From 69dbfe01c47cd078682a87f179f5846e2679e927 Mon Sep 17 00:00:00 2001 From: bashonly Date: Mon, 4 Sep 2023 11:18:59 -0500 Subject: [PATCH] Bugfix for bae4834245a708fff97219849ec880c319c88bc6 Authored by: bashonly --- yt_dlp/extractor/noodlemagazine.py | 35 ++++++++++++++++++------------ 1 file changed, 21 insertions(+), 14 deletions(-) diff --git a/yt_dlp/extractor/noodlemagazine.py b/yt_dlp/extractor/noodlemagazine.py index 1cea0dbda..1c1a763dc 100644 --- a/yt_dlp/extractor/noodlemagazine.py +++ b/yt_dlp/extractor/noodlemagazine.py @@ -1,7 +1,5 @@ from .common import InfoExtractor from ..utils import ( - extract_attributes, - get_element_html_by_id, int_or_none, parse_count, parse_duration, @@ -42,27 +40,36 @@ class NoodleMagazineIE(InfoExtractor): like_count = parse_count(self._html_search_meta('ya:ovs:likes', webpage, default=None)) upload_date = unified_strdate(self._html_search_meta('ya:ovs:upload_date', webpage, default='')) - player_path = extract_attributes(get_element_html_by_id('iplayer', webpage) or '')['src'] + def build_url(url_or_path): + return urljoin('https://adult.noodlemagazine.com', url_or_path) + + headers = {'Referer': url} + player_path = self._html_search_regex( + r']+\bid="iplayer"[^>]+\bsrc="([^"]+)"', webpage, 'player path') player_iframe = self._download_webpage( - urljoin('https://adult.noodlemagazine.com', player_path), video_id, 'Downloading iframe page') + build_url(player_path), video_id, 'Downloading iframe page', headers=headers) playlist_url = self._search_regex( r'window\.playlistUrl\s*=\s*["\']([^"\']+)["\']', player_iframe, 'playlist url') - playlist_info = self._download_json( - urljoin('https://adult.noodlemagazine.com', playlist_url), video_id, headers={'Referer': url}) + playlist_info = self._download_json(build_url(playlist_url), video_id, headers=headers) - thumbnail = self._og_search_property('image', webpage, default=None) or playlist_info.get('image') - formats = traverse_obj(playlist_info, ('sources', lambda _, v: v['file'], { - 'url': 'file', - 'format_id': 'label', - 'height': ('label', {int_or_none}), - 'ext': 'type', - })) + formats = [] + for source in traverse_obj(playlist_info, ('sources', lambda _, v: v['file'])): + if source.get('type') == 'hls': + formats.extend(self._extract_m3u8_formats( + build_url(source['file']), video_id, 'mp4', fatal=False, m3u8_id='hls')) + else: + formats.append(traverse_obj(source, { + 'url': ('file', {build_url}), + 'format_id': 'label', + 'height': ('label', {int_or_none}), + 'ext': 'type', + })) return { 'id': video_id, 'formats': formats, 'title': title, - 'thumbnail': thumbnail, + 'thumbnail': self._og_search_property('image', webpage, default=None) or playlist_info.get('image'), 'duration': duration, 'description': description, 'tags': tags,