From a9c7198a0b3f6a94c3f3132f8ea5e7585478f344 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 19 Feb 2014 01:06:16 +0100 Subject: [PATCH] [testurl] Add extractor This is a pseudo extractor that can be used to quickly look up test URLs, or test without the test harness. --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/testurl.py | 66 ++++++++++++++++++++++++++++++++ 2 files changed, 67 insertions(+) create mode 100644 youtube_dl/extractor/testurl.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 725371883..e35287f88 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -216,6 +216,7 @@ from .sztvhu import SztvHuIE from .teamcoco import TeamcocoIE from .techtalks import TechTalksIE from .ted import TEDIE +from .testurl import TestURLIE from .tf1 import TF1IE from .theplatform import ThePlatformIE from .thisav import ThisAVIE diff --git a/youtube_dl/extractor/testurl.py b/youtube_dl/extractor/testurl.py new file mode 100644 index 000000000..bdc6e2064 --- /dev/null +++ b/youtube_dl/extractor/testurl.py @@ -0,0 +1,66 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ExtractorError + + +class TestURLIE(InfoExtractor): + """ Allows adressing of the test cases as test:yout.*be_1 """ + + IE_DESC = False # Do not list + _VALID_URL = r'test(?:url)?:(?P(?P.+?)(?:_(?P[0-9]+))?)$' + + def _real_extract(self, url): + from ..extractor import gen_extractors + + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + extractor_id = mobj.group('extractor') + all_extractors = gen_extractors() + + rex = re.compile(extractor_id, flags=re.IGNORECASE) + matching_extractors = [ + e for e in all_extractors if rex.search(e.IE_NAME)] + + if len(matching_extractors) == 0: + raise ExtractorError( + 'No extractors matching %r found' % extractor_id, + expected=True) + elif len(matching_extractors) > 1: + # Is it obvious which one to pick? + try: + extractor = next( + ie for ie in matching_extractors + if ie.IE_NAME.lower() == extractor_id.lower()) + except StopIteration: + raise ExtractorError( + ('Found multiple matching extractors: %s' % + ' '.join(ie.IE_NAME for ie in matching_extractors)), + expected=True) + + num_str = mobj.group('num') + num = int(num_str) if num_str else 0 + + testcases = [] + t = getattr(extractor, '_TEST', None) + if t: + testcases.append(t) + testcases.extend(getattr(extractor, '_TESTS', [])) + + try: + tc = testcases[num] + except IndexError: + raise ExtractorError( + ('Test case %d not found, got only %d tests' % + (num, len(testcases))), + expected=True) + + self.to_screen('Test URL: %s' % tc['url']) + + return { + '_type': 'url', + 'url': tc['url'], + 'id': video_id, + }