[ie/SaucePlusChannel] Add extractor (#15830)

Closes #14985
Authored by: regulad

README.md

@@ -2261,7 +2261,7 @@ with yt_dlp.YoutubeDL(ydl_opts) as ydl:
 * **Merged with animelover1984/youtube-dl**: You get most of the features and improvements from [animelover1984/youtube-dl](https://github.com/animelover1984/youtube-dl) including `--write-comments`, `BiliBiliSearch`, `BilibiliChannel`, Embedding thumbnail in mp4/ogg/opus, playlist infojson etc. See [#31](https://github.com/yt-dlp/yt-dlp/pull/31) for details.
 
 * **YouTube improvements**:
-    * Supports Clips, Stories (`ytstories:<channel UCID>`), Search (including filters)**\***, YouTube Music Search, Channel-specific search, Search prefixes (`ytsearch:`, `ytsearchdate:`)**\***, Mixes, and Feeds (`:ytfav`, `:ytwatchlater`, `:ytsubs`, `:ythistory`, `:ytrec`, `:ytnotif`)
+    * Supports Clips, Stories (`ytstories:<channel UCID>`), Search (including filters)**\***, YouTube Music Search, Channel-specific search, Search prefix (`ytsearch:`)**\***, Mixes, and Feeds (`:ytfav`, `:ytwatchlater`, `:ytsubs`, `:ythistory`, `:ytrec`, `:ytnotif`)
     * Fix for [n-sig based throttling](https://github.com/ytdl-org/youtube-dl/issues/29326) **\***
     * Download livestreams from the start using `--live-from-start` (*experimental*)
     * Channel URLs download all uploads of the channel, including shorts and live

yt_dlp/extractor/_extractors.py

@@ -1792,7 +1792,10 @@ from .safari import (
 from .saitosan import SaitosanIE
 from .samplefocus import SampleFocusIE
 from .sapo import SapoIE
-from .sauceplus import SaucePlusIE
+from .sauceplus import (
+    SaucePlusChannelIE,
+    SaucePlusIE,
+)
 from .sbs import SBSIE
 from .sbscokr import (
     SBSCoKrAllvodProgramIE,
@@ -2553,7 +2556,6 @@ from .youtube import (
     YoutubeNotificationsIE,
     YoutubePlaylistIE,
     YoutubeRecommendedIE,
-    YoutubeSearchDateIE,
     YoutubeSearchIE,
     YoutubeSearchURLIE,
     YoutubeShortsAudioPivotIE,

yt_dlp/extractor/facebook.py

@@ -1041,8 +1041,6 @@ class FacebookAdsIE(InfoExtractor):
             'uploader': 'Casper',
             'uploader_id': '224110981099062',
             'uploader_url': 'https://www.facebook.com/Casper/',
-            'timestamp': 1766299837,
-            'upload_date': '20251221',
             'like_count': int,
         },
         'playlist_count': 2,
@@ -1054,12 +1052,23 @@ class FacebookAdsIE(InfoExtractor):
             'uploader': 'Case \u00e0 Chocs',
             'uploader_id': '112960472096793',
             'uploader_url': 'https://www.facebook.com/Caseachocs/',
-            'timestamp': 1768498293,
-            'upload_date': '20260115',
             'like_count': int,
             'description': 'md5:f02a255fcf7dce6ed40e9494cf4bc49a',
         },
         'playlist_count': 3,
+    }, {
+        'url': 'https://www.facebook.com/ads/library/?id=1704834754236452',
+        'info_dict': {
+            'id': '1704834754236452',
+            'ext': 'mp4',
+            'title': 'Get answers now!',
+            'description': 'Ask the best psychics and get accurate answers on questions that bother you!',
+            'uploader': 'Your Relationship Advisor',
+            'uploader_id': '108939234726306',
+            'uploader_url': 'https://www.facebook.com/100068970634636/',
+            'like_count': int,
+            'thumbnail': r're:https://.+/.+\.jpg',
+        },
     }, {
         'url': 'https://es-la.facebook.com/ads/library/?id=901230958115569',
         'only_matching': True,
@@ -1123,8 +1132,11 @@ class FacebookAdsIE(InfoExtractor):
         post_data = traverse_obj(
             re.findall(r'data-sjs>({.*?ScheduledServerJS.*?})</script>', webpage), (..., {json.loads}))
         data = get_first(post_data, (
-            'require', ..., ..., ..., '__bbox', 'require', ..., ..., ...,
+            'require', ..., ..., ..., '__bbox', 'require', ..., ..., ..., (
-            'entryPointRoot', 'otherProps', 'deeplinkAdCard', 'snapshot', {dict}))
+                ('__bbox', 'result', 'data', 'ad_library_main', 'deeplink_ad_archive_result', 'deeplink_ad_archive'),
+                # old path
+                ('entryPointRoot', 'otherProps', 'deeplinkAdCard'),
+            ), 'snapshot', {dict}))
         if not data:
             raise ExtractorError('Unable to extract ad data')
 
