Adding upstream version 2024.03.10.upstream/2024.03.10

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 50 insertions, 0 deletions

diff --git a/yt_dlp/extractor/testurl.py b/yt_dlp/extractor/testurl.py
new file mode 100644
index 0000000..3cf0017
--- /dev/null
+++ b/yt_dlp/extractor/testurl.py
@@ -0,0 +1,50 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class TestURLIE(InfoExtractor):
+    """ Allows addressing of the test cases as test:yout.*be_1 """
+
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'test(?:url)?:(?P<extractor>.*?)(?:_(?P<num>\d+|all))?$'
+
+    def _real_extract(self, url):
+        from . import gen_extractor_classes
+
+        extractor_id, num = self._match_valid_url(url).group('extractor', 'num')
+        if not extractor_id:
+            return {'id': ':test', 'title': '', 'url': url}
+
+        rex = re.compile(extractor_id, flags=re.IGNORECASE)
+        matching_extractors = [e for e in gen_extractor_classes() if rex.search(e.IE_NAME)]
+
+        if len(matching_extractors) == 0:
+            raise ExtractorError(f'No extractors matching {extractor_id!r} found', expected=True)
+        elif len(matching_extractors) > 1:
+            extractor = next((  # Check for exact match
+                ie for ie in matching_extractors if ie.IE_NAME.lower() == extractor_id.lower()
+            ), None) or next((  # Check for exact match without plugin suffix
+                ie for ie in matching_extractors if ie.IE_NAME.split('+')[0].lower() == extractor_id.lower()
+            ), None)
+            if not extractor:
+                raise ExtractorError(
+                    'Found multiple matching extractors: %s' % ' '.join(ie.IE_NAME for ie in matching_extractors),
+                    expected=True)
+        else:
+            extractor = matching_extractors[0]
+
+        testcases = tuple(extractor.get_testcases(True))
+        if num == 'all':
+            return self.playlist_result(
+                [self.url_result(tc['url'], extractor) for tc in testcases],
+                url, f'{extractor.IE_NAME} tests')
+        try:
+            tc = testcases[int(num or 0)]
+        except IndexError:
+            raise ExtractorError(
+                f'Test case {num or 0} not found, got only {len(testcases)} tests', expected=True)
+
+        self.to_screen(f'Test URL: {tc["url"]}')
+        return self.url_result(tc['url'], extractor)