diff --git a/Makefile b/Makefile index 573c82685..708732956 100644 --- a/Makefile +++ b/Makefile @@ -43,7 +43,7 @@ test: ot: offlinetest offlinetest: codetest - nosetests --verbose test --exclude test_download --exclude test_age_restriction --exclude test_subtitles --exclude test_write_annotations --exclude test_youtube_lists + nosetests --verbose test --exclude test_download.py --exclude test_age_restriction.py --exclude test_subtitles.py --exclude test_write_annotations.py --exclude test_youtube_lists.py tar: youtube-dl.tar.gz diff --git a/test/parameters.json b/test/parameters.json index af77b89b4..cbff9bd16 100644 --- a/test/parameters.json +++ b/test/parameters.json @@ -28,7 +28,7 @@ "retries": 10, "simulate": false, "subtitleslang": null, - "subtitlesformat": "srt", + "subtitlesformat": "best", "test": true, "updatetime": true, "usenetrc": false, diff --git a/test/test_YoutubeDL.py b/test/test_YoutubeDL.py index b1cd6a69f..055e42555 100644 --- a/test/test_YoutubeDL.py +++ b/test/test_YoutubeDL.py @@ -337,6 +337,65 @@ def test_format_filtering(self): downloaded = ydl.downloaded_info_dicts[0] self.assertEqual(downloaded['format_id'], 'G') + def test_subtitles(self): + def s_formats(lang, autocaption=False): + return [{ + 'ext': ext, + 'url': 'http://localhost/video.%s.%s' % (lang, ext), + '_auto': autocaption, + } for ext in ['vtt', 'srt', 'ass']] + subtitles = dict((l, s_formats(l)) for l in ['en', 'fr', 'es']) + auto_captions = dict((l, s_formats(l, True)) for l in ['it', 'pt', 'es']) + info_dict = { + 'id': 'test', + 'title': 'Test', + 'url': 'http://localhost/video.mp4', + 'subtitles': subtitles, + 'automatic_captions': auto_captions, + 'extractor': 'TEST', + } + + def get_info(params={}): + params.setdefault('simulate', True) + ydl = YDL(params) + ydl.report_warning = lambda *args, **kargs: None + return ydl.process_video_result(info_dict, download=False) + + result = get_info() + self.assertFalse(result.get('requested_subtitles')) + self.assertEqual(result['subtitles'], subtitles) + self.assertEqual(result['automatic_captions'], auto_captions) + + result = get_info({'writesubtitles': True}) + subs = result['requested_subtitles'] + self.assertTrue(subs) + self.assertEqual(set(subs.keys()), set(['en'])) + self.assertTrue(subs['en'].get('data') is None) + self.assertEqual(subs['en']['ext'], 'ass') + + result = get_info({'writesubtitles': True, 'subtitlesformat': 'foo/srt'}) + subs = result['requested_subtitles'] + self.assertEqual(subs['en']['ext'], 'srt') + + result = get_info({'writesubtitles': True, 'subtitleslangs': ['es', 'fr', 'it']}) + subs = result['requested_subtitles'] + self.assertTrue(subs) + self.assertEqual(set(subs.keys()), set(['es', 'fr'])) + + result = get_info({'writesubtitles': True, 'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']}) + subs = result['requested_subtitles'] + self.assertTrue(subs) + self.assertEqual(set(subs.keys()), set(['es', 'pt'])) + self.assertFalse(subs['es']['_auto']) + self.assertTrue(subs['pt']['_auto']) + + result = get_info({'writeautomaticsub': True, 'subtitleslangs': ['es', 'pt']}) + subs = result['requested_subtitles'] + self.assertTrue(subs) + self.assertEqual(set(subs.keys()), set(['es', 'pt'])) + self.assertTrue(subs['es']['_auto']) + self.assertTrue(subs['pt']['_auto']) + def test_add_extra_info(self): test_dict = { 'extractor': 'Foo', diff --git a/test/test_subtitles.py b/test/test_subtitles.py index bcc69a778..7f93f0a75 100644 --- a/test/test_subtitles.py +++ b/test/test_subtitles.py @@ -18,6 +18,13 @@ VimeoIE, WallaIE, CeskaTelevizeIE, + LyndaIE, + NPOIE, + ComedyCentralIE, + NRKTVIE, + RaiIE, + VikiIE, + ThePlatformIE, ) @@ -27,42 +34,38 @@ 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['requested_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): url = 'QRS8MkLhQmM' IE = YoutubeIE - def test_youtube_no_writesubtitles(self): - self.DL.params['writesubtitles'] = False - subtitles = self.getSubtitles() - self.assertEqual(subtitles, None) - - def test_youtube_subtitles(self): - self.DL.params['writesubtitles'] = True - subtitles = self.getSubtitles() - self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260') - - def test_youtube_subtitles_lang(self): - self.DL.params['writesubtitles'] = True - self.DL.params['subtitleslangs'] = ['it'] - subtitles = self.getSubtitles() - self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d') - def test_youtube_allsubtitles(self): self.DL.params['writesubtitles'] = True self.DL.params['allsubtitles'] = True subtitles = self.getSubtitles() self.assertEqual(len(subtitles.keys()), 13) + self.assertEqual(md5(subtitles['en']), '4cd9278a35ba2305f47354ee13472260') + self.assertEqual(md5(subtitles['it']), '164a51f16f260476a05b50fe4c2f161d') + for lang in ['it', 'fr', 'de']: + self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang) def test_youtube_subtitles_sbv_format(self): self.DL.params['writesubtitles'] = True @@ -76,12 +79,6 @@ def test_youtube_subtitles_vtt_format(self): subtitles = self.getSubtitles() self.assertEqual(md5(subtitles['en']), '3cb210999d3e021bd6c7f0ea751eab06') - def test_youtube_list_subtitles(self): - self.DL.expect_warning('Video doesn\'t have automatic captions') - self.DL.params['listsubtitles'] = True - info_dict = self.getInfoDict() - self.assertEqual(info_dict, None) - def test_youtube_automatic_captions(self): self.url = '8YoUxe5ncPo' self.DL.params['writeautomaticsub'] = True @@ -103,55 +100,22 @@ def test_youtube_nosubtitles(self): self.DL.params['writesubtitles'] = True self.DL.params['allsubtitles'] = True subtitles = self.getSubtitles() - self.assertEqual(len(subtitles), 0) - - def test_youtube_multiple_langs(self): - self.url = 'QRS8MkLhQmM' - self.DL.params['writesubtitles'] = True - langs = ['it', 'fr', 'de'] - self.DL.params['subtitleslangs'] = langs - subtitles = self.getSubtitles() - for lang in langs: - self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang) + self.assertFalse(subtitles) class TestDailymotionSubtitles(BaseTestSubtitles): url = 'http://www.dailymotion.com/video/xczg00' IE = DailymotionIE - def test_no_writesubtitles(self): - subtitles = self.getSubtitles() - self.assertEqual(subtitles, None) - - def test_subtitles(self): - self.DL.params['writesubtitles'] = True - subtitles = self.getSubtitles() - self.assertEqual(md5(subtitles['en']), '976553874490cba125086bbfea3ff76f') - - def test_subtitles_lang(self): - self.DL.params['writesubtitles'] = True - self.DL.params['subtitleslangs'] = ['fr'] - subtitles = self.getSubtitles() - self.assertEqual(md5(subtitles['fr']), '594564ec7d588942e384e920e5341792') - def test_allsubtitles(self): self.DL.params['writesubtitles'] = True self.DL.params['allsubtitles'] = True subtitles = self.getSubtitles() self.assertTrue(len(subtitles.keys()) >= 6) - - 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) + self.assertEqual(md5(subtitles['en']), '976553874490cba125086bbfea3ff76f') + self.assertEqual(md5(subtitles['fr']), '594564ec7d588942e384e920e5341792') + for lang in ['es', 'fr', 'de']: + self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang) def test_nosubtitles(self): self.DL.expect_warning('video doesn\'t have subtitles') @@ -159,61 +123,21 @@ def test_nosubtitles(self): self.DL.params['writesubtitles'] = True self.DL.params['allsubtitles'] = True subtitles = self.getSubtitles() - self.assertEqual(len(subtitles), 0) - - def test_multiple_langs(self): - self.DL.params['writesubtitles'] = True - langs = ['es', 'fr', 'de'] - self.DL.params['subtitleslangs'] = langs - subtitles = self.getSubtitles() - for lang in langs: - self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang) + self.assertFalse(subtitles) class TestTedSubtitles(BaseTestSubtitles): url = 'http://www.ted.com/talks/dan_dennett_on_our_consciousness.html' IE = TEDIE - def test_no_writesubtitles(self): - subtitles = self.getSubtitles() - self.assertEqual(subtitles, None) - - def test_subtitles(self): - self.DL.params['writesubtitles'] = True - subtitles = self.getSubtitles() - self.assertEqual(md5(subtitles['en']), '4262c1665ff928a2dada178f62cb8d14') - - def test_subtitles_lang(self): - self.DL.params['writesubtitles'] = True - self.DL.params['subtitleslangs'] = ['fr'] - subtitles = self.getSubtitles() - self.assertEqual(md5(subtitles['fr']), '66a63f7f42c97a50f8c0e90bc7797bb5') - def test_allsubtitles(self): self.DL.params['writesubtitles'] = True self.DL.params['allsubtitles'] = True subtitles = self.getSubtitles() 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'] - self.DL.params['subtitleslangs'] = langs - subtitles = self.getSubtitles() - for lang in langs: + self.assertEqual(md5(subtitles['en']), '4262c1665ff928a2dada178f62cb8d14') + self.assertEqual(md5(subtitles['fr']), '66a63f7f42c97a50f8c0e90bc7797bb5') + for lang in ['es', 'fr', 'de']: self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang) @@ -221,14 +145,7 @@ class TestBlipTVSubtitles(BaseTestSubtitles): url = 'http://blip.tv/a/a-6603250' IE = BlipTVIE - 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() @@ -240,39 +157,13 @@ class TestVimeoSubtitles(BaseTestSubtitles): url = 'http://vimeo.com/76979871' IE = VimeoIE - def test_no_writesubtitles(self): - subtitles = self.getSubtitles() - self.assertEqual(subtitles, None) - - def test_subtitles(self): - self.DL.params['writesubtitles'] = True - subtitles = self.getSubtitles() - self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888') - - def test_subtitles_lang(self): - self.DL.params['writesubtitles'] = True - self.DL.params['subtitleslangs'] = ['fr'] - subtitles = self.getSubtitles() - self.assertEqual(md5(subtitles['fr']), 'b6191146a6c5d3a452244d853fde6dc8') - def test_allsubtitles(self): self.DL.params['writesubtitles'] = True self.DL.params['allsubtitles'] = True subtitles = self.getSubtitles() self.assertEqual(set(subtitles.keys()), set(['de', 'en', 'es', 'fr'])) - - 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) + self.assertEqual(md5(subtitles['en']), '8062383cf4dec168fc40a088aa6d5888') + self.assertEqual(md5(subtitles['fr']), 'b6191146a6c5d3a452244d853fde6dc8') def test_nosubtitles(self): self.DL.expect_warning('video doesn\'t have subtitles') @@ -280,27 +171,13 @@ def test_nosubtitles(self): self.DL.params['writesubtitles'] = True self.DL.params['allsubtitles'] = True subtitles = self.getSubtitles() - self.assertEqual(len(subtitles), 0) - - def test_multiple_langs(self): - self.DL.params['writesubtitles'] = True - langs = ['es', 'fr', 'de'] - self.DL.params['subtitleslangs'] = langs - subtitles = self.getSubtitles() - for lang in langs: - self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang) + self.assertFalse(subtitles) class TestWallaSubtitles(BaseTestSubtitles): url = 'http://vod.walla.co.il/movie/2705958/the-yes-men' IE = WallaIE - 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 @@ -315,19 +192,13 @@ def test_nosubtitles(self): self.DL.params['writesubtitles'] = True self.DL.params['allsubtitles'] = True subtitles = self.getSubtitles() - self.assertEqual(len(subtitles), 0) + self.assertFalse(subtitles) 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 @@ -342,7 +213,96 @@ def test_nosubtitles(self): self.DL.params['writesubtitles'] = True self.DL.params['allsubtitles'] = True subtitles = self.getSubtitles() - self.assertEqual(len(subtitles), 0) + self.assertFalse(subtitles) + + +class TestLyndaSubtitles(BaseTestSubtitles): + url = 'http://www.lynda.com/Bootstrap-tutorials/Using-exercise-files/110885/114408-4.html' + IE = LyndaIE + + 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']), '09bbe67222259bed60deaa26997d73a7') + + +class TestNPOSubtitles(BaseTestSubtitles): + url = 'http://www.npo.nl/nos-journaal/28-08-2014/POW_00722860' + IE = NPOIE + + def test_allsubtitles(self): + self.DL.params['writesubtitles'] = True + self.DL.params['allsubtitles'] = True + subtitles = self.getSubtitles() + self.assertEqual(set(subtitles.keys()), set(['nl'])) + 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') + + +class TestNRKSubtitles(BaseTestSubtitles): + url = 'http://tv.nrk.no/serie/ikke-gjoer-dette-hjemme/DMPV73000411/sesong-2/episode-1' + IE = NRKTVIE + + def test_allsubtitles(self): + self.DL.params['writesubtitles'] = True + self.DL.params['allsubtitles'] = True + subtitles = self.getSubtitles() + self.assertEqual(set(subtitles.keys()), set(['no'])) + self.assertEqual(md5(subtitles['no']), '1d221e6458c95c5494dcd38e6a1f129a') + + +class TestRaiSubtitles(BaseTestSubtitles): + url = 'http://www.rai.tv/dl/RaiTV/programmi/media/ContentItem-cb27157f-9dd0-4aee-b788-b1f67643a391.html' + IE = RaiIE + + def test_allsubtitles(self): + self.DL.params['writesubtitles'] = True + self.DL.params['allsubtitles'] = True + subtitles = self.getSubtitles() + self.assertEqual(set(subtitles.keys()), set(['it'])) + self.assertEqual(md5(subtitles['it']), 'b1d90a98755126b61e667567a1f6680a') + + +class TestVikiSubtitles(BaseTestSubtitles): + url = 'http://www.viki.com/videos/1060846v-punch-episode-18' + IE = VikiIE + + 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']), '53cb083a5914b2d84ef1ab67b880d18a') + + +class TestThePlatformSubtitles(BaseTestSubtitles): + # from http://www.3playmedia.com/services-features/tools/integrations/theplatform/ + # (see http://theplatform.com/about/partners/type/subtitles-closed-captioning/) + url = 'theplatform:JFUjUE1_ehvq' + IE = ThePlatformIE + + 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']), '97e7670cbae3c4d26ae8bcc7fdd78d4b') if __name__ == '__main__': diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index ca7c3f5c6..76fc394bc 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -154,7 +154,7 @@ class YoutubeDL(object): allsubtitles: Downloads all the subtitles of the video (requires writesubtitles or writeautomaticsub) listsubtitles: Lists all available subtitles for the video - subtitlesformat: Subtitle format [srt/sbv/vtt] (default=srt) + subtitlesformat: The format code for subtitles subtitleslangs: List of languages of the subtitles to download keepvideo: Keep the video file after post-processing daterange: A DateRange object, download only if the