diff --git a/AUTHORS b/AUTHORS index 47f12a9ee..4674a5af3 100644 --- a/AUTHORS +++ b/AUTHORS @@ -111,3 +111,5 @@ Paul Hartmann Frans de Jonge Robin de Rooij Ryan Schmidt +Leslie P. Polzer +Duncan Keall diff --git a/Makefile b/Makefile index 573c82685..c6c76274f 100644 --- a/Makefile +++ b/Makefile @@ -2,6 +2,7 @@ all: youtube-dl README.md CONTRIBUTING.md README.txt youtube-dl.1 youtube-dl.bas clean: rm -rf youtube-dl.1.temp.md youtube-dl.1 youtube-dl.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ youtube-dl.tar.gz youtube-dl.zsh youtube-dl.fish *.dump *.part *.info.json *.mp4 *.flv *.mp3 *.avi CONTRIBUTING.md.tmp youtube-dl youtube-dl.exe + find -name "*.pyc" -delete PREFIX ?= /usr/local BINDIR ?= $(PREFIX)/bin @@ -43,7 +44,7 @@ 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/README.md b/README.md index 8ea31d605..04f664cd3 100644 --- a/README.md +++ b/README.md @@ -139,6 +139,8 @@ which means you can modify it, redistribute it or use it however you like. dislike_count = 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 +124,21 @@ class TestDailymotionSubtitles(BaseTestSubtitles): 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 +146,7 @@ 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 +158,13 @@ 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 +172,13 @@ class TestVimeoSubtitles(BaseTestSubtitles): 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 +193,13 @@ class TestWallaSubtitles(BaseTestSubtitles): 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 +214,110 @@ class TestCeskaTelevizeSubtitles(BaseTestSubtitles): 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') + + +class TestRtveSubtitles(BaseTestSubtitles): + url = 'http://www.rtve.es/alacarta/videos/los-misterios-de-laura/misterios-laura-capitulo-32-misterio-del-numero-17-2-parte/2428621/' + IE = RTVEALaCartaIE + + def test_allsubtitles(self): + print('Skipping, only available from Spain') + return + self.DL.params['writesubtitles'] = True + self.DL.params['allsubtitles'] = True + subtitles = self.getSubtitles() + self.assertEqual(set(subtitles.keys()), set(['es'])) + self.assertEqual(md5(subtitles['es']), '69e70cae2d40574fb7316f31d6eb7fca') if __name__ == '__main__': diff --git a/test/test_swfinterp.py b/test/test_swfinterp.py index 9f18055e6..f1e899819 100644 --- a/test/test_swfinterp.py +++ b/test/test_swfinterp.py @@ -34,8 +34,8 @@ def _make_testfunc(testfile): def test_func(self): as_file = os.path.join(TEST_DIR, testfile) swf_file = os.path.join(TEST_DIR, test_id + '.swf') - if ((not os.path.exists(swf_file)) - or os.path.getmtime(swf_file) < os.path.getmtime(as_file)): + if ((not os.path.exists(swf_file)) or + os.path.getmtime(swf_file) < os.path.getmtime(as_file)): # Recompile try: subprocess.check_call([ diff --git a/test/test_utils.py b/test/test_utils.py index c7373af1e..3fba8ae11 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -85,6 +85,8 @@ class TestUtil(unittest.TestCase): self.assertEqual( sanitize_filename('New World record at 0:12:34'), 'New World record at 0_12_34') + self.assertEqual(sanitize_filename('--gasdgf'), '_-gasdgf') + self.assertEqual(sanitize_filename('--gasdgf', is_id=True), '--gasdgf') forbidden = '"\0\\/' for fc in forbidden: @@ -244,6 +246,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(parse_duration('2.5 hours'), 9000) self.assertEqual(parse_duration('02:03:04'), 7384) self.assertEqual(parse_duration('01:02:03:04'), 93784) + self.assertEqual(parse_duration('1 hour 3 minutes'), 3780) def test_fix_xml_ampersands(self): self.assertEqual( diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 8b4a2ff5f..a15d03358 