From 0af25f784bc5bff7cbce2d4af725b4bf2d2262c5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Wed, 18 Feb 2015 18:27:45 +0100 Subject: [PATCH] [mtv] Convert to new subtitles system --- test/test_subtitles.py | 16 ++++++++++++++++ youtube_dl/extractor/mtv.py | 26 +++++++------------------- 2 files changed, 23 insertions(+), 19 deletions(-) diff --git a/test/test_subtitles.py b/test/test_subtitles.py index b2195cac4b..c018d9b494 100644 --- a/test/test_subtitles.py +++ b/test/test_subtitles.py @@ -20,6 +20,7 @@ CeskaTelevizeIE, LyndaIE, NPOIE, + ComedyCentralIE, ) @@ -330,5 +331,20 @@ def test_allsubtitles(self): self.assertEqual(md5(subtitles['nl']), 'fc6435027572b63fb4ab143abd5ad3f4') +class TestMTVSubtitles(BaseTestSubtitles): + url = 'http://www.cc.com/video-clips/kllhuv/stand-up-greg-fitzsimmons--uncensored---too-good-of-a-mother' + IE = ComedyCentralIE + + def getInfoDict(self): + return super(TestMTVSubtitles, self).getInfoDict()['entries'][0] + + def test_allsubtitles(self): + self.DL.params['writesubtitles'] = True + self.DL.params['allsubtitles'] = True + subtitles = self.getSubtitles() + self.assertEqual(set(subtitles.keys()), set(['en'])) + self.assertEqual(md5(subtitles['en']), 'b9f6ca22a6acf597ec76f61749765e65') + + if __name__ == '__main__': unittest.main() diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index bc7f49ebba..c11de1cb61 100644 --- a/youtube_dl/extractor/mtv.py +++ b/youtube_dl/extractor/mtv.py @@ -2,7 +2,7 @@ import re -from .subtitles import SubtitlesInfoExtractor +from .common import InfoExtractor from ..compat import ( compat_urllib_parse, compat_urllib_request, @@ -23,7 +23,7 @@ def _media_xml_tag(tag): return '{http://search.yahoo.com/mrss/}%s' % tag -class MTVServicesInfoExtractor(SubtitlesInfoExtractor): +class MTVServicesInfoExtractor(InfoExtractor): _MOBILE_TEMPLATE = None @staticmethod @@ -95,25 +95,15 @@ def _extract_video_formats(self, mdoc, mtvn_id): def _extract_subtitles(self, mdoc, mtvn_id): subtitles = {} - FORMATS = { - 'scc': 'cea-608', - 'eia-608': 'cea-608', - 'xml': 'ttml', - } - subtitles_format = FORMATS.get( - self._downloader.params.get('subtitlesformat'), 'ttml') for transcript in mdoc.findall('.//transcript'): if transcript.get('kind') != 'captions': continue lang = transcript.get('srclang') - for typographic in transcript.findall('./typographic'): - captions_format = typographic.get('format') - if captions_format == subtitles_format: - subtitles[lang] = compat_str(typographic.get('src')) - break - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(mtvn_id, subtitles) - return self.extract_subtitles(mtvn_id, subtitles) + subtitles[lang] = [{ + 'url': compat_str(typographic.get('src')), + 'ext': typographic.get('format') + } for typographic in transcript.findall('./typographic')] + return subtitles def _get_video_info(self, itemdoc): uri = itemdoc.find('guid').text @@ -196,8 +186,6 @@ def _real_extract(self, url): webpage, 'mgid') videos_info = self._get_videos_info(mgid) - if self._downloader.params.get('listsubtitles', False): - return return videos_info