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 ..extractor import gen_extractor_classes
  15
  16         extractor_id, num = self._match_valid_url(url).group('extractor', 'num')
  17
  18         rex = re.compile(extractor_id, flags=re.IGNORECASE)
  19         matching_extractors = [e for e in gen_extractor_classes() if rex.search(e.IE_NAME)]
  20
  21         if len(matching_extractors) == 0:
  22             raise ExtractorError('No extractors matching {extractor_id!r} found', expected=True)
  23         elif len(matching_extractors) > 1:
  24             try:  # Check for exact match
  25                 extractor = next(
  26                     ie for ie in matching_extractors
  27                     if ie.IE_NAME.lower() == extractor_id.lower())
  28             except StopIteration:
  29                 raise ExtractorError(
  30                     'Found multiple matching extractors: %s' % ' '.join(ie.IE_NAME for ie in matching_extractors),
  31                     expected=True)
  32         else:
  33             extractor = matching_extractors[0]
  34
  35         testcases = tuple(extractor.get_testcases(True))
  36         try:
  37             tc = testcases[int(num or 0)]
  38         except IndexError:
  39             raise ExtractorError(
  40                 f'Test case {num or 0} not found, got only {len(testcases)} tests', expected=True)
  41
  42         self.to_screen(f'Test URL: {tc["url"]}')
  43         return self.url_result(tc['url'])