upload_date is in the range. @@ -1008,6 +1008,15 @@ def process_video_result(self, info_dict, download=True): info_dict['timestamp']) info_dict['upload_date'] = upload_date.strftime('%Y%m%d') + if self.params.get('listsubtitles', False): + if 'automatic_captions' in info_dict: + self.list_subtitles(info_dict['id'], info_dict.get('automatic_captions'), 'automatic captions') + self.list_subtitles(info_dict['id'], info_dict.get('subtitles'), 'subtitles') + return + info_dict['requested_subtitles'] = self.process_subtitles( + info_dict['id'], info_dict.get('subtitles'), + info_dict.get('automatic_captions')) + # This extractors handle format selection themselves if info_dict['extractor'] in ['Youku']: if download: @@ -1136,6 +1145,55 @@ def process_video_result(self, info_dict, download=True): info_dict.update(formats_to_download[-1]) return info_dict + def process_subtitles(self, video_id, normal_subtitles, automatic_captions): + """Select the requested subtitles and their format""" + available_subs = {} + if normal_subtitles and self.params.get('writesubtitles'): + available_subs.update(normal_subtitles) + if automatic_captions and self.params.get('writeautomaticsub'): + for lang, cap_info in automatic_captions.items(): + if lang not in available_subs: + available_subs[lang] = cap_info + + if (not self.params.get('writesubtitles') and not + self.params.get('writeautomaticsub') or not + available_subs): + return None + + if self.params.get('allsubtitles', False): + requested_langs = available_subs.keys() + else: + if self.params.get('subtitleslangs', False): + requested_langs = self.params.get('subtitleslangs') + elif 'en' in available_subs: + requested_langs = ['en'] + else: + requested_langs = [list(available_subs.keys())[0]] + + formats_query = self.params.get('subtitlesformat', 'best') + formats_preference = formats_query.split('/') if formats_query else [] + subs = {} + for lang in requested_langs: + formats = available_subs.get(lang) + if formats is None: + self.report_warning('%s subtitles not available for %s' % (lang, video_id)) + continue + for ext in formats_preference: + if ext == 'best': + f = formats[-1] + break + matches = list(filter(lambda f: f['ext'] == ext, formats)) + if matches: + f = matches[-1] + break + else: + f = formats[-1] + self.report_warning( + 'No subtitle format found matching "%s" for language %s, ' + 'using %s' % (formats_query, lang, f['ext'])) + subs[lang] = f + return subs + def process_info(self, info_dict): """Process a single resolved IE result.""" @@ -1238,15 +1296,22 @@ def process_info(self, info_dict): subtitles_are_requested = any([self.params.get('writesubtitles', False), self.params.get('writeautomaticsub')]) - if subtitles_are_requested and 'subtitles' in info_dict and info_dict['subtitles']: + if subtitles_are_requested and info_dict.get('requested_subtitles'): # subtitles download errors are already managed as troubles in relevant IE # that way it will silently go on when used with unsupporting IE - subtitles = info_dict['subtitles'] - sub_format = self.params.get('subtitlesformat', 'srt') - for sub_lang in subtitles.keys(): - sub = subtitles[sub_lang] - if sub is None: - continue + subtitles = info_dict['requested_subtitles'] + for sub_lang, sub_info in subtitles.items(): + sub_format = sub_info['ext'] + if sub_info.get('data') is not None: + sub_data = sub_info['data'] + else: + try: + uf = self.urlopen(sub_info['url']) + sub_data = uf.read().decode('utf-8') + except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err: + self.report_warning('Unable to download subtitle for "%s": %s' % + (sub_lang, compat_str(err))) + continue try: sub_filename = subtitles_filename(filename, sub_lang, sub_format) if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)): @@ -1254,7 +1319,7 @@ def process_info(self, info_dict): else: self.to_screen('[info] Writing video subtitles to: ' + sub_filename) with io.open(encodeFilename(sub_filename), 'w', encoding='utf-8') as subfile: - subfile.write(sub) + subfile.write(sub_data) except (OSError, IOError): self.report_error('Cannot write subtitles file ' + sub_filename) return @@ -1564,6 +1629,17 @@ def list_thumbnails(self, info_dict): ['ID', 'width', 'height', 'URL'], [[t['id'], t.get('width', 'unknown'), t.get('height', 'unknown'), t['url']] for t in thumbnails])) + def list_subtitles(self, video_id, subtitles, name='subtitles'): + if not subtitles: + self.to_screen('%s has no %s' % (video_id, name)) + return + self.to_screen( + 'Available %s for %s:' % (name, video_id)) + self.to_screen(render_table( + ['Language', 'formats'], + [[lang, ', '.join(f['ext'] for f in reversed(formats))] + for lang, formats in subtitles.items()])) + def urlopen(self, req): """ Start an HTTP download """ diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 25ab3fdfe..5ce201800 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -226,7 +226,6 @@ def _real_main(argv=None): if opts.embedsubtitles: postprocessors.append({ 'key': 'FFmpegEmbedSubtitle', - 'subtitlesformat': opts.subtitlesformat, }) if opts.xattrs: postprocessors.append({'key': 'XAttrMetadata'}) diff --git a/youtube_dl/extractor/atresplayer.py b/youtube_dl/extractor/atresplayer.py index f016368fa..7669e0e3d 100644 --- a/youtube_dl/extractor/atresplayer.py +++ b/youtube_dl/extractor/atresplayer.py @@ -3,7 +3,7 @@ import time import hmac -from .subtitles import SubtitlesInfoExtractor +from .common import InfoExtractor from ..compat import ( compat_str, compat_urllib_parse, @@ -17,7 +17,7 @@ ) -class AtresPlayerIE(SubtitlesInfoExtractor): +class AtresPlayerIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?atresplayer\.com/television/[^/]+/[^/]+/[^/]+/(?P.+?)_\d+\.html' _TESTS = [ { @@ -144,13 +144,12 @@ def _real_extract(self, url): thumbnail = xpath_text(episode, './media/asset/files/background', 'thumbnail') subtitles = {} - subtitle = xpath_text(episode, './media/asset/files/subtitle', 'subtitle') - if subtitle: - subtitles['es'] = subtitle - - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, subtitles) - return + subtitle_url = xpath_text(episode, './media/asset/files/subtitle', 'subtitle') + if subtitle_url: + subtitles['es'] = [{ + 'ext': 'srt', + 'url': subtitle_url, + }] return { 'id': video_id, @@ -159,5 +158,5 @@ def _real_extract(self, url): 'thumbnail': thumbnail, 'duration': duration, 'formats': formats, - 'subtitles': self.extract_subtitles(video_id, subtitles), + 'subtitles': subtitles, } diff --git a/youtube_dl/extractor/bbccouk.py b/youtube_dl/extractor/bbccouk.py index f23e39545..abc34a576 100644 --- a/youtube_dl/extractor/bbccouk.py +++ b/youtube_dl/extractor/bbccouk.py @@ -2,12 +2,12 @@ import xml.etree.ElementTree -from .subtitles import SubtitlesInfoExtractor +from .common import InfoExtractor from ..utils import ExtractorError from ..compat import compat_HTTPError -class BBCCoUkIE(SubtitlesInfoExtractor): +class BBCCoUkIE(InfoExtractor): IE_NAME = 'bbc.co.uk' IE_DESC = 'BBC iPlayer' _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/(?:(?:(?:programmes|iplayer(?:/[^/]+)?