Hello community, here is the log from the commit of package youtube-dl for openSUSE:Factory checked in at 2019-09-13 15:00:26 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/youtube-dl (Old) and /work/SRC/openSUSE:Factory/.youtube-dl.new.7948 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "youtube-dl" Fri Sep 13 15:00:26 2019 rev:115 rq:730324 version:2019.09.12.1 Changes: -------- --- /work/SRC/openSUSE:Factory/youtube-dl/python-youtube-dl.changes 2019-09-09 12:35:43.277469020 +0200 +++ /work/SRC/openSUSE:Factory/.youtube-dl.new.7948/python-youtube-dl.changes 2019-09-13 15:00:44.217283385 +0200 @@ -1,0 +2,7 @@ +Wed Sep 11 20:45:42 UTC 2019 - Fritz Reichwald <[email protected]> + +- Update to release 2019.09.12.1 + * nickjr: Add support for nickelodeonjunior.fr + * youtube: Add support for invidious tor instances + +------------------------------------------------------------------- youtube-dl.changes: same change Old: ---- youtube-dl-2019.09.01.tar.gz youtube-dl-2019.09.01.tar.gz.sig New: ---- youtube-dl-2019.09.12.1.tar.gz youtube-dl-2019.09.12.1.tar.gz.sig ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ python-youtube-dl.spec ++++++ --- /var/tmp/diff_new_pack.yayjyC/_old 2019-09-13 15:00:48.053283547 +0200 +++ /var/tmp/diff_new_pack.yayjyC/_new 2019-09-13 15:00:48.061283548 +0200 @@ -19,7 +19,7 @@ %define modname youtube-dl %{?!python_module:%define python_module() python-%{**} python3-%{**}} Name: python-youtube-dl -Version: 2019.09.01 +Version: 2019.09.12.1 Release: 0 Summary: A Python module for downloading from video sites for offline watching License: SUSE-Public-Domain AND CC-BY-SA-3.0 ++++++ youtube-dl.spec ++++++ --- /var/tmp/diff_new_pack.yayjyC/_old 2019-09-13 15:00:48.077283548 +0200 +++ /var/tmp/diff_new_pack.yayjyC/_new 2019-09-13 15:00:48.077283548 +0200 @@ -17,7 +17,7 @@ Name: youtube-dl -Version: 2019.09.01 +Version: 2019.09.12.1 Release: 0 Summary: A tool for downloading from video sites for offline watching License: SUSE-Public-Domain AND CC-BY-SA-3.0 ++++++ youtube-dl-2019.09.01.tar.gz -> youtube-dl-2019.09.12.1.tar.gz ++++++ diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/youtube-dl/ChangeLog new/youtube-dl/ChangeLog --- old/youtube-dl/ChangeLog 2019-08-31 22:32:58.000000000 +0200 +++ new/youtube-dl/ChangeLog 2019-09-11 21:53:49.000000000 +0200 @@ -1,3 +1,15 @@ +version 2019.09.12.1 + +Extractors +* [youtube] Remove quality and tbr for itag 43 (#22372) + + +version 2019.09.12 + +Extractors +* [youtube] Quick extraction tempfix (#22367, #22163) + + version 2019.09.01 Core Binary files old/youtube-dl/youtube-dl and new/youtube-dl/youtube-dl differ diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/nick.py new/youtube-dl/youtube_dl/extractor/nick.py --- old/youtube-dl/youtube_dl/extractor/nick.py 2019-08-31 22:32:46.000000000 +0200 +++ new/youtube-dl/youtube_dl/extractor/nick.py 2019-09-11 21:52:44.000000000 +0200 @@ -85,7 +85,8 @@ https?:// (?: (?P<domain>(?:www\.)?nickjr|mundonick\.uol)\.com\.br| - (?:www\.)?nickjr\.[a-z]{2} + (?:www\.)?nickjr\.[a-z]{2}| + (?:www\.)?nickelodeonjunior\.fr ) /(?:programas/)?[^/]+/videos/(?:episodios/)?(?P<id>[^/?\#.]+) ''' @@ -101,6 +102,9 @@ }, { 'url': 'http://www.nickjr.de/blaze-und-die-monster-maschinen/videos/f6caaf8f-e4e8-4cc1-b489-9380d6dcd059/', 'only_matching': True, + }, { + 'url': 'http://www.nickelodeonjunior.fr/paw-patrol-la-pat-patrouille/videos/episode-401-entier-paw-patrol/', + 'only_matching': True, }] def _real_extract(self, url): diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/platzi.py new/youtube-dl/youtube_dl/extractor/platzi.py --- old/youtube-dl/youtube_dl/extractor/platzi.py 2019-08-31 22:32:46.000000000 +0200 +++ new/youtube-dl/youtube_dl/extractor/platzi.py 2019-09-11 21:52:44.000000000 +0200 @@ -18,43 +18,10 @@ ) -class PlatziIE(InfoExtractor): - _VALID_URL = r'''(?x) - https?:// - (?: - platzi\.com/clases| # es version - courses\.platzi\.com/classes # en version - )/[^/]+/(?P<id>\d+)-[^/?