@@ -1140,11 +1152,12 @@ class FacebookAdsIE(InfoExtractor):
             'title': title,
             'description': markup or None,
         }, traverse_obj(data, {
-            'description': ('link_description', {lambda x: x if not x.startswith('{{product.') else None}),
+            'description': (
+                (('body', 'text'), 'link_description'),
+                {lambda x: x if not x.startswith('{{product.') else None}, any),
             'uploader': ('page_name', {str}),
             'uploader_id': ('page_id', {str_or_none}),
             'uploader_url': ('page_profile_uri', {url_or_none}),
-            'timestamp': ('creation_time', {int_or_none}),
             'like_count': ('page_like_count', {int_or_none}),
         }))
 
@@ -1155,7 +1168,8 @@ class FacebookAdsIE(InfoExtractor):
             entries.append({
                 'id': f'{video_id}_{idx}',
                 'title': entry.get('title') or title,
-                'description': traverse_obj(entry, 'body', 'link_description') or info_dict.get('description'),
+                'description': traverse_obj(
+                    entry, 'body', 'link_description', expected_type=str) or info_dict.get('description'),
                 'thumbnail': url_or_none(entry.get('video_preview_image_url')),
                 'formats': self._extract_formats(entry),
             })

yt_dlp/extractor/floatplane.py

@@ -318,9 +318,48 @@ class FloatplaneIE(FloatplaneBaseIE):
             self.raise_login_required()
 
 
-class FloatplaneChannelIE(InfoExtractor):
+class FloatplaneChannelBaseIE(InfoExtractor):
+    """Subclasses must set _RESULT_IE, _BASE_URL and _PAGE_SIZE"""
+
+    def _fetch_page(self, display_id, creator_id, channel_id, page):
+        query = {
+            'id': creator_id,
+            'limit': self._PAGE_SIZE,
+            'fetchAfter': page * self._PAGE_SIZE,
+        }
+        if channel_id:
+            query['channel'] = channel_id
+        page_data = self._download_json(
+            f'{self._BASE_URL}/api/v3/content/creator', display_id,
+            query=query, note=f'Downloading page {page + 1}')
+        for post in page_data or []:
+            yield self.url_result(
+                f'{self._BASE_URL}/post/{post["id"]}',
+                self._RESULT_IE, id=post['id'], title=post.get('title'),
+                release_timestamp=parse_iso8601(post.get('releaseDate')))
+
+    def _real_extract(self, url):
+        creator, channel = self._match_valid_url(url).group('id', 'channel')
+        display_id = join_nonempty(creator, channel, delim='/')
+
+        creator_data = self._download_json(
+            f'{self._BASE_URL}/api/v3/creator/named',
+            display_id, query={'creatorURL[0]': creator})[0]
+
+        channel_data = traverse_obj(
+            creator_data, ('channels', lambda _, v: v['urlname'] == channel), get_all=False) or {}
+
+        return self.playlist_result(OnDemandPagedList(functools.partial(
+            self._fetch_page, display_id, creator_data['id'], channel_data.get('id')), self._PAGE_SIZE),
+            display_id, title=channel_data.get('title') or creator_data.get('title'),
+            description=channel_data.get('about') or creator_data.get('about'))
+
+
+class FloatplaneChannelIE(FloatplaneChannelBaseIE):
     _VALID_URL = r'https?://(?:(?:www|beta)\.)?floatplane\.com/channel/(?P<id>[\w-]+)/home(?:/(?P<channel>[\w-]+))?'
+    _BASE_URL = 'https://www.floatplane.com'
     _PAGE_SIZE = 20
+    _RESULT_IE = FloatplaneIE
     _TESTS = [{
         'url': 'https://www.floatplane.com/channel/linustechtips/home/ltxexpo',
         'info_dict': {
@@ -346,36 +385,3 @@ class FloatplaneChannelIE(InfoExtractor):
         },
         'playlist_mincount': 200,
     }]
-
-    def _fetch_page(self, display_id, creator_id, channel_id, page):
-        query = {
-            'id': creator_id,
-            'limit': self._PAGE_SIZE,
-            'fetchAfter': page * self._PAGE_SIZE,
-        }
-        if channel_id:
-            query['channel'] = channel_id
-        page_data = self._download_json(
-            'https://www.floatplane.com/api/v3/content/creator', display_id,
-            query=query, note=f'Downloading page {page + 1}')
-        for post in page_data or []:
-            yield self.url_result(
-                f'https://www.floatplane.com/post/{post["id"]}',
-                FloatplaneIE, id=post['id'], title=post.get('title'),
-                release_timestamp=parse_iso8601(post.get('releaseDate')))
-
-    def _real_extract(self, url):
-        creator, channel = self._match_valid_url(url).group('id', 'channel')
-        display_id = join_nonempty(creator, channel, delim='/')
-
-        creator_data = self._download_json(
-            'https://www.floatplane.com/api/v3/creator/named',
-            display_id, query={'creatorURL[0]': creator})[0]
-
-        channel_data = traverse_obj(
-            creator_data, ('channels', lambda _, v: v['urlname'] == channel), get_all=False) or {}
-
-        return self.playlist_result(OnDemandPagedList(functools.partial(
-            self._fetch_page, display_id, creator_data['id'], channel_data.get('id')), self._PAGE_SIZE),
-            display_id, title=channel_data.get('title') or creator_data.get('title'),
-            description=channel_data.get('about') or creator_data.get('about'))

