diff options
| -rw-r--r-- | AUTHORS | 1 | ||||
| -rw-r--r-- | test/test_subtitles.py | 28 | ||||
| -rw-r--r-- | youtube_dl/extractor/ceskatelevize.py | 45 |
3 files changed, 72 insertions, 2 deletions
@@ -100,3 +100,4 @@ Cédric Luthi Thijs Vermeir Joel Leclerc Christopher Krooss +Ondřej Caletka diff --git a/test/test_subtitles.py b/test/test_subtitles.py index d34565191..6336dd317 100644 --- a/test/test_subtitles.py +++ b/test/test_subtitles.py @@ -17,6 +17,7 @@ from youtube_dl.extractor import ( TEDIE, VimeoIE, WallaIE, + CeskaTelevizeIE, ) @@ -317,5 +318,32 @@ class TestWallaSubtitles(BaseTestSubtitles): self.assertEqual(len(subtitles), 0) +class TestCeskaTelevizeSubtitles(BaseTestSubtitles): + url = 'http://www.ceskatelevize.cz/ivysilani/10600540290-u6-uzasny-svet-techniky' + IE = CeskaTelevizeIE + + def test_list_subtitles(self): + self.DL.expect_warning('Automatic Captions not supported by this server') + self.DL.params['listsubtitles'] = True + info_dict = self.getInfoDict() + self.assertEqual(info_dict, None) + + def test_allsubtitles(self): + self.DL.expect_warning('Automatic Captions not supported by this server') + self.DL.params['writesubtitles'] = True + self.DL.params['allsubtitles'] = True + subtitles = self.getSubtitles() + self.assertEqual(set(subtitles.keys()), set(['cs'])) + self.assertEqual(md5(subtitles['cs']), '9bf52d9549533c32c427e264bf0847d4') + + def test_nosubtitles(self): + self.DL.expect_warning('video doesn\'t have subtitles') + self.url = 'http://www.ceskatelevize.cz/ivysilani/ivysilani/10441294653-hyde-park-civilizace/214411058091220' + self.DL.params['writesubtitles'] = True + self.DL.params['allsubtitles'] = True + subtitles = self.getSubtitles() + self.assertEqual(len(subtitles), 0) + + if __name__ == '__main__': unittest.main() diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index ba8376338..f70e090bb 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -3,7 +3,7 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor +from .subtitles import SubtitlesInfoExtractor from ..compat import ( compat_urllib_request, compat_urllib_parse, @@ -15,7 +15,7 @@ from ..utils import ( ) -class CeskaTelevizeIE(InfoExtractor): +class CeskaTelevizeIE(SubtitlesInfoExtractor): _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P<id>[^?#]+)' _TESTS = [ @@ -104,6 +104,17 @@ class CeskaTelevizeIE(InfoExtractor): duration = float_or_none(item.get('duration')) thumbnail = item.get('previewImageUrl') + subtitles = {} + subs = item.get('subtitles') + if subs: + subtitles['cs'] = subs[0]['url'] + + if self._downloader.params.get('listsubtitles', False): + self._list_available_subtitles(video_id, subtitles) + return + + subtitles = self._fix_subtitles(self.extract_subtitles(video_id, subtitles)) + return { 'id': episode_id, 'title': title, @@ -111,4 +122,34 @@ class CeskaTelevizeIE(InfoExtractor): 'thumbnail': thumbnail, 'duration': duration, 'formats': formats, + 'subtitles': subtitles, } + + @staticmethod + def _fix_subtitles(subtitles): + """ Convert millisecond-based subtitles to SRT """ + if subtitles is None: + return subtitles # subtitles not requested + + def _msectotimecode(msec): + """ Helper utility to convert milliseconds to timecode """ + components = [] + for divider in [1000, 60, 60, 100]: + components.append(msec % divider) + msec //= divider + return "{3:02}:{2:02}:{1:02},{0:03}".format(*components) + + def _fix_subtitle(subtitle): + for line in subtitle.splitlines(): + m = re.match(r"^\s*([0-9]+);\s*([0-9]+)\s+([0-9]+)\s*$", line) + if m: + yield m.group(1) + start, stop = (_msectotimecode(int(t)) for t in m.groups()[1:]) + yield "{0} --> {1}".format(start, stop) + else: + yield line + + fixed_subtitles = {} + for k, v in subtitles.items(): + fixed_subtitles[k] = "\r\n".join(_fix_subtitle(v)) + return fixed_subtitles |