Myzel394/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-06-18 15:55:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

[ie/nobelprize] Fix extractor (#13205)

Browse Source 
Authored by: doe1080
This commit is contained in:
doe1080 2025-06-08 09:04:32 +09:00 committed by GitHub
parent a8bf0011bd
commit 97ddfefeb4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 39 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

80
yt_dlp/extractor/nobelprize.py
View File

@ -1,59 +1,57 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
determine_ext, UnsupportedError,
get_element_by_attribute, clean_html,
int_or_none, int_or_none,
js_to_json, parse_duration,
mimetype2ext, parse_qs,
update_url_query, str_or_none,
update_url,
) )
from ..utils.traversal import find_element, traverse_obj
class NobelPrizeIE(InfoExtractor): class NobelPrizeIE(InfoExtractor):
_WORKING = False _VALID_URL = r'https?://(?:(?:mediaplayer|www)\.)?nobelprize\.org/mediaplayer/'
_VALID_URL = r'https?://(?:www\.)?nobelprize\.org/mediaplayer.*?\bid=(?P<id>\d+)' _TESTS = [{
_TEST = { 'url': 'https://www.nobelprize.org/mediaplayer/?id=2636',
'url': 'http://www.nobelprize.org/mediaplayer/?id=2636',
'md5': '04c81e5714bb36cc4e2232fee1d8157f',
'info_dict': { 'info_dict': {
'id': '2636', 'id': '2636',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Announcement of the 2016 Nobel Prize in Physics', 'title': 'Announcement of the 2016 Nobel Prize in Physics',
'description': 'md5:05beba57f4f5a4bbd4cf2ef28fcff739', 'description': 'md5:1a2d8a6ca80c88fb3b9a326e0b0e8e43',
'duration': 1560.0,
'thumbnail': r're:https?://www\.nobelprize\.org/images/.+\.jpg',
'timestamp': 1504883793,
'upload_date': '20170908',
}, },
} }, {
'url': 'https://mediaplayer.nobelprize.org/mediaplayer/?qid=12693',
'info_dict': {
'id': '12693',
'ext': 'mp4',
'title': 'Nobel Lecture by Peter Higgs',
'description': 'md5:9b12e275dbe3a8138484e70e00673a05',
'duration': 1800.0,
'thumbnail': r're:https?://www\.nobelprize\.org/images/.+\.jpg',
'timestamp': 1504883793,
'upload_date': '20170908',
},
}]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = traverse_obj(parse_qs(url), (
webpage = self._download_webpage(url, video_id) ('id', 'qid'), -1, {int_or_none}, {str_or_none}, any))
media = self._parse_json(self._search_regex( if not video_id:
r'(?s)var\s*config\s*=\s*({.+?});', webpage, raise UnsupportedError(url)
'config'), video_id, js_to_json)['media'] webpage = self._download_webpage(
title = media['title'] update_url(url, netloc='mediaplayer.nobelprize.org'), video_id)
formats = []
for source in media.get('source', []):
source_src = source.get('src')
if not source_src:
continue
ext = mimetype2ext(source.get('type')) or determine_ext(source_src)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_src, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
update_url_query(source_src, {'hdcore': '3.7.0'}),
video_id, f4m_id='hds', fatal=False))
else:
formats.append({
'url': source_src,
})
return { return {
**self._search_json_ld(webpage, video_id),
'id': video_id, 'id': video_id,
'title': title, 'title': self._html_search_meta('caption', webpage),
'description': get_element_by_attribute('itemprop', 'description', webpage), 'description': traverse_obj(webpage, (
'duration': int_or_none(media.get('duration')), {find_element(tag='span', attr='itemprop', value='description')}, {clean_html})),
'formats': formats, 'duration': parse_duration(self._html_search_meta('duration', webpage)),
} }