From 4a9bc8c3630378bc29f0266126b503f6190c0430 Mon Sep 17 00:00:00 2001 From: 1-Byte <1-Byte@users.noreply.github.com> Date: Tue, 17 Sep 2024 21:17:05 +0200 Subject: [PATCH] [ie/NZZ] Fix extractor (#10461) Closes #5653 Authored by: 1-Byte --- yt_dlp/extractor/nzz.py | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) diff --git a/yt_dlp/extractor/nzz.py b/yt_dlp/extractor/nzz.py index ac3b73156e..047c4e1ac9 100644 --- a/yt_dlp/extractor/nzz.py +++ b/yt_dlp/extractor/nzz.py @@ -1,9 +1,6 @@ import re from .common import InfoExtractor -from ..utils import ( - extract_attributes, -) class NZZIE(InfoExtractor): @@ -22,19 +19,14 @@ class NZZIE(InfoExtractor): 'playlist_count': 1, }] + def _entries(self, webpage, page_id): + for script in re.findall(r'(?s)]* data-hid="jw-video-jw[^>]+>(.+?)', webpage): + settings = self._search_json(r'var\s+settings\s*=[^{]*', script, 'settings', page_id, fatal=False) + if entry := self._parse_jwplayer_data(settings, page_id): + yield entry + def _real_extract(self, url): page_id = self._match_id(url) webpage = self._download_webpage(url, page_id) - entries = [] - for player_element in re.findall( - r'(<[^>]+class="kalturaPlayer[^"]*"[^>]*>)', webpage): - player_params = extract_attributes(player_element) - if player_params.get('data-type') not in ('kaltura_singleArticle',): - self.report_warning('Unsupported player type') - continue - entry_id = player_params['data-id'] - entries.append(self.url_result( - 'kaltura:1750922:' + entry_id, 'Kaltura', entry_id)) - - return self.playlist_result(entries, page_id) + return self.playlist_result(self._entries(webpage, page_id), page_id)