yt_dlp/extractor/sauceplus.py

@@ -1,4 +1,4 @@
-from .floatplane import FloatplaneBaseIE
+from .floatplane import FloatplaneBaseIE, FloatplaneChannelBaseIE
 
 
 class SaucePlusIE(FloatplaneBaseIE):
@@ -39,3 +39,19 @@ class SaucePlusIE(FloatplaneBaseIE):
     def _real_initialize(self):
         if not self._get_cookies(self._BASE_URL).get('__Host-sp-sess'):
             self.raise_login_required()
+
+
+class SaucePlusChannelIE(FloatplaneChannelBaseIE):
+    _VALID_URL = r'https?://(?:(?:www|beta)\.)?sauceplus\.com/channel/(?P<id>[\w-]+)/home(?:/(?P<channel>[\w-]+))?'
+    _BASE_URL = 'https://www.sauceplus.com'
+    _RESULT_IE = SaucePlusIE
+    _PAGE_SIZE = 20
+    _TESTS = [{
+        'url': 'https://www.sauceplus.com/channel/williamosman/home',
+        'info_dict': {
+            'id': 'williamosman',
+            'title': 'William Osman',
+            'description': 'md5:a67bc961d23c293b2c5308d84f34f26c',
+        },
+        'playlist_mincount': 158,
+    }]

yt_dlp/extractor/tele5.py

@@ -9,39 +9,39 @@ class Tele5IE(DiscoveryPlusBaseIE):
     _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?P<parent_slug>[\w-]+)/(?P<slug_a>[\w-]+)(?:/(?P<slug_b>[\w-]+))?'
     _TESTS = [{
         # slug_a and slug_b
-        'url': 'https://tele5.de/mediathek/stargate-atlantis/quarantane',
+        'url': 'https://tele5.de/mediathek/star-trek-enterprise/vox-sola',
         'info_dict': {
-            'id': '6852024',
+            'id': '4140114',
             'ext': 'mp4',
-            'title': 'Quarantäne',
+            'title': 'Vox Sola',
-            'description': 'md5:6af0373bd0fcc4f13e5d47701903d675',
+            'description': 'md5:329d115f74324d4364efc1a11c4ea7c9',
-            'episode': 'Episode 73',
+            'duration': 2542.76,
-            'episode_number': 73,
+            'thumbnail': r're:https://[^/.]+\.disco-api\.com/.+\.jpe?g',
-            'season': 'Season 4',
-            'season_number': 4,
-            'series': 'Stargate Atlantis',
-            'upload_date': '20240525',
-            'timestamp': 1716643200,
-            'duration': 2503.2,
-            'thumbnail': 'https://eu1-prod-images.disco-api.com/2024/05/21/c81fcb45-8902-309b-badb-4e6d546b575d.jpeg',
-            'creators': ['Tele5'],
             'tags': [],
+            'creators': ['Tele5'],
+            'series': 'Star Trek - Enterprise',
+            'season': 'Season 1',
+            'season_number': 1,
+            'episode': 'Episode 22',
+            'episode_number': 22,
+            'timestamp': 1770491100,
+            'upload_date': '20260207',
         },
     }, {
         # only slug_a
-        'url': 'https://tele5.de/mediathek/inside-out',
+        'url': 'https://tele5.de/mediathek/30-miles-from-nowhere-im-wald-hoert-dich-niemand-schreien',
         'info_dict': {
-            'id': '6819502',
+            'id': '4102641',
             'ext': 'mp4',
-            'title': 'Inside out',
+            'title': '30 Miles from Nowhere - Im Wald hört dich niemand schreien',
-            'description': 'md5:7e5f32ed0be5ddbd27713a34b9293bfd',
+            'description': 'md5:0b731539f39ee186ebcd9dd444a86fc2',
-            'series': 'Inside out',
+            'duration': 4849.96,
-            'upload_date': '20240523',
+            'thumbnail': r're:https://[^/.]+\.disco-api\.com/.+\.jpe?g',
-            'timestamp': 1716494400,
-            'duration': 5343.4,
-            'thumbnail': 'https://eu1-prod-images.disco-api.com/2024/05/15/181eba3c-f9f0-3faf-b14d-0097050a3aa4.jpeg',
-            'creators': ['Tele5'],
             'tags': [],
+            'creators': ['Tele5'],
+            'series': '30 Miles from Nowhere - Im Wald hört dich niemand schreien',
+            'timestamp': 1770417300,
+            'upload_date': '20260206',
         },
     }, {
         # playlist
@@ -50,20 +50,27 @@ class Tele5IE(DiscoveryPlusBaseIE):
             'id': 'mediathek-schlefaz',
         },
         'playlist_mincount': 3,
+        'skip': 'Dead link',
     }]
 
     def _real_extract(self, url):
         parent_slug, slug_a, slug_b = self._match_valid_url(url).group('parent_slug', 'slug_a', 'slug_b')
         playlist_id = join_nonempty(parent_slug, slug_a, slug_b, delim='-')
 
-        query = {'environment': 'tele5', 'v': '2'}
+        query = {
+            'include': 'default',
+            'filter[environment]': 'tele5',
+            'v': '2',
+        }
+
         if not slug_b:
             endpoint = f'page/{slug_a}'
             query['parent_slug'] = parent_slug
         else:
-            endpoint = f'videos/{slug_b}'
+            endpoint = f'shows/{slug_a}'
-            query['filter[show.slug]'] = slug_a
+            query['filter[video.slug]'] = slug_b
-        cms_data = self._download_json(f'https://de-api.loma-cms.com/feloma/{endpoint}/', playlist_id, query=query)
+
+        cms_data = self._download_json(f'https://public.aurora.enhanced.live/site/{endpoint}/', playlist_id, query=query)
 
         return self.playlist_result(map(
             functools.partial(self._get_disco_api_info, url, disco_host='eu1-prod.disco-api.com', realm='dmaxde', country='DE'),

yt_dlp/extractor/youtube/__init__.py

@@ -16,7 +16,7 @@ from ._redirect import (
     YoutubeYtBeIE,
     YoutubeYtUserIE,
 )
-from ._search import YoutubeMusicSearchURLIE, YoutubeSearchDateIE, YoutubeSearchIE, YoutubeSearchURLIE
+from ._search import YoutubeMusicSearchURLIE, YoutubeSearchIE, YoutubeSearchURLIE
 from ._tab import YoutubePlaylistIE, YoutubeTabBaseInfoExtractor, YoutubeTabIE
 from ._video import YoutubeIE
 
@@ -39,7 +39,6 @@ for _cls in [
     YoutubeYtBeIE,
     YoutubeYtUserIE,
     YoutubeMusicSearchURLIE,
-    YoutubeSearchDateIE,
     YoutubeSearchIE,
     YoutubeSearchURLIE,
     YoutubePlaylistIE,

yt_dlp/extractor/youtube/_search.py

@@ -28,21 +28,6 @@ class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
     }]
 
 
-class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
-    IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
-    _SEARCH_KEY = 'ytsearchdate'
-    IE_DESC = 'YouTube search, newest videos first'
-    _SEARCH_PARAMS = 'CAISAhAB8AEB'  # Videos only, sorted by date
-    _TESTS = [{
-        'url': 'ytsearchdate5:youtube-dl test video',
-        'playlist_count': 5,
-        'info_dict': {
-            'id': 'youtube-dl test video',
-            'title': 'youtube-dl test video',
-        },
-    }]
-
-
 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
     IE_DESC = 'YouTube search URLs with sorting and filter support'
     IE_NAME = YoutubeSearchIE.IE_NAME + '_url'