/(?:episode|playlist))/)|music/clips[/#])(?P[\da-z]{8})' @@ -215,17 +215,32 @@ def _extract_audio(self, media, programme_id): formats.extend(conn_formats) return formats - def _extract_captions(self, media, programme_id): + def _get_subtitles(self, media, programme_id): subtitles = {} for connection in self._extract_connections(media): captions = self._download_xml(connection.get('href'), programme_id, 'Downloading captions') lang = captions.get('{http://www.w3.org/XML/1998/namespace}lang', 'en') ps = captions.findall('./{0}body/{0}div/{0}p'.format('{http://www.w3.org/2006/10/ttaf1}')) srt = '' + + def _extract_text(p): + if p.text is not None: + stripped_text = p.text.strip() + if stripped_text: + return stripped_text + return ' '.join(span.text.strip() for span in p.findall('{http://www.w3.org/2006/10/ttaf1}span')) for pos, p in enumerate(ps): - srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), p.get('begin'), p.get('end'), - p.text.strip() if p.text is not None else '') - subtitles[lang] = srt + srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), p.get('begin'), p.get('end'), _extract_text(p)) + subtitles[lang] = [ + { + 'url': connection.get('href'), + 'ext': 'ttml', + }, + { + 'data': srt, + 'ext': 'srt', + }, + ] return subtitles def _download_media_selector(self, programme_id): @@ -249,7 +264,7 @@ def _download_media_selector(self, programme_id): elif kind == 'video': formats.extend(self._extract_video(media, programme_id)) elif kind == 'captions': - subtitles = self._extract_captions(media, programme_id) + subtitles = self.extract_subtitles(media, programme_id) return formats, subtitles @@ -324,10 +339,6 @@ def _real_extract(self, url): else: programme_id, title, description, duration, formats, subtitles = self._download_playlist(group_id) - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(programme_id, subtitles) - return - self._sort_formats(formats) return { diff --git a/youtube_dl/extractor/bliptv.py b/youtube_dl/extractor/bliptv.py index 436cc5155..8c7ba4b91 100644 --- a/youtube_dl/extractor/bliptv.py +++ b/youtube_dl/extractor/bliptv.py @@ -3,7 +3,6 @@ import re from .common import InfoExtractor -from .subtitles import SubtitlesInfoExtractor from ..compat import ( compat_str, @@ -18,7 +17,7 @@ ) -class BlipTVIE(SubtitlesInfoExtractor): +class BlipTVIE(InfoExtractor): _VALID_URL = r'https?://(?:\w+\.)?blip\.tv/(?:(?:.+-|rss/flash/)(?P\d+)|((?:play/|api\.swf#)(?P[\da-zA-Z+_]+)))' _TESTS = [ @@ -143,7 +142,7 @@ def itunes(s): categories = [category.text for category in item.findall('category')] formats = [] - subtitles = {} + subtitles_urls = {} media_group = item.find(media('group')) for media_content in media_group.findall(media('content')): @@ -161,7 +160,7 @@ def itunes(s): } lang = role.rpartition('-')[-1].strip().lower() langcode = LANGS.get(lang, lang) - subtitles[langcode] = url + subtitles_urls[langcode] = url elif media_type.startswith('video/'): formats.append({ 'url': real_url, @@ -175,11 +174,7 @@ def itunes(s): }) self._sort_formats(formats) - # subtitles - video_subtitles = self.extract_subtitles(video_id, subtitles) - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, subtitles) - return + subtitles = self.extract_subtitles(video_id, subtitles_urls) return { 'id': video_id, @@ -192,15 +187,22 @@ def itunes(s): 'thumbnail': thumbnail, 'categories': categories, 'formats': formats, - 'subtitles': video_subtitles, + 'subtitles': subtitles, } - def _download_subtitle_url(self, sub_lang, url): - # For some weird reason, blip.tv serves a video instead of subtitles - # when we request with a common UA - req = compat_urllib_request.Request(url) - req.add_header('User-Agent', 'youtube-dl') - return self._download_webpage(req, None, note=False) + def _get_subtitles(self, video_id, subtitles_urls): + subtitles = {} + for lang, url in subtitles_urls.items(): + # For some weird reason, blip.tv serves a video instead of subtitles + # when we request with a common UA + req = compat_urllib_request.Request(url) + req.add_header('User-Agent', 'youtube-dl') + subtitles[lang] = [{ + # The extension is 'srt' but it's actually an 'ass' file + 'ext': 'ass', + 'data': self._download_webpage(req, None, note=False), + }] + return subtitles class BlipTVUserIE(InfoExtractor): diff --git a/youtube_dl/extractor/ceskatelevize.py b/youtube_dl/extractor/ceskatelevize.py index f70e090bb..65f6be623 100644 --- a/youtube_dl/extractor/ceskatelevize.py +++ b/youtube_dl/extractor/ceskatelevize.py @@ -3,7 +3,7 @@ import re -from .subtitles import SubtitlesInfoExtractor +from .common import InfoExtractor from ..compat import ( compat_urllib_request, compat_urllib_parse, @@ -15,7 +15,7 @@ ) -class CeskaTelevizeIE(SubtitlesInfoExtractor): +class CeskaTelevizeIE(InfoExtractor): _VALID_URL = r'https?://www\.ceskatelevize\.cz/(porady|ivysilani)/(.+/)?(?P[^?#]+)' _TESTS = [ @@ -107,13 +107,7 @@ def _real_extract(self, url): 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)) + subtitles = self.extract_subtitles(episode_id, subs) return { 'id': episode_id, @@ -125,11 +119,20 @@ def _real_extract(self, url): 'subtitles': subtitles, } + def _get_subtitles(self, episode_id, subs): + original_subtitles = self._download_webpage( + subs[0]['url'], episode_id, 'Downloading subtitles') + srt_subs = self._fix_subtitles(original_subtitles) + return { + 'cs': [{ + 'ext': 'srt', + 'data': srt_subs, + }] + } + @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 """ @@ -149,7 +152,4 @@ def _fix_subtitle(subtitle): else: yield line - fixed_subtitles = {} - for k, v in subtitles.items(): - fixed_subtitles[k] = "\r\n".join(_fix_subtitle(v)) - return fixed_subtitles + return "\r\n".join(_fix_subtitle(subtitles)) diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 79f6d199b..87fce9cd8 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -150,8 +150,14 @@ class InfoExtractor(object): If not explicitly set, calculated from timestamp. uploader_id: Nickname or id of the video uploader. location: Physical location where the video was filmed. - subtitles: The subtitle file contents as a dictionary in the format - {language: subtitles}. + subtitles: The available subtitles as a dictionary in the format + {language: subformats}. "subformats" is a list sorted from + lower to higher preference, each element is a dictionary + with the "ext" entry and one of: + * "data": The subtitles file contents + * "url": A url pointing to the subtitles file + automatic_captions: Like 'subtitles', used by the YoutubeIE for + automatically generated captions duration: Length of the video in seconds, as an integer. view_count: How many users have watched the video on the platform. like_count: Number of positive ratings of the video @@ -1011,6 +1017,24 @@ def is_suitable(self, age_limit): any_restricted = any_restricted or is_restricted return not any_restricted + def extract_subtitles(self, *args, **kwargs): + if (self._downloader.params.get('writesubtitles', False) or + self._downloader.params.get('listsubtitles')): + return self._get_subtitles(*args, **kwargs) + return {} + + def _get_subtitles(self, *args, **kwargs): + raise NotImplementedError("This method must be implemented by subclasses") + + def extract_automatic_captions(self, *args, **kwargs): + if (self._downloader.params.get('writeautomaticsub', False) or + self._downloader.params.get('listsubtitles')): + return self._get_automatic_captions(*args, **kwargs) + return {} + + def _get_automatic_captions(self, *args, **kwargs): + raise NotImplementedError("This method must be implemented by subclasses") + class SearchInfoExtractor(InfoExtractor): """ diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 1680f532f..f1da7d09b 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -9,7 +9,7 @@ from hashlib import sha1 from math import pow, sqrt, floor -from .subtitles import SubtitlesInfoExtractor +from .common import InfoExtractor from ..compat import ( compat_urllib_parse, compat_urllib_request, @@ -25,10 +25,9 @@ aes_cbc_decrypt, inc, ) -from .common import InfoExtractor -class CrunchyrollIE(SubtitlesInfoExtractor): +class CrunchyrollIE(InfoExtractor): _VALID_URL = r'https?://(?:(?Pwww|m)\.)?(?Pcrunchyroll\.(?:com|fr)/(?:[^/]*/[^/?&]*?|media/\?id=)(?P[0-9]+))(?:[/?&]|$)' _TESTS = [{ 'url': 'http://www.crunchyroll.com/wanna-be-the-strongest-in-the-world/episode-1-an-idol-wrestler-is-born-645513', @@ -187,6 +186,38 @@ def ass_bool(strvalue): return output + def _get_subtitles(self, video_id, webpage): + subtitles = {} + for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage): + sub_page = self._download_webpage( + 'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id, + video_id, note='Downloading subtitles for ' + sub_name) + id = self._search_regex(r'id=\'([0-9]+)', sub_page, 'subtitle_id', fatal=False) + iv = self._search_regex(r'([^<]+)', sub_page, 'subtitle_iv', fatal=False) + data = self._search_regex(r'([^<]+)', sub_page, 'subtitle_data', fatal=False) + if not id or not iv or not data: + continue + id = int(id) + iv = base64.b64decode(iv) + data = base64.b64decode(data) + + subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8') + lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False) + if not lang_code: + continue + sub_root = xml.etree.ElementTree.fromstring(subtitle) + subtitles[lang_code] = [ + { + 'ext': 'srt', + 'data': self._convert_subtitles_to_srt(sub_root), + }, + { + 'ext': 'ass', + 'data': self._convert_subtitles_to_ass(sub_root), + }, + ] + return subtitles + def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('video_id') @@ -249,34 +280,7 @@ def _real_extract(self, url): 'format_id': video_format, }) - subtitles = {} - sub_format = self._downloader.params.get('subtitlesformat', 'srt') - for sub_id, sub_name in re.findall(r'\?ssid=([0-9]+)" title="([^"]+)', webpage): - sub_page = self._download_webpage( - 'http://www.crunchyroll.com/xml/?req=RpcApiSubtitle_GetXml&subtitle_script_id=' + sub_id, - video_id, note='Downloading subtitles for ' + sub_name) - id = self._search_regex(r'id=\'([0-9]+)', sub_page, 'subtitle_id', fatal=False) - iv = self._search_regex(r'([^<]+)', sub_page, 'subtitle_iv', fatal=False) - data = self._search_regex(r'([^<]+)', sub_page, 'subtitle_data', fatal=False) - if not id or not iv or not data: - continue - id = int(id) - iv = base64.b64decode(iv) - data = base64.b64decode(data) - - subtitle = self._decrypt_subtitles(data, iv, id).decode('utf-8') - lang_code = self._search_regex(r'lang_code=["\']([^"\']+)', subtitle, 'subtitle_lang_code', fatal=False) - if not lang_code: - continue - sub_root = xml.etree.ElementTree.fromstring(subtitle) - if sub_format == 'ass': - subtitles[lang_code] = self._convert_subtitles_to_ass(sub_root) - else: - subtitles[lang_code] = self._convert_subtitles_to_srt(sub_root) - - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, subtitles) - return + subtitles = self.extract_subtitles(video_id, webpage) return { 'id': video_id, diff --git a/youtube_dl/extractor/dailymotion.py b/youtube_dl/extractor/dailymotion.py index b2dbf4a92..42b20a46d 100644 --- a/youtube_dl/extractor/dailymotion.py +++ b/youtube_dl/extractor/dailymotion.py @@ -6,7 +6,6 @@ import itertools from .common import InfoExtractor -from .subtitles import SubtitlesInfoExtractor from ..compat import ( compat_str, @@ -31,7 +30,7 @@ def _build_request(url): return request -class DailymotionIE(DailymotionBaseInfoExtractor, SubtitlesInfoExtractor): +class DailymotionIE(DailymotionBaseInfoExtractor): """Information Extractor for Dailymotion""" _VALID_URL = r'(?i)(?:https?://)?(?:(www|touch)\.)?dailymotion\.[a-z]{2,3}/(?:(embed|#)/)?video/(?P[^/?_]+)' @@ -143,9 +142,6 @@ def _real_extract(self, url): # subtitles video_subtitles = self.extract_subtitles(video_id, webpage) - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, webpage) - return view_count = str_to_int(self._search_regex( r'video_views_count[^>]+>\s+([\d\.,]+)', @@ -169,7 +165,7 @@ def _real_extract(self, url): 'view_count': view_count, } - def _get_available_subtitles(self, video_id, webpage): + def _get_subtitles(self, video_id, webpage): try: sub_list = self._download_webpage( 'https://api.dailymotion.com/video/%s/subtitles?fields=id,language,url' % video_id, @@ -179,7 +175,7 @@ def _get_available_subtitles(self, video_id, webpage): return {} info = json.loads(sub_list) if (info['total'] > 0): - sub_lang_list = dict((l['language'], l['url']) for l in info['list']) + sub_lang_list = dict((l['language'], [{'url': l['url'], 'ext': 'srt'}]) for l in info['list']) return sub_lang_list self._downloader.report_warning('video doesn\'t have subtitles') return {} diff --git a/youtube_dl/extractor/drtv.py b/youtube_dl/extractor/drtv.py index d5df18d7c..8257e35a4 100644 --- a/youtube_dl/extractor/drtv.py +++ b/youtube_dl/extractor/drtv.py @@ -1,11 +1,10 @@ from __future__ import unicode_literals -from .subtitles import SubtitlesInfoExtractor -from .common import ExtractorError +from .common import InfoExtractor, ExtractorError from ..utils import parse_iso8601 -class DRTVIE(SubtitlesInfoExtractor): +class DRTVIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P[\da-z-]+)(?:[/#?]|$)' _TEST = { @@ -76,7 +75,7 @@ def _real_extract(self, url): } for subs in subtitles_list: lang = subs['Language'] - subtitles[LANGS.get(lang, lang)] = subs['Uri'] + subtitles[LANGS.get(lang, lang)] = [{'url': subs['Uri'], 'ext': 'vtt'}] if not formats and restricted_to_denmark: raise ExtractorError( @@ -84,10 +83,6 @@ def _real_extract(self, url): self._sort_formats(formats) - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, subtitles) - return - return { 'id': video_id, 'title': title, @@ -96,5 +91,5 @@ def _real_extract(self, url): 'timestamp': timestamp, 'duration': duration, 'formats': formats, - 'subtitles': self.extract_subtitles(video_id, subtitles), + 'subtitles': subtitles, } diff --git a/youtube_dl/extractor/lynda.py b/youtube_dl/extractor/lynda.py index 762cefa34..109055e72 100644 --- a/youtube_dl/extractor/lynda.py +++ b/youtube_dl/extractor/lynda.py @@ -3,7 +3,6 @@ import re import json -from .subtitles import SubtitlesInfoExtractor from .common import InfoExtractor from ..compat import ( compat_str, @@ -16,7 +15,7 @@ ) -class LyndaIE(SubtitlesInfoExtractor): +class LyndaIE(InfoExtractor): IE_NAME = 'lynda' IE_DESC = 'lynda.com videos' _VALID_URL = r'https?://www\.lynda\.com/[^/]+/[^/]+/\d+/(\d+)-\d\.html' @@ -88,11 +87,7 @@ def _real_extract(self, url): self._check_formats(formats, video_id) self._sort_formats(formats) - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, page) - return - - subtitles = self._fix_subtitles(self.extract_subtitles(video_id, page)) + subtitles = self.extract_subtitles(video_id, page) return { 'id': video_id, @@ -144,38 +139,31 @@ def _login(self): if re.search(self._SUCCESSFUL_LOGIN_REGEX, login_page) is None: raise ExtractorError('Unable to log in') - def _fix_subtitles(self, subtitles): - if subtitles is None: - return subtitles # subtitles not requested - - fixed_subtitles = {} - for k, v in subtitles.items(): - subs = json.loads(v) - if len(subs) == 0: + def _fix_subtitles(self, subs): + srt = '' + for pos in range(0, len(subs) - 1): + seq_current = subs[pos] + m_current = re.match(self._TIMECODE_REGEX, seq_current['Timecode']) + if m_current is None: continue - srt = '' - for pos in range(0, len(subs) - 1): - seq_current = subs[pos] - m_current = re.match(self._TIMECODE_REGEX, seq_current['Timecode']) - if m_current is None: - continue - seq_next = subs[pos + 1] - m_next = re.match(self._TIMECODE_REGEX, seq_next['Timecode']) - if m_next is None: - continue - appear_time = m_current.group('timecode') - disappear_time = m_next.group('timecode') - text = seq_current['Caption'] - srt += '%s\r\n%s --> %s\r\n%s' % (str(pos), appear_time, disappear_time, text) - if srt: - fixed_subtitles[k] = srt - return fixed_subtitles + seq_next = subs[pos + 1] + m_next = re.match(self._TIMECODE_REGEX, seq_next['Timecode']) + if m_next is None: + continue + appear_time = m_current.group('timecode') + disappear_time = m_next.group('timecode') + text = seq_current['Caption'] + srt += '%s\r\n%s --> %s\r\n%s' % (str(pos), appear_time, disappear_time, text) + if srt: + return srt - def _get_available_subtitles(self, video_id, webpage): + def _get_subtitles(self, video_id, webpage): url = 'http://www.lynda.com/ajax/player?videoId=%s&type=transcript' % video_id - sub = self._download_webpage(url, None, False) - sub_json = json.loads(sub) - return {'en': url} if len(sub_json) > 0 else {} + subs = self._download_json(url, None, False) + if subs: + return {'en': [{'ext': 'srt', 'data': self._fix_subtitles(subs)}]} + else: + return {} class LyndaCourseIE(InfoExtractor): diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py index 3c61a850f..d7ab6a9ae 100644 --- a/youtube_dl/extractor/mit.py +++ b/youtube_dl/extractor/mit.py @@ -5,9 +5,6 @@ from .common import InfoExtractor from .youtube import YoutubeIE -from ..compat import ( - compat_urlparse, -) from ..utils import ( clean_html, ExtractorError, @@ -108,7 +105,6 @@ class OCWMITIE(InfoExtractor): 'upload_date': '20121109', 'uploader_id': 'MIT', 'uploader': 'MIT OpenCourseWare', - # 'subtitles': 'http://ocw.mit.edu/courses/electrical-engineering-and-computer-science/6-041-probabilistic-systems-analysis-and-applied-probability-fall-2010/video-lectures/lecture-7-multiple-variables-expectations-independence/MIT6_041F11_lec07_300k.mp4.srt' } }, { @@ -121,7 +117,6 @@ class OCWMITIE(InfoExtractor): 'uploader_id': 'MIT', 'uploader': 'MIT OpenCourseWare', 'description': 'This section contains lecture video excerpts, lecture notes, an interactive mathlet with supporting documents, and problem solving videos.', - # 'subtitles': 'http://ocw.mit.edu//courses/mathematics/18-01sc-single-variable-calculus-fall-2010/ocw-18.01-f07-lec01_300k.SRT' } } ] @@ -140,7 +135,6 @@ def _real_extract(self, url): metadata = re.sub(r'[\'"]', '', embed_chapter_media.group(1)) metadata = re.split(r', ?', metadata) yt = metadata[1] - subs = compat_urlparse.urljoin(self._BASE_URL, metadata[7]) else: # search for call to ocw_embed_chapter_media(container_id, media_url, provider, page_url, image_url, captions_file) embed_media = re.search(r'ocw_embed_media\((.+?)\)', webpage) @@ -148,7 +142,6 @@ def _real_extract(self, url): metadata = re.sub(r'[\'"]', '', embed_media.group(1)) metadata = re.split(r', ?', metadata) yt = metadata[1] - subs = compat_urlparse.urljoin(self._BASE_URL, metadata[5]) else: raise ExtractorError('Unable to find embedded YouTube video.') video_id = YoutubeIE.extract_id(yt) @@ -159,7 +152,5 @@ def _real_extract(self, url): 'title': title, 'description': description, 'url': yt, - 'url_transparent' - 'subtitles': subs, 'ie_key': 'Youtube', } diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py index bc7f49ebb..c11de1cb6 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 diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py index c075618e8..9c01eb0af 100644 --- a/youtube_dl/extractor/npo.py +++ b/youtube_dl/extractor/npo.py @@ -1,6 +1,5 @@ from __future__ import unicode_literals -from .subtitles import SubtitlesInfoExtractor from .common import InfoExtractor from ..utils import ( fix_xml_ampersands, @@ -12,7 +11,7 @@ ) -class NPOBaseIE(SubtitlesInfoExtractor): +class NPOBaseIE(InfoExtractor): def _get_token(self, video_id): token_page = self._download_webpage( 'http://ida.omroep.nl/npoplayer/i.js', @@ -164,13 +163,10 @@ def _get_info(self, video_id): subtitles = {} if metadata.get('tt888') == 'ja': - subtitles['nl'] = 'http://e.omroep.nl/tt888/%s' % video_id - - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, subtitles) - return - - subtitles = self.extract_subtitles(video_id, subtitles) + subtitles['nl'] = [{ + 'ext': 'vtt', + 'url': 'http://e.omroep.nl/tt888/%s' % video_id, + }] return { 'id': video_id, diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py index f6de26022..46f493cfc 100644 --- a/youtube_dl/extractor/nrk.py +++ b/youtube_dl/extractor/nrk.py @@ -10,7 +10,6 @@ parse_duration, unified_strdate, ) -from .subtitles import SubtitlesInfoExtractor class NRKIE(InfoExtractor): @@ -73,7 +72,7 @@ def _real_extract(self, url): } -class NRKTVIE(SubtitlesInfoExtractor): +class NRKTVIE(InfoExtractor): _VALID_URL = r'(?Phttp://tv\.nrk(?:super)?\.no/)(?:serie/[^/]+|program)/(?P[a-zA-Z]{4}\d{8})(?:/\d{2}-\d{2}-\d{4})?(?:#del=(?P\d+))?' _TESTS = [ @@ -156,7 +155,7 @@ def _debug_print(self, txt): if self._downloader.params.get('verbose', False): self.to_screen('[debug] %s' % txt) - def _extract_captions(self, subtitlesurl, video_id, baseurl): + def _get_subtitles(self, subtitlesurl, video_id, baseurl): url = "%s%s" % (baseurl, subtitlesurl) self._debug_print('%s: Subtitle url: %s' % (video_id, url)) captions = self._download_xml(url, video_id, 'Downloading subtitles') @@ -170,7 +169,10 @@ def _extract_captions(self, subtitlesurl, video_id, baseurl): endtime = self._seconds2str(begin + duration) text = '\n'.join(p.itertext()) srt += '%s\r\n%s --> %s\r\n%s\r\n\r\n' % (str(pos), starttime, endtime, text) - return {lang: srt} + return {lang: [ + {'ext': 'ttml', 'url': url}, + {'ext': 'srt', 'data': srt}, + ]} def _extract_f4m(self, manifest_url, video_id): return self._extract_f4m_formats(manifest_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124', video_id) @@ -243,10 +245,7 @@ def _real_extract(self, url): webpage, 'subtitle URL', default=None) subtitles = None if subtitles_url: - subtitles = self._extract_captions(subtitles_url, video_id, baseurl) - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, subtitles) - return + subtitles = self.extract_subtitles(subtitles_url, video_id, baseurl) return { 'id': video_id, diff --git a/youtube_dl/extractor/rai.py b/youtube_dl/extractor/rai.py index aa26b7e0b..144e33982 100644 --- a/youtube_dl/extractor/rai.py +++ b/youtube_dl/extractor/rai.py @@ -2,7 +2,7 @@ import re -from .subtitles import SubtitlesInfoExtractor +from .common import InfoExtractor from ..compat import ( compat_urllib_parse, ) @@ -12,7 +12,7 @@ ) -class RaiIE(SubtitlesInfoExtractor): +class RaiIE(InfoExtractor): _VALID_URL = r'(?Phttp://(?:.+?\.)?(?:rai\.it|rai\.tv|rainews\.it)/dl/.+?-(?P[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})(?:-.+?)?\.html)' _TESTS = [ { @@ -89,15 +89,7 @@ def _real_extract(self, url): 'ext': 'mp4', }) - if self._downloader.params.get('listsubtitles', False): - page = self._download_webpage(url, video_id) - self._list_available_subtitles(video_id, page) - return - - subtitles = {} - if self._have_to_download_any_subtitles: - page = self._download_webpage(url, video_id) - subtitles = self.extract_subtitles(video_id, page) + subtitles = self.extract_subtitles(video_id, url) return { 'id': video_id, @@ -111,7 +103,8 @@ def _real_extract(self, url): 'subtitles': subtitles, } - def _get_available_subtitles(self, video_id, webpage): + def _get_subtitles(self, video_id, url): + webpage = self._download_webpage(url, video_id) subtitles = {} m = re.search(r'https?://) (?Pwww|embed(?:-ssl)?)(?P\.ted\.com/ @@ -184,11 +184,6 @@ def _talk_info(self, url, video_name): self._sort_formats(formats) video_id = compat_str(talk_info['id']) - # subtitles - video_subtitles = self.extract_subtitles(video_id, talk_info) - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, talk_info) - return thumbnail = talk_info['thumb'] if not thumbnail.startswith('http'): @@ -199,21 +194,25 @@ def _talk_info(self, url, video_name): 'uploader': talk_info['speaker'], 'thumbnail': thumbnail, 'description': self._og_search_description(webpage), - 'subtitles': video_subtitles, + 'subtitles': self._get_subtitles(video_id, talk_info), 'formats': formats, 'duration': talk_info.get('duration'), } - def _get_available_subtitles(self, video_id, talk_info): + def _get_subtitles(self, video_id, talk_info): languages = [lang['languageCode'] for lang in talk_info.get('languages', [])] if languages: sub_lang_list = {} for l in languages: - url = 'http://www.ted.com/talks/subtitles/id/%s/lang/%s/format/srt' % (video_id, l) - sub_lang_list[l] = url + sub_lang_list[l] = [ + { + 'url': 'http://www.ted.com/talks/subtitles/id/%s/lang/%s/format/%s' % (video_id, l, ext), + 'ext': ext, + } + for ext in ['ted', 'srt'] + ] return sub_lang_list else: - self._downloader.report_warning('video doesn\'t have subtitles') return {} def _watch_info(self, url, name): diff --git a/youtube_dl/extractor/theplatform.py b/youtube_dl/extractor/theplatform.py index f7b34bd26..feac666f7 100644 --- a/youtube_dl/extractor/theplatform.py +++ b/youtube_dl/extractor/theplatform.py @@ -8,7 +8,7 @@ import hashlib -from .subtitles import SubtitlesInfoExtractor +from .common import InfoExtractor from ..compat import ( compat_str, ) @@ -22,7 +22,7 @@ _x = lambda p: xpath_with_ns(p, {'smil': 'http://www.w3.org/2005/SMIL21/Language'}) -class ThePlatformIE(SubtitlesInfoExtractor): +class ThePlatformIE(InfoExtractor): _VALID_URL = r'''(?x) (?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P[^/]+)/ (?P(?:[^/\?]+/(?:swf|config)|onsite)/select/)? @@ -106,15 +106,11 @@ def _real_extract(self, url): captions = info.get('captions') if isinstance(captions, list): for caption in captions: - lang, src = caption.get('lang'), caption.get('src') - if lang and src: - subtitles[lang] = src - - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, subtitles) - return - - subtitles = self.extract_subtitles(video_id, subtitles) + lang, src, mime = caption.get('lang', 'en'), caption.get('src'), caption.get('type') + subtitles[lang] = [{ + 'ext': 'srt' if mime == 'text/srt' else 'ttml', + 'url': src, + }] head = meta.find(_x('smil:head')) body = meta.find(_x('smil:body')) diff --git a/youtube_dl/extractor/viki.py b/youtube_dl/extractor/viki.py index 944901e14..6816dacb6 100644 --- a/youtube_dl/extractor/viki.py +++ b/youtube_dl/extractor/viki.py @@ -2,16 +2,17 @@ import re +from ..compat import compat_urlparse from ..utils import ( ExtractorError, unescapeHTML, unified_strdate, US_RATINGS, ) -from .subtitles import SubtitlesInfoExtractor +from .common import InfoExtractor -class VikiIE(SubtitlesInfoExtractor): +class VikiIE(InfoExtractor): IE_NAME = 'viki' _VALID_URL = r'^https?://(?:www\.)?viki\.com/videos/(?P[0-9]+v)' @@ -69,9 +70,6 @@ def _real_extract(self, url): # subtitles video_subtitles = self.extract_subtitles(video_id, info_webpage) - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, info_webpage) - return return { 'id': video_id, @@ -85,12 +83,15 @@ def _real_extract(self, url): 'upload_date': upload_date, } - def _get_available_subtitles(self, video_id, info_webpage): + def _get_subtitles(self, video_id, info_webpage): res = {} - for sturl_html in re.findall(r'', info_webpage): + for sturl_html in re.findall(r'[a-z]+)\.vtt', sturl) if not m: continue - res[m.group('lang')] = sturl + res[m.group('lang')] = [{ + 'url': compat_urlparse.urljoin('http://www.viki.com', sturl), + 'ext': 'vtt', + }] return res diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py index 4cd2f73d9..8f540f578 100644 --- a/youtube_dl/extractor/vimeo.py +++ b/youtube_dl/extractor/vimeo.py @@ -7,7 +7,6 @@ import hashlib from .common import InfoExtractor -from .subtitles import SubtitlesInfoExtractor from ..compat import ( compat_HTTPError, compat_urllib_parse, @@ -53,7 +52,7 @@ def _login(self): self._download_webpage(login_request, None, False, 'Wrong login info') -class VimeoIE(VimeoBaseInfoExtractor, SubtitlesInfoExtractor): +class VimeoIE(VimeoBaseInfoExtractor): """Information extractor for vimeo.com.""" # _VALID_URL matches Vimeo URLs @@ -378,12 +377,10 @@ def _real_extract(self, url): text_tracks = config['request'].get('text_tracks') if text_tracks: for tt in text_tracks: - subtitles[tt['lang']] = 'http://vimeo.com' + tt['url'] - - video_subtitles = self.extract_subtitles(video_id, subtitles) - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, subtitles) - return + subtitles[tt['lang']] = [{ + 'ext': 'vtt', + 'url': 'http://vimeo.com' + tt['url'], + }] return { 'id': video_id, @@ -399,7 +396,7 @@ def _real_extract(self, url): 'view_count': view_count, 'like_count': like_count, 'comment_count': comment_count, - 'subtitles': video_subtitles, + 'subtitles': subtitles, } diff --git a/youtube_dl/extractor/walla.py b/youtube_dl/extractor/walla.py index 672bda7a7..24efbd6e6 100644 --- a/youtube_dl/extractor/walla.py +++ b/youtube_dl/extractor/walla.py @@ -3,14 +3,14 @@ import re -from .subtitles import SubtitlesInfoExtractor +from .common import InfoExtractor from ..utils import ( xpath_text, int_or_none, ) -class WallaIE(SubtitlesInfoExtractor): +class WallaIE(InfoExtractor): _VALID_URL = r'http://vod\.walla\.co\.il/[^/]+/(?P\d+)/(?P.+)' _TEST = { 'url': 'http://vod.walla.co.il/movie/2642630/one-direction-all-for-one', @@ -52,13 +52,10 @@ def _real_extract(self, url): subtitles = {} for subtitle in item.findall('./subtitles/subtitle'): lang = xpath_text(subtitle, './title') - subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = xpath_text(subtitle, './src') - - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, subtitles) - return - - subtitles = self.extract_subtitles(video_id, subtitles) + subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = [{ + 'ext': 'srt', + 'url': xpath_text(subtitle, './src'), + }] formats = [] for quality in item.findall('./qualities/quality'): diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 3d3d43491..22db896b1 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -11,7 +11,6 @@ import traceback from .common import InfoExtractor, SearchInfoExtractor -from .subtitles import SubtitlesInfoExtractor from ..jsinterp import JSInterpreter from ..swfinterp import SWFInterpreter from ..compat import ( @@ -185,7 +184,7 @@ def _real_initialize(self): return -class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): +class YoutubeIE(YoutubeBaseInfoExtractor): IE_DESC = 'YouTube.com' _VALID_URL = r"""(?x)^ ( @@ -648,7 +647,7 @@ def _decrypt_signature(self, s, video_id, player_url, age_gate=False): raise ExtractorError( 'Signature extraction failed: ' + tb, cause=e) - def _get_available_subtitles(self, video_id, webpage): + def _get_subtitles(self, video_id, webpage): try: subs_doc = self._download_xml( 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, @@ -662,23 +661,27 @@ def _get_available_subtitles(self, video_id, webpage): lang = track.attrib['lang_code'] if lang in sub_lang_list: continue - params = compat_urllib_parse.urlencode({ - 'lang': lang, - 'v': video_id, - 'fmt': self._downloader.params.get('subtitlesformat', 'srt'), - 'name': track.attrib['name'].encode('utf-8'), - }) - url = 'https://www.youtube.com/api/timedtext?' + params - sub_lang_list[lang] = url + sub_formats = [] + for ext in ['sbv', 'vtt', 'srt']: + params = compat_urllib_parse.urlencode({ + 'lang': lang, + 'v': video_id, + 'fmt': ext, + 'name': track.attrib['name'].encode('utf-8'), + }) + sub_formats.append({ + 'url': 'https://www.youtube.com/api/timedtext?' + params, + 'ext': ext, + }) + sub_lang_list[lang] = sub_formats if not sub_lang_list: self._downloader.report_warning('video doesn\'t have subtitles') return {} return sub_lang_list - def _get_available_automatic_caption(self, video_id, webpage): + def _get_automatic_captions(self, video_id, webpage): """We need the webpage for getting the captions url, pass it as an argument to speed up the process.""" - sub_format = self._downloader.params.get('subtitlesformat', 'srt') self.to_screen('%s: Looking for automatic captions' % video_id) mobj = re.search(r';ytplayer.config = ({.*?});', webpage) err_msg = 'Couldn\'t find automatic captions for %s' % video_id @@ -708,14 +711,20 @@ def _get_available_automatic_caption(self, video_id, webpage): sub_lang_list = {} for lang_node in caption_list.findall('target'): sub_lang = lang_node.attrib['lang_code'] - params = compat_urllib_parse.urlencode({ - 'lang': original_lang, - 'tlang': sub_lang, - 'fmt': sub_format, - 'ts': timestamp, - 'kind': caption_kind, - }) - sub_lang_list[sub_lang] = caption_url + '&' + params + sub_formats = [] + for ext in ['sbv', 'vtt', 'srt']: + params = compat_urllib_parse.urlencode({ + 'lang': original_lang, + 'tlang': sub_lang, + 'fmt': ext, + 'ts': timestamp, + 'kind': caption_kind, + }) + sub_formats.append({ + 'url': caption_url + '&' + params, + 'ext': ext, + }) + sub_lang_list[sub_lang] = sub_formats return sub_lang_list # An extractor error can be raise by the download process if there are # no automatic captions but there are subtitles @@ -970,10 +979,7 @@ def _extract_count(count_name): # subtitles video_subtitles = self.extract_subtitles(video_id, video_webpage) - - if self._downloader.params.get('listsubtitles', False): - self._list_available_subtitles(video_id, video_webpage) - return + automatic_captions = self.extract_automatic_captions(video_id, video_webpage) if 'length_seconds' not in video_info: self._downloader.report_warning('unable to extract video duration') @@ -1122,6 +1128,7 @@ def _map_to_format_list(urlmap): 'description': video_description, 'categories': video_categories, 'subtitles': video_subtitles, + 'automatic_captions': automatic_captions, 'duration': video_duration, 'age_limit': 18 if age_gate else 0, 'annotations': video_annotations, diff --git a/youtube_dl/options.py b/youtube_dl/options.py index 5f678f76b..5c2d153b1 100644 --- a/youtube_dl/options.py +++ b/youtube_dl/options.py @@ -387,8 +387,8 @@ def _hide_login_info(opts): help='lists all available subtitles for the video') subtitles.add_option( '--sub-format', - action='store', dest='subtitlesformat', metavar='FORMAT', default='srt', - help='subtitle format (default=srt) ([sbv/vtt] youtube only)') + action='store', dest='subtitlesformat', metavar='FORMAT', default='best', + help='subtitle format, accepts formats preference, for example: "ass/srt/best"') subtitles.add_option( '--sub-lang', '--sub-langs', '--srt-lang', action='callback', dest='subtitleslangs', metavar='LANGS', type='str', diff --git a/youtube_dl/postprocessor/ffmpeg.py b/youtube_dl/postprocessor/ffmpeg.py index 3f2e6cf1d..398fe050e 100644 --- a/youtube_dl/postprocessor/ffmpeg.py +++ b/youtube_dl/postprocessor/ffmpeg.py @@ -496,10 +496,6 @@ class FFmpegEmbedSubtitlePP(FFmpegPostProcessor): 'zu': 'zul', } - def __init__(self, downloader=None, subtitlesformat='srt'): - super(FFmpegEmbedSubtitlePP, self).__init__(downloader) - self._subformat = subtitlesformat - @classmethod def _conver_lang_code(cls, code): """Convert language code from ISO 639-1 to ISO 639-2/T""" @@ -509,13 +505,14 @@ def run(self, information): if information['ext'] != 'mp4': self._downloader.to_screen('[ffmpeg] Subtitles can only be embedded in mp4 files') return True, information - if not information.get('subtitles'): + subtitles = information.get('requested_subtitles') + if not subtitles: self._downloader.to_screen('[ffmpeg] There aren\'t any subtitles to embed') return True, information - sub_langs = [key for key in information['subtitles']] + sub_langs = list(subtitles.keys()) filename = information['filepath'] - input_files = [filename] + [subtitles_filename(filename, lang, self._subformat) for lang in sub_langs] + input_files = [filename] + [subtitles_filename(filename, lang, sub_info['ext']) for lang, sub_info in subtitles.items()] opts = [ '-map', '0',