yt_dlp/extractor/testurl.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import ExtractorError
   5
   6
   7 class TestURLIE(InfoExtractor):
   8     """ Allows addressing of the test cases as test:yout.*be_1 """
   9
  10     IE_DESC = False  # Do not list
  11     _VALID_URL = r'test(?:url)?:(?P<extractor>.*?)(?:_(?P<num>[0-9]+))?$'
  12
  13     def _real_extract(self, url):
  14         from . import gen_extractor_classes
  15
  16         extractor_id, num = self._match_valid_url(url).group('extractor', 'num')
  17         if not extractor_id:
  18             return {'id': ':test', 'title': '', 'url': url}
  19
  20         rex = re.compile(extractor_id, flags=re.IGNORECASE)
  21         matching_extractors = [e for e in gen_extractor_classes() if rex.search(e.IE_NAME)]
  22
  23         if len(matching_extractors) == 0:
  24             raise ExtractorError(f'No extractors matching {extractor_id!r} found', expected=True)
  25         elif len(matching_extractors) > 1:
  26             extractor = next((  # Check for exact match
  27                 ie for ie in matching_extractors if ie.IE_NAME.lower() == extractor_id.lower()
  28             ), None) or next((  # Check for exact match without plugin suffix
  29                 ie for ie in matching_extractors if ie.IE_NAME.split('+')[0].lower() == extractor_id.lower()
  30             ), None)
  31             if not extractor:
  32                 raise ExtractorError(
  33                     'Found multiple matching extractors: %s' % ' '.join(ie.IE_NAME for ie in matching_extractors),
  34                     expected=True)
  35         else:
  36             extractor = matching_extractors[0]
  37
  38         testcases = tuple(extractor.get_testcases(True))
  39         try:
  40             tc = testcases[int(num or 0)]
  41         except IndexError:
  42             raise ExtractorError(
  43                 f'Test case {num or 0} not found, got only {len(testcases)} tests', expected=True)
  44
  45         self.to_screen(f'Test URL: {tc["url"]}')
  46         return self.url_result(tc['url'])