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -28,6 +28,7 @@ from .compat import ( compat_basestring, compat_cookiejar, compat_expanduser, + compat_get_terminal_size, compat_http_client, compat_kwargs, compat_str, @@ -46,7 +47,6 @@ from .utils import ( ExtractorError, format_bytes, formatSeconds, - get_term_width, locked_file, make_HTTPS_handler, MaxDownloadsReached, @@ -155,7 +155,7 @@ 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. @@ -285,7 +285,7 @@ class YoutubeDL(object): try: import pty master, slave = pty.openpty() - width = get_term_width() + width = compat_get_terminal_size().columns if width is None: width_args = [] else: @@ -309,8 +309,8 @@ class YoutubeDL(object): raise if (sys.version_info >= (3,) and sys.platform != 'win32' and - sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968'] - and not params.get('restrictfilenames', False)): + sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968'] and + not params.get('restrictfilenames', False)): # On Python 3, the Unicode filesystem API will throw errors (#1474) self.report_warning( 'Assuming --restrict-filenames since file system encoding ' @@ -1009,6 +1009,15 @@ class YoutubeDL(object): 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: @@ -1146,6 +1155,55 @@ class YoutubeDL(object): 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.""" @@ -1248,15 +1306,23 @@ class YoutubeDL(object): 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'] + ie = self.get_info_extractor(info_dict['extractor_key']) + 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: + sub_data = ie._download_webpage( + sub_info['url'], info_dict['id'], note=False) + except ExtractorError as err: + self.report_warning('Unable to download subtitle for "%s": %s' % + (sub_lang, compat_str(err.cause))) + continue try: sub_filename = subtitles_filename(filename, sub_lang, sub_format) if self.params.get('nooverwrites', False) and os.path.exists(encodeFilename(sub_filename)): @@ -1264,7 +1330,7 @@ class YoutubeDL(object): 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 @@ -1395,8 +1461,8 @@ class YoutubeDL(object): """Download a given list of URLs.""" outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) if (len(url_list) > 1 and - '%' not in outtmpl - and self.params.get('max_downloads') != 1): + '%' not in outtmpl and + self.params.get('max_downloads') != 1): raise SameFileError(outtmpl) for url in url_list: @@ -1593,6 +1659,17 @@ class YoutubeDL(object): ['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 5182dac15..2da0cff2f 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -170,6 +170,9 @@ def _real_main(argv=None): if opts.recodevideo is not None: if opts.recodevideo not in ['mp4', 'flv', 'webm', 'ogg', 'mkv']: parser.error('invalid video recode format specified') + if opts.convertsubtitles is not None: + if opts.convertsubtitles not in ['srt', 'vtt', 'ass']: + parser.error('invalid subtitle format specified') if opts.date is not None: date = DateRange.day(opts.date) @@ -189,14 +192,14 @@ def _real_main(argv=None): # In Python 2, sys.argv is a bytestring (also note http://bugs.python.org/issue2128 for Windows systems) if opts.outtmpl is not None: opts.outtmpl = opts.outtmpl.decode(preferredencoding()) - outtmpl = ((opts.outtmpl is not None and opts.outtmpl) - or (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') - or (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') - or (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') - or (opts.usetitle and '%(title)s-%(id)s.%(ext)s') - or (opts.useid and '%(id)s.%(ext)s') - or (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') - or DEFAULT_OUTTMPL) + outtmpl = ((opts.outtmpl is not None and opts.outtmpl) or + (opts.format == '-1' and opts.usetitle and '%(title)s-%(id)s-%(format)s.%(ext)s') or + (opts.format == '-1' and '%(id)s-%(format)s.%(ext)s') or + (opts.usetitle and opts.autonumber and '%(autonumber)s-%(title)s-%(id)s.%(ext)s') or + (opts.usetitle and '%(title)s-%(id)s.%(ext)s') or + (opts.useid and '%(id)s.%(ext)s') or + (opts.autonumber and '%(autonumber)s-%(id)s.%(ext)s') or + DEFAULT_OUTTMPL) if not os.path.splitext(outtmpl)[1] and opts.extractaudio: parser.error('Cannot download a video and extract audio into the same' ' file! Use "{0}.%(ext)s" instead of "{0}" as the output' @@ -223,10 +226,14 @@ def _real_main(argv=None): 'key': 'FFmpegVideoConvertor', 'preferedformat': opts.recodevideo, }) + if opts.convertsubtitles: + postprocessors.append({ + 'key': 'FFmpegSubtitlesConvertor', + 'format': opts.convertsubtitles, + }) if opts.embedsubtitles: postprocessors.append({ 'key': 'FFmpegEmbedSubtitle', - 'subtitlesformat': opts.subtitlesformat, }) if opts.xattrs: postprocessors.append({'key': 'XAttrMetadata'}) diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index e989cdbbd..b2bf149ef 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -1,9 +1,11 @@ from __future__ import unicode_literals +import collections import getpass import optparse import os import re +import shutil import socket import subprocess import sys @@ -364,6 +366,33 @@ def workaround_optparse_bug9161(): return real_add_option(self, *bargs, **bkwargs) optparse.OptionGroup.add_option = _compat_add_option +if hasattr(shutil, 'get_terminal_size'): # Python >= 3.3 + compat_get_terminal_size = shutil.get_terminal_size +else: + _terminal_size = collections.namedtuple('terminal_size', ['columns', 'lines']) + + def compat_get_terminal_size(): + columns = compat_getenv('COLUMNS', None) + if columns: + columns = int(columns) + else: + columns = None + lines = compat_getenv('LINES', None) + if lines: + lines = int(lines) + else: + lines = None + + try: + sp = subprocess.Popen( + ['stty', 'size'], + stdout=subprocess.PIPE, stderr=subprocess.PIPE) + out, err = sp.communicate() + lines, columns = map(int, out.split()) + except: + pass + return _terminal_size(columns, lines) + __all__ = [ 'compat_HTTPError', @@ -371,6 +400,7 @@ __all__ = [ 'compat_chr', 'compat_cookiejar', 'compat_expanduser', + 'compat_get_terminal_size', 'compat_getenv', 'compat_getpass', 'compat_html_entities', diff --git a/youtube_dl/downloader/common.py b/youtube_dl/downloader/common.py index 45e55b99c..3ae90021a 100644 --- a/youtube_dl/downloader/common.py +++ b/youtube_dl/downloader/common.py @@ -311,14 +311,14 @@ class FileDownloader(object): """ nooverwrites_and_exists = ( - self.params.get('nooverwrites', False) - and os.path.exists(encodeFilename(filename)) + self.params.get('nooverwrites', False) and + os.path.exists(encodeFilename(filename)) ) continuedl_and_exists = ( - self.params.get('continuedl', False) - and os.path.isfile(encodeFilename(filename)) - and not self.params.get('nopart', False) + self.params.get('continuedl', False) and + os.path.isfile(encodeFilename(filename)) and + not self.params.get('nopart', False) ) # Check file already present diff --git a/youtube_dl/downloader/f4m.py b/youtube_dl/downloader/f4m.py index b40ebfa50..3dc796faa 100644 --- a/youtube_dl/downloader/f4m.py +++ b/youtube_dl/downloader/f4m.py @@ -11,6 +11,7 @@ from .common import FileDownloader from .http import HttpFD from ..compat import ( compat_urlparse, + compat_urllib_error, ) from ..utils import ( struct_pack, @@ -121,7 +122,8 @@ class FlvReader(io.BytesIO): self.read_unsigned_int() # BootstrapinfoVersion # Profile,Live,Update,Reserved - self.read(1) + flags = self.read_unsigned_char() + live = flags & 0x20 != 0 # time scale self.read_unsigned_int() # CurrentMediaTime @@ -160,6 +162,7 @@ class FlvReader(io.BytesIO): return { 'segments': segments, 'fragments': fragments, + 'live': live, } def read_bootstrap_info(self): @@ -182,6 +185,10 @@ def build_fragments_list(boot_info): for segment, fragments_count in segment_run_table['segment_run']: for _ in range(fragments_count): res.append((segment, next(fragments_counter))) + + if boot_info['live']: + res = res[-2:] + return res @@ -246,6 +253,38 @@ class F4mFD(FileDownloader): self.report_error('Unsupported DRM') return media + def _get_bootstrap_from_url(self, bootstrap_url): + bootstrap = self.ydl.urlopen(bootstrap_url).read() + return read_bootstrap_info(bootstrap) + + def _update_live_fragments(self, bootstrap_url, latest_fragment): + fragments_list = [] + retries = 30 + while (not fragments_list) and (retries > 0): + boot_info = self._get_bootstrap_from_url(bootstrap_url) + fragments_list = build_fragments_list(boot_info) + fragments_list = [f for f in fragments_list if f[1] > latest_fragment] + if not fragments_list: + # Retry after a while + time.sleep(5.0) + retries -= 1 + + if not fragments_list: + self.report_error('Failed to update fragments') + + return fragments_list + + def _parse_bootstrap_node(self, node, base_url): + if node.text is None: + bootstrap_url = compat_urlparse.urljoin( + base_url, node.attrib['url']) + boot_info = self._get_bootstrap_from_url(bootstrap_url) + else: + bootstrap_url = None + bootstrap = base64.b64decode(node.text) + boot_info = read_bootstrap_info(bootstrap) + return (boot_info, bootstrap_url) + def real_download(self, filename, info_dict): man_url = info_dict['url'] requested_bitrate = info_dict.get('tbr') @@ -265,18 +304,13 @@ class F4mFD(FileDownloader): base_url = compat_urlparse.urljoin(man_url, media.attrib['url']) bootstrap_node = doc.find(_add_ns('bootstrapInfo')) - if bootstrap_node.text is None: - bootstrap_url = compat_urlparse.urljoin( - base_url, bootstrap_node.attrib['url']) - bootstrap = self.ydl.urlopen(bootstrap_url).read() - else: - bootstrap = base64.b64decode(bootstrap_node.text) + boot_info, bootstrap_url = self._parse_bootstrap_node(bootstrap_node, base_url) + live = boot_info['live'] metadata_node = media.find(_add_ns('metadata')) if metadata_node is not None: metadata = base64.b64decode(metadata_node.text) else: metadata = None - boot_info = read_bootstrap_info(bootstrap) fragments_list = build_fragments_list(boot_info) if self.params.get('test', False): @@ -301,7 +335,8 @@ class F4mFD(FileDownloader): (dest_stream, tmpfilename) = sanitize_open(tmpfilename, 'wb') write_flv_header(dest_stream) - write_metadata_tag(dest_stream, metadata) + if not live: + write_metadata_tag(dest_stream, metadata) # This dict stores the download progress, it's updated by the progress # hook @@ -325,8 +360,8 @@ class F4mFD(FileDownloader): state['frag_index'] += 1 estimated_size = ( - (state['downloaded_bytes'] + frag_total_bytes) - / (state['frag_index'] + 1) * total_frags) + (state['downloaded_bytes'] + frag_total_bytes) / + (state['frag_index'] + 1) * total_frags) time_now = time.time() state['total_bytes_estimate'] = estimated_size state['elapsed'] = time_now - start @@ -348,24 +383,45 @@ class F4mFD(FileDownloader): http_dl.add_progress_hook(frag_progress_hook) frags_filenames = [] - for (seg_i, frag_i) in fragments_list: + while fragments_list: + seg_i, frag_i = fragments_list.pop(0) name = 'Seg%d-Frag%d' % (seg_i, frag_i) url = base_url + name if akamai_pv: url += '?' + akamai_pv.strip(';') frag_filename = '%s-%s' % (tmpfilename, name) - success = http_dl.download(frag_filename, {'url': url}) - if not success: - return False - with open(frag_filename, 'rb') as down: - down_data = down.read() - reader = FlvReader(down_data) - while True: - _, box_type, box_data = reader.read_box_info() - if box_type == b'mdat': - dest_stream.write(box_data) - break - frags_filenames.append(frag_filename) + try: + success = http_dl.download(frag_filename, {'url': url}) + if not success: + return False + with open(frag_filename, 'rb') as down: + down_data = down.read() + reader = FlvReader(down_data) + while True: + _, box_type, box_data = reader.read_box_info() + if box_type == b'mdat': + dest_stream.write(box_data) + break + if live: + os.remove(frag_filename) + else: + frags_filenames.append(frag_filename) + except (compat_urllib_error.HTTPError, ) as err: + if live and (err.code == 404 or err.code == 410): + # We didn't keep up with the live window. Continue + # with the next available fragment. + msg = 'Fragment %d unavailable' % frag_i + self.report_warning(msg) + fragments_list = [] + else: + raise + + if not fragments_list and live and bootstrap_url: + fragments_list = self._update_live_fragments(bootstrap_url, frag_i) + total_frags += len(fragments_list) + if fragments_list and (fragments_list[0][1] > frag_i + 1): + msg = 'Missed %d fragments' % (fragments_list[0][1] - (frag_i + 1)) + self.report_warning(msg) dest_stream.close() diff --git a/youtube_dl/downloader/rtmp.py b/youtube_dl/downloader/rtmp.py index 0a52c34c7..89e98ae61 100644 --- a/youtube_dl/downloader/rtmp.py +++ b/youtube_dl/downloader/rtmp.py @@ -119,7 +119,9 @@ class RtmpFD(FileDownloader): # Download using rtmpdump. rtmpdump returns exit code 2 when # the connection was interrumpted and resuming appears to be # possible. This is part of rtmpdump's normal usage, AFAIK. - basic_args = ['rtmpdump', '--verbose', '-r', url, '-o', tmpfilename] + basic_args = [ + 'rtmpdump', '--verbose', '-r', url, + '-o', encodeFilename(tmpfilename, True)] if player_url is not None: basic_args += ['--swfVfy', player_url] if page_url is not None: diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 7d0c6b5ac..ffcc7d9ab 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -8,6 +8,7 @@ from .adobetv import AdobeTVIE from .adultswim import AdultSwimIE from .aftenposten import AftenpostenIE from .aftonbladet import AftonbladetIE +from .airmozilla import AirMozillaIE from .aljazeera import AlJazeeraIE from .alphaporno import AlphaPornoIE from .anitube import AnitubeIE @@ -63,6 +64,10 @@ from .ccc import CCCIE from .ceskatelevize import CeskaTelevizeIE from .channel9 import Channel9IE from .chilloutzone import ChilloutzoneIE +from .chirbit import ( + ChirbitIE, + ChirbitProfileIE, +) from .cinchcast import CinchcastIE from .clipfish import ClipfishIE from .cliphunter import CliphunterIE @@ -222,6 +227,7 @@ from .jeuxvideo import JeuxVideoIE from .jove import JoveIE from .jukebox import JukeboxIE from .jpopsukitv import JpopsukiIE +from .kaltura import KalturaIE from .kankan import KankanIE from .karaoketv import KaraoketvIE from .keezmovies import KeezMoviesIE @@ -233,6 +239,11 @@ from .krasview import KrasViewIE from .ku6 import Ku6IE from .la7 import LA7IE from .laola1tv import Laola1TvIE +from .letv import ( + LetvIE, + LetvTvIE, + LetvPlaylistIE +) from .lifenews import LifeNewsIE from .liveleak import LiveLeakIE from .livestream import ( @@ -335,6 +346,7 @@ from .ntvde import NTVDeIE from .ntvru import NTVRuIE from .nytimes import NYTimesIE from .nuvid import NuvidIE +from .odnoklassniki