse_obj(json_data, (
dict) 'cache', 'page', ..., (None, ('entries', 0)), 'item', 'customId',
video_id = item['customId'].split(':')[-1] {lambda x: x.split(':')[-1]}), get_all=False)
if not video_id:
raise ExtractorError('Unable to extract video id')
query['productionnumber'] = video_id query['productionnumber'] = video_id
data = self._download_json( data = self._download_json(
@ -269,10 +288,11 @@ def decrypt_uri(e):
f['vcodec'] = 'none' f['vcodec'] = 'none'
formats.extend(f4m_formats) formats.extend(f4m_formats)
elif target == 'HLS': elif target == 'HLS':
formats.extend(self._extract_m3u8_formats( fmts, subs = self._extract_m3u8_formats_and_subtitles(
uri, video_id, 'mp4', entry_protocol='m3u8_native', uri, video_id, 'mp4', entry_protocol='m3u8_native',
quality=preference, m3u8_id=format_id, quality=preference, m3u8_id=format_id, fatal=False)
fatal=False)) formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
else: else:
bitrate = link.get('Bitrate') bitrate = link.get('Bitrate')
if bitrate: if bitrate: