Merge 548d50db25 into f2a4983df7

test/test_traversal.py

@@ -481,7 +481,7 @@ class TestTraversalHelpers:
             'id': 'name',
             'data': 'content',
             'url': 'url',
-        }, all, {subs_list_to_dict(lang=None)}]) == {
+        }, all, {subs_list_to_dict}]) == {
             'de': [{'url': 'https://example.com/subs/de.ass'}],
             'en': [{'data': 'content'}],
         }, 'subs with mandatory items missing should be filtered'
@@ -507,54 +507,6 @@ class TestTraversalHelpers:
             {'url': 'https://example.com/subs/en1', 'ext': 'ext'},
             {'url': 'https://example.com/subs/en2', 'ext': 'ext'},
         ]}, '`quality` key should sort subtitle list accordingly'
-        assert traverse_obj([
-            {'name': 'de', 'url': 'https://example.com/subs/de.ass'},
-            {'name': 'de'},
-            {'name': 'en', 'content': 'content'},
-            {'url': 'https://example.com/subs/en'},
-        ], [..., {
-            'id': 'name',
-            'url': 'url',
-            'data': 'content',
-        }, all, {subs_list_to_dict(lang='en')}]) == {
-            'de': [{'url': 'https://example.com/subs/de.ass'}],
-            'en': [
-                {'data': 'content'},
-                {'url': 'https://example.com/subs/en'},
-            ],
-        }, 'optionally provided lang should be used if no id available'
-        assert traverse_obj([
-            {'name': 1, 'url': 'https://example.com/subs/de1'},
-            {'name': {}, 'url': 'https://example.com/subs/de2'},
-            {'name': 'de', 'ext': 1, 'url': 'https://example.com/subs/de3'},
-            {'name': 'de', 'ext': {}, 'url': 'https://example.com/subs/de4'},
-        ], [..., {
-            'id': 'name',
-            'url': 'url',
-            'ext': 'ext',
-        }, all, {subs_list_to_dict(lang=None)}]) == {
-            'de': [
-                {'url': 'https://example.com/subs/de3'},
-                {'url': 'https://example.com/subs/de4'},
-            ],
-        }, 'non str types should be ignored for id and ext'
-        assert traverse_obj([
-            {'name': 1, 'url': 'https://example.com/subs/de1'},
-            {'name': {}, 'url': 'https://example.com/subs/de2'},
-            {'name': 'de', 'ext': 1, 'url': 'https://example.com/subs/de3'},
-            {'name': 'de', 'ext': {}, 'url': 'https://example.com/subs/de4'},
-        ], [..., {
-            'id': 'name',
-            'url': 'url',
-            'ext': 'ext',
-        }, all, {subs_list_to_dict(lang='de')}]) == {
-            'de': [
-                {'url': 'https://example.com/subs/de1'},
-                {'url': 'https://example.com/subs/de2'},
-                {'url': 'https://example.com/subs/de3'},
-                {'url': 'https://example.com/subs/de4'},
-            ],
-        }, 'non str types should be replaced by default id'
 
     def test_trim_str(self):
         with pytest.raises(TypeError):
@@ -573,7 +525,7 @@ class TestTraversalHelpers:
     def test_unpack(self):
         assert unpack(lambda *x: ''.join(map(str, x)))([1, 2, 3]) == '123'
         assert unpack(join_nonempty)([1, 2, 3]) == '1-2-3'
-        assert unpack(join_nonempty, delim=' ')([1, 2, 3]) == '1 2 3'
+        assert unpack(join_nonempty(delim=' '))([1, 2, 3]) == '1 2 3'
         with pytest.raises(TypeError):
             unpack(join_nonempty)()
         with pytest.raises(TypeError):

test/test_utils.py

@@ -72,6 +72,7 @@ from yt_dlp.utils import (
     intlist_to_bytes,
     iri_to_uri,
     is_html,
+    join_nonempty,
     js_to_json,
     limit_length,
     locked_file,
@@ -2157,6 +2158,10 @@ Line 1
         assert int_or_none(v=10) == 10, 'keyword passed positional should call function'
         assert int_or_none(scale=0.1)(10) == 100, 'call after partial application should call the function'
 
+        assert callable(join_nonempty(delim=', ')), 'varargs positional should apply partially'
+        assert callable(join_nonempty()), 'varargs positional should apply partially'
+        assert join_nonempty(None, delim=', ') == '', 'passed varargs should call the function'
+
 
 if __name__ == '__main__':
     unittest.main()

yt_dlp/YoutubeDL.py

@@ -4381,9 +4381,7 @@ class YoutubeDL:
             return None
 
         for idx, t in list(enumerate(thumbnails))[::-1]:
-            thumb_ext = t.get('ext') or determine_ext(t['url'], 'jpg')
-            if multiple:
-                thumb_ext = f'{t["id"]}.{thumb_ext}'
+            thumb_ext = (f'{t["id"]}.' if multiple else '') + determine_ext(t['url'], 'jpg')
             thumb_display_id = f'{label} thumbnail {t["id"]}'
             thumb_filename = replace_extension(filename, thumb_ext, info_dict.get('ext'))
             thumb_filename_final = replace_extension(thumb_filename_base, thumb_ext, info_dict.get('ext'))

yt_dlp/extractor/afreecatv.py

@@ -66,14 +66,6 @@ class AfreecaTVBaseIE(InfoExtractor):
             extensions={'legacy_ssl': True}), display_id,
             'Downloading API JSON', 'Unable to download API JSON')
 
-    @staticmethod
-    def _fixup_thumb(thumb_url):
-        if not url_or_none(thumb_url):
-            return None
-        # Core would determine_ext as 'php' from the url, so we need to provide the real ext
-        # See: https://github.com/yt-dlp/yt-dlp/issues/11537
-        return [{'url': thumb_url, 'ext': 'jpg'}]
-
 
 class AfreecaTVIE(AfreecaTVBaseIE):
     IE_NAME = 'soop'
@@ -163,7 +155,7 @@ class AfreecaTVIE(AfreecaTVBaseIE):
             'uploader': ('writer_nick', {str}),
             'uploader_id': ('bj_id', {str}),
             'duration': ('total_file_duration', {int_or_none(scale=1000)}),
-            'thumbnails': ('thumb', {self._fixup_thumb}),
+            'thumbnail': ('thumb', {url_or_none}),
         })
 
         entries = []
@@ -234,7 +226,8 @@ class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
 
         return self.playlist_result(self._entries(data), video_id)
 
-    def _entries(self, data):
+    @staticmethod
+    def _entries(data):
         # 'files' is always a list with 1 element
         yield from traverse_obj(data, (
             'data', lambda _, v: v['story_type'] == 'catch',
@@ -245,7 +238,7 @@ class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
                 'title': ('title', {str}),
                 'uploader': ('writer_nick', {str}),
                 'uploader_id': ('writer_id', {str}),
-                'thumbnails': ('thumb', {self._fixup_thumb}),
+                'thumbnail': ('thumb', {url_or_none}),
                 'timestamp': ('write_timestamp', {int_or_none}),
             }))
 

yt_dlp/extractor/chaturbate.py

@@ -1,11 +1,11 @@
 import re
 
 from .common import InfoExtractor
+from ..networking import Request
 from ..utils import (
     ExtractorError,
     lowercase_escape,
     url_or_none,
-    urlencode_postdata,
 )
 
 
@@ -41,48 +41,58 @@ class ChaturbateIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    _ERROR_MAP = {
-        'offline': 'Room is currently offline',
-        'private': 'Room is currently in a private show',
-        'away': 'Performer is currently away',
-        'password protected': 'Room is password protected',
-        'hidden': 'Hidden session in progress',
-    }
+    _ROOM_OFFLINE = 'Room is currently offline'
+    _ROOM_PRIVATE = 'Room is currently in a private show'
+    _ROOM_AWAY = 'Performer is currently away'
+    _ROOM_PASSWORD = 'Room is password protected'
+    _ROOM_HIDDEN = 'Hidden session in progress'
+    _ROOM_BLOCKED = 'Room is not avaiable in this region'
 
     def _extract_from_api(self, video_id, tld):
-        response = self._download_json(
-            f'https://chaturbate.{tld}/get_edge_hls_url_ajax/', video_id,
-            data=urlencode_postdata({'room_slug': video_id}),
+        req = Request(
+            f'https://chaturbate.{tld}/get_edge_hls_url_ajax/',
+            data=f'room_slug={video_id}'.encode(),
             headers={
-                **self.geo_verification_headers(),
                 'X-Requested-With': 'XMLHttpRequest',
-                'Accept': 'application/json',
-            }, fatal=False, impersonate=True) or {}
+                'Content-Type': 'application/x-www-form-urlencoded',
+            },
+        )
+        response = self._download_json(req, video_id, fatal=False)
 
         status = response.get('room_status')
-        if status != 'public':
-            if error := self._ERROR_MAP.get(status):
-                raise ExtractorError(error, expected=True)
-            self.report_warning('Falling back to webpage extraction')
+        if status == 'offline':
+            raise ExtractorError(self._ROOM_OFFLINE, expected=True)
+        elif status == 'private':
+            raise ExtractorError(self._ROOM_PRIVATE, expected=True)
+        elif status == 'away':
+            raise ExtractorError(self._ROOM_AWAY, expected=True)
+        elif status == 'hidden':
+            raise ExtractorError(self._ROOM_HIDDEN, expected=True)
+        elif status == 'password protected':
+            raise ExtractorError(self._ROOM_PASSWORD, expected=True)
+        elif status != 'public':
             return None
 
         m3u8_url = response.get('url')
         if not m3u8_url:
-            self.raise_geo_restricted()
+            raise ExtractorError(self._ROOM_BLOCKED, expected=True)
+
+        formats = self._extract_m3u8_formats(
+            m3u8_url, video_id, ext='mp4',
+            fatal=False, live=True)
 
         return {
             'id': video_id,
             'title': video_id,
             'thumbnail': f'https://roomimg.stream.highwebmedia.com/ri/{video_id}.jpg',
             'is_live': True,
-            'age_limit': 18,
-            'formats': self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True),
+            'formats': formats,
         }
 
     def _extract_from_webpage(self, video_id, tld):
         webpage = self._download_webpage(
             f'https://chaturbate.{tld}/{video_id}/', video_id,
-            headers=self.geo_verification_headers(), impersonate=True)
+            headers=self.geo_verification_headers())
 
         found_m3u8_urls = []
 
@@ -120,8 +130,8 @@ class ChaturbateIE(InfoExtractor):
                 webpage, 'error', group='error', default=None)
             if not error:
                 if any(p in webpage for p in (
-                        self._ERROR_MAP['offline'], 'offline_tipping', 'tip_offline')):
-                    error = self._ERROR_MAP['offline']
+                        self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
+                    error = self._ROOM_OFFLINE
             if error:
                 raise ExtractorError(error, expected=True)
             raise ExtractorError('Unable to find stream URL')
@@ -151,4 +161,7 @@ class ChaturbateIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id, tld = self._match_valid_url(url).group('id', 'tld')
-        return self._extract_from_api(video_id, tld) or self._extract_from_webpage(video_id, tld)
+        extraction = self._extract_from_api(video_id, tld)
+        if extraction is None:
+            extraction = self._extract_from_webpage(video_id, tld)
+        return extraction

yt_dlp/extractor/common.py

@@ -279,7 +279,6 @@ class InfoExtractor:
     thumbnails:     A list of dictionaries, with the following entries:
                         * "id" (optional, string) - Thumbnail format ID
                         * "url"
-                        * "ext" (optional, string) - actual image extension if not given in URL
                         * "preference" (optional, int) - quality of the image
                         * "width" (optional, int)
                         * "height" (optional, int)

yt_dlp/utils/_utils.py

@@ -216,7 +216,7 @@ def partial_application(func):
     sig = inspect.signature(func)
     required_args = [
         param.name for param in sig.parameters.values()
-        if param.kind in (inspect.Parameter.POSITIONAL_ONLY, inspect.Parameter.POSITIONAL_OR_KEYWORD)
+        if param.kind in (inspect.Parameter.POSITIONAL_ONLY, inspect.Parameter.POSITIONAL_OR_KEYWORD, inspect.Parameter.VAR_POSITIONAL)
         if param.default is inspect.Parameter.empty
     ]
 
@@ -4837,6 +4837,7 @@ def number_of_digits(number):
     return len('%d' % number)
 
 
+@partial_application
 def join_nonempty(*values, delim='-', from_dict=None):
     if from_dict is not None:
         values = (traversal.traverse_obj(from_dict, variadic(v)) for v in values)

yt_dlp/utils/traversal.py

@@ -332,14 +332,14 @@ class _RequiredError(ExtractorError):
 
 
 @typing.overload
-def subs_list_to_dict(*, lang: str | None = 'und', ext: str | None = None) -> collections.abc.Callable[[list[dict]], dict[str, list[dict]]]: ...
+def subs_list_to_dict(*, ext: str | None = None) -> collections.abc.Callable[[list[dict]], dict[str, list[dict]]]: ...
 
 
 @typing.overload
-def subs_list_to_dict(subs: list[dict] | None, /, *, lang: str | None = 'und', ext: str | None = None) -> dict[str, list[dict]]: ...
+def subs_list_to_dict(subs: list[dict] | None, /, *, ext: str | None = None) -> dict[str, list[dict]]: ...
 
 
-def subs_list_to_dict(subs: list[dict] | None = None, /, *, lang='und', ext=None):
+def subs_list_to_dict(subs: list[dict] | None = None, /, *, ext=None):
     """
     Convert subtitles from a traversal into a subtitle dict.
     The path should have an `all` immediately before this function.
@@ -352,7 +352,7 @@ def subs_list_to_dict(subs: list[dict] | None = None, /, *, lang='und', ext=None
     `quality`  The sort order for each subtitle
     """
     if subs is None:
-        return functools.partial(subs_list_to_dict, lang=lang, ext=ext)
+        return functools.partial(subs_list_to_dict, ext=ext)
 
     result = collections.defaultdict(list)
 
@@ -360,16 +360,10 @@ def subs_list_to_dict(subs: list[dict] | None = None, /, *, lang='und', ext=None
         if not url_or_none(sub.get('url')) and not sub.get('data'):
             continue
         sub_id = sub.pop('id', None)
-        if not isinstance(sub_id, str):
-            if not lang:
-                continue
-            sub_id = lang
-        sub_ext = sub.get('ext')
-        if not isinstance(sub_ext, str):
-            if not ext:
-                sub.pop('ext', None)
-            else:
-                sub['ext'] = ext
+        if sub_id is None:
+            continue
+        if ext is not None and not sub.get('ext'):
+            sub['ext'] = ext
         result[sub_id].append(sub)
     result = dict(result)
 
@@ -458,9 +452,9 @@ def trim_str(*, start=None, end=None):
     return trim
 
 
-def unpack(func, **kwargs):
+def unpack(func):
     @functools.wraps(func)
-    def inner(items):
+    def inner(items, **kwargs):
         return func(*items, **kwargs)
 
     return inner