import OdnoklassnikiIE from .oktoberfesttv import OktoberfestTVIE from .ooyala import OoyalaIE from .openfilm import OpenFilmIE @@ -362,8 +374,10 @@ from .pornotube import PornotubeIE from .pornoxo import PornoXOIE from .promptfile import PromptFileIE from .prosiebensat1 import ProSiebenSat1IE +from .puls4 import Puls4IE from .pyvideo import PyvideoIE from .quickvid import QuickVidIE +from .r7 import R7IE from .radiode import RadioDeIE from .radiobremen import RadioBremenIE from .radiofrance import RadioFranceIE @@ -424,7 +438,10 @@ from .soundcloud import ( SoundcloudUserIE, SoundcloudPlaylistIE ) -from .soundgasm import SoundgasmIE +from .soundgasm import ( + SoundgasmIE, + SoundgasmProfileIE +) from .southpark import ( SouthParkIE, SouthparkDeIE, @@ -612,6 +629,7 @@ from .youtube import ( YoutubeUserIE, YoutubeWatchLaterIE, ) +from .zapiks import ZapiksIE from .zdf import ZDFIE, ZDFChannelIE from .zingmp3 import ( ZingMp3SongIE, diff --git a/youtube_dl/extractor/adobetv.py b/youtube_dl/extractor/adobetv.py index 28e07f8b0..97d128560 100644 --- a/youtube_dl/extractor/adobetv.py +++ b/youtube_dl/extractor/adobetv.py @@ -28,7 +28,6 @@ class AdobeTVIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) - webpage = self._download_webpage(url, video_id) player = self._parse_json( @@ -44,8 +43,10 @@ class AdobeTVIE(InfoExtractor): self._html_search_meta('datepublished', webpage, 'upload date')) duration = parse_duration( - self._html_search_meta('duration', webpage, 'duration') - or self._search_regex(r'Runtime:\s*(\d{2}:\d{2}:\d{2})', webpage, 'duration')) + self._html_search_meta('duration', webpage, 'duration') or + self._search_regex( + r'Runtime:\s*(\d{2}:\d{2}:\d{2})', + webpage, 'duration', fatal=False)) view_count = str_to_int(self._search_regex( r'
\s*Views?:\s*([\d,.]+)\s*
', diff --git a/youtube_dl/extractor/airmozilla.py b/youtube_dl/extractor/airmozilla.py new file mode 100644 index 000000000..611ad1e9d --- /dev/null +++ b/youtube_dl/extractor/airmozilla.py @@ -0,0 +1,74 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_duration, + parse_iso8601, +) + + +class AirMozillaIE(InfoExtractor): + _VALID_URL = r'https?://air\.mozilla\.org/(?P[0-9a-z-]+)/?' + _TEST = { + 'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/', + 'md5': '2e3e7486ba5d180e829d453875b9b8bf', + 'info_dict': { + 'id': '6x4q2w', + 'ext': 'mp4', + 'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco', + 'thumbnail': 're:https://\w+\.cloudfront\.net/6x4q2w/poster\.jpg\?t=\d+', + 'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...', + 'timestamp': 1422487800, + 'upload_date': '20150128', + 'location': 'SFO Commons', + 'duration': 3780, + 'view_count': int, + 'categories': ['Main'], + } + } + + def _real_extract(self, url): + display_id = self._match_id(url) + webpage = self._download_webpage(url, display_id) + video_id = self._html_search_regex(r'//vid.ly/(.*?)/embed', webpage, 'id') + + embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id) + jwconfig = self._search_regex(r'\svar jwconfig = (\{.*?\});\s', embed_script, 'metadata') + metadata = self._parse_json(jwconfig, video_id) + + formats = [{ + 'url': source['file'], + 'ext': source['type'], + 'format_id': self._search_regex(r'&format=(.*)$', source['file'], 'video format'), + 'format': source['label'], + 'height': int(source['label'].rstrip('p')), + } for source in metadata['playlist'][0]['sources']] + self._sort_formats(formats) + + view_count = int_or_none(self._html_search_regex( + r'Views since archived: ([0-9]+)', + webpage, 'view count', fatal=False)) + timestamp = parse_iso8601(self._html_search_regex( + r'