From c9ce57d9bf51541da2381d99bc096a9d0ddf1f27 Mon Sep 17 00:00:00 2001 From: bashonly <88596187+bashonly@users.noreply.github.com> Date: Thu, 18 Apr 2024 18:18:56 -0500 Subject: [PATCH] [ie/patreon] Fix Vimeo embed extraction (#9712) Fixes regression in 36b240f9a72af57eb2c9d927ebb7fd1c917ebf18 Closes #9709 Authored by: bashonly --- yt_dlp/extractor/patreon.py | 45 ++++++++++++++++++++++++++++--------- 1 file changed, 34 insertions(+), 11 deletions(-) diff --git a/yt_dlp/extractor/patreon.py b/yt_dlp/extractor/patreon.py index d4f822f52..9381c7eab 100644 --- a/yt_dlp/extractor/patreon.py +++ b/yt_dlp/extractor/patreon.py @@ -1,8 +1,8 @@ import itertools +import urllib.parse from .common import InfoExtractor from .vimeo import VimeoIE -from ..compat import compat_urllib_parse_unquote from ..networking.exceptions import HTTPError from ..utils import ( KNOWN_EXTENSIONS, @@ -14,7 +14,6 @@ parse_iso8601, str_or_none, traverse_obj, - try_get, url_or_none, urljoin, ) @@ -199,6 +198,27 @@ class PatreonIE(PatreonBaseIE): 'channel_id': '2147162', 'uploader_url': 'https://www.patreon.com/yaboyroshi', }, + }, { + # NSFW vimeo embed URL + 'url': 'https://www.patreon.com/posts/4k-spiderman-4k-96414599', + 'info_dict': { + 'id': '902250943', + 'ext': 'mp4', + 'title': '❤️(4K) Spiderman Girl Yeonhwa’s Gift ❤️(4K) 스파이더맨걸 연화의 선물', + 'description': '❤️(4K) Spiderman Girl Yeonhwa’s Gift \n❤️(4K) 스파이더맨걸 연화의 선물', + 'uploader': 'Npickyeonhwa', + 'uploader_id': '90574422', + 'uploader_url': 'https://www.patreon.com/Yeonhwa726', + 'channel_id': '10237902', + 'channel_url': 'https://www.patreon.com/Yeonhwa726', + 'duration': 70, + 'timestamp': 1705150153, + 'upload_date': '20240113', + 'comment_count': int, + 'like_count': int, + 'thumbnail': r're:^https?://.+', + }, + 'params': {'skip_download': 'm3u8'}, }] def _real_extract(self, url): @@ -268,16 +288,19 @@ def _real_extract(self, url): }) # handle Vimeo embeds - if try_get(attributes, lambda x: x['embed']['provider']) == 'Vimeo': - embed_html = try_get(attributes, lambda x: x['embed']['html']) - v_url = url_or_none(compat_urllib_parse_unquote( - self._search_regex(r'(https(?:%3A%2F%2F|://)player\.vimeo\.com.+app_id(?:=|%3D)+\d+)', embed_html, 'vimeo url', fatal=False))) - if v_url: - v_url = VimeoIE._smuggle_referrer(v_url, 'https://patreon.com') - if self._request_webpage(v_url, video_id, 'Checking Vimeo embed URL', fatal=False, errnote=False): - return self.url_result(v_url, VimeoIE, url_transparent=True, **info) + if traverse_obj(attributes, ('embed', 'provider')) == 'Vimeo': + v_url = urllib.parse.unquote(self._html_search_regex( + r'(https(?:%3A%2F%2F|://)player\.vimeo\.com.+app_id(?:=|%3D)+\d+)', + traverse_obj(attributes, ('embed', 'html', {str})), 'vimeo url', fatal=False) or '') + if url_or_none(v_url) and self._request_webpage( + v_url, video_id, 'Checking Vimeo embed URL', + headers={'Referer': 'https://patreon.com/'}, + fatal=False, errnote=False): + return self.url_result( + VimeoIE._smuggle_referrer(v_url, 'https://patreon.com/'), + VimeoIE, url_transparent=True, **info) - embed_url = try_get(attributes, lambda x: x['embed']['url']) + embed_url = traverse_obj(attributes, ('embed', 'url', {url_or_none})) if embed_url and self._request_webpage(embed_url, video_id, 'Checking embed URL', fatal=False, errnote=False): return self.url_result(embed_url, **info)