Sirius/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

Improve subtitles support

Browse source 
For each language the extractor builds a list with the available formats sorted (like for video formats), then YoutubeDL selects one of them using the '--sub-format' option which now allows giving the format preferences (for example 'ass/srt/best').
For each format the 'url' field can be set so that we only download the contents if needed, or if the contents needs to be processed (like in crunchyroll) the 'data' field can be used.

The reasons for this change are:
* We weren't checking that the format given with '--sub-format' was available, checking it in each extractor would be repetitive.
* It allows to easily support giving a format preference.
* The subtitles were automatically downloaded in the extractor, but I think that if you use for example the '--dump-json' option you want to finish as fast as possible.

Currently only the ted extractor has been updated, but the old system still works.
This commit is contained in:
Jaime Marquínez Ferrándiz 2015-02-15 18:03:41 +01:00
parent 8fb474fb17
commit a504ced097
7 changed files with 121 additions and 37 deletions
Download patch file Download diff file Expand all files Collapse all files

24
test/test_subtitles.py
View file

@ -27,15 +27,23 @@ class BaseTestSubtitles(unittest.TestCase):
def setUp(self):
self.DL = FakeYDL()
self.ie = self.IE(self.DL)
self.ie = self.IE()
self.DL.add_info_extractor(self.ie)
def getInfoDict(self):
info_dict = self.ie.extract(self.url)
info_dict = self.DL.extract_info(self.url, download=False)
return info_dict
def getSubtitles(self):
info_dict = self.getInfoDict()
return info_dict['subtitles']
subtitles = info_dict['subtitles']
if not subtitles:
return subtitles
for sub_info in subtitles.values():
if sub_info.get('data') is None:
uf = self.DL.urlopen(sub_info['url'])
sub_info['data'] = uf.read().decode('utf-8')
return dict((l, sub_info['data']) for l, sub_info in subtitles.items())
class TestYoutubeSubtitles(BaseTestSubtitles):
@ -176,7 +184,7 @@ class TestTedSubtitles(BaseTestSubtitles):
def test_no_writesubtitles(self):
subtitles = self.getSubtitles()
self.assertEqual(subtitles, None)
self.assertFalse(subtitles)
def test_subtitles(self):
self.DL.params['writesubtitles'] = True
@ -196,18 +204,10 @@ class TestTedSubtitles(BaseTestSubtitles):
self.assertTrue(len(subtitles.keys()) >= 28)
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_automatic_captions(self):
self.DL.expect_warning('Automatic Captions not supported by this server')
self.DL.params['writeautomaticsub'] = True
self.DL.params['subtitleslang'] = ['en']
subtitles = self.getSubtitles()
self.assertTrue(len(subtitles.keys()) == 0)
def test_multiple_langs(self):
self.DL.params['writesubtitles'] = True
langs = ['es', 'fr', 'de']