\#&]+ - ''' +class PlatziBaseIE(InfoExtractor): _LOGIN_URL = 'https://platzi.com/login/' _NETRC_MACHINE = 'platzi' - _TESTS = [{ - 'url': 'https://platzi.com/clases/1311-next-js/12074-creando-nuestra-primera-pagina/', - 'md5': '8f56448241005b561c10f11a595b37e3', - 'info_dict': { - 'id': '12074', - 'ext': 'mp4', - 'title': 'Creando nuestra primera página', - 'description': 'md5:4c866e45034fc76412fbf6e60ae008bc', - 'duration': 420, - }, - 'skip': 'Requires platzi account credentials', - }, { - 'url': 'https://courses.platzi.com/classes/1367-communication-codestream/13430-background/', - 'info_dict': { - 'id': '13430', - 'ext': 'mp4', - 'title': 'Background', - 'description': 'md5:49c83c09404b15e6e71defaf87f6b305', - 'duration': 360, - }, - 'skip': 'Requires platzi account credentials', - 'params': { - 'skip_download': True, - }, - }] - def _real_initialize(self): self._login() @@ -97,6 +64,42 @@ 'Unable to login: %s' % error, expected=True) raise ExtractorError('Unable to log in') + +class PlatziIE(PlatziBaseIE): + _VALID_URL = r'''(?x) + https?:// + (?: + platzi\.com/clases| # es version + courses\.platzi\.com/classes # en version + )/[^/]+/(?P<id>\d+)-[^/?\#&]+ + ''' + + _TESTS = [{ + 'url': 'https://platzi.com/clases/1311-next-js/12074-creando-nuestra-primera-pagina/', + 'md5': '8f56448241005b561c10f11a595b37e3', + 'info_dict': { + 'id': '12074', + 'ext': 'mp4', + 'title': 'Creando nuestra primera página', + 'description': 'md5:4c866e45034fc76412fbf6e60ae008bc', + 'duration': 420, + }, + 'skip': 'Requires platzi account credentials', + }, { + 'url': 'https://courses.platzi.com/classes/1367-communication-codestream/13430-background/', + 'info_dict': { + 'id': '13430', + 'ext': 'mp4', + 'title': 'Background', + 'description': 'md5:49c83c09404b15e6e71defaf87f6b305', + 'duration': 360, + }, + 'skip': 'Requires platzi account credentials', + 'params': { + 'skip_download': True, + }, + }] + def _real_extract(self, url): lecture_id = self._match_id(url) @@ -104,7 +107,11 @@ data = self._parse_json( self._search_regex( - r'client_data\s*=\s*({.+?})\s*;', webpage, 'client data'), + # client_data may contain "};" so that we have to try more + # strict regex first + (r'client_data\s*=\s*({.+?})\s*;\s*\n', + r'client_data\s*=\s*({.+?})\s*;'), + webpage, 'client data'), lecture_id) material = data['initialState']['material'] @@ -146,7 +153,7 @@ } -class PlatziCourseIE(InfoExtractor): +class PlatziCourseIE(PlatziBaseIE): _VALID_URL = r'''(?x) https?:// (?: diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/youtube.py new/youtube-dl/youtube_dl/extractor/youtube.py --- old/youtube-dl/youtube_dl/extractor/youtube.py 2019-08-31 22:32:53.000000000 +0200 +++ new/youtube-dl/youtube_dl/extractor/youtube.py 2019-09-11 21:53:02.000000000 +0200 @@ -41,7 +41,6 @@ orderedSet, parse_codecs, parse_duration, - qualities, remove_quotes, remove_start, smuggle_url, @@ -391,6 +390,12 @@ (?:www\.)?tube\.poal\.co/| (?:www\.)?vid\.wxzm\.sx/| (?:www\.)?yt\.elukerio\.org/| + (?:www\.)?kgg2m7yk5aybusll\.onion/| + (?:www\.)?qklhadlycap4cnod\.onion/| + (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/| + (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/| + (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/| + (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/| youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains (?:.*?\#/)? # handle anchor (#/) redirect urls (?: # the various things that can precede the ID: @@ -1909,6 +1914,9 @@ return int_or_none(self._search_regex( r'\bclen[=/](\d+)', media_url, 'filesize', default=None)) + streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list) or [] + streaming_formats.extend(try_get(player_response, lambda x: x['streamingData']['adaptiveFormats'], list) or []) + if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): self.report_rtmp_download() formats = [{ @@ -1917,10 +1925,11 @@ 'url': video_info['conn'][0], 'player_url': player_url, }] - elif not is_live and (len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1): + elif not is_live and (streaming_formats or len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1): encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] if 'rtmpe%3Dyes' in encoded_url_map: raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True) + formats = [] formats_spec = {} fmt_list = video_info.get('fmt_list', [''])[0] if fmt_list: @@ -1934,91 +1943,104 @@ 'width': int_or_none(width_height[0]), 'height': int_or_none(width_height[1]), } - q = qualities(['small', 'medium', 'hd720']) - streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list) - if streaming_formats: - for fmt in streaming_formats: - itag = str_or_none(fmt.get('itag')) - if not itag: - continue - quality = fmt.get('quality') - quality_label = fmt.get('qualityLabel') or quality - formats_spec[itag] = { - 'asr': int_or_none(fmt.get('audioSampleRate')), - 'filesize': int_or_none(fmt.get('contentLength')), - 'format_note': quality_label, - 'fps': int_or_none(fmt.get('fps')), - 'height': int_or_none(fmt.get('height')), - 'quality': q(quality), - # bitrate for itag 43 is always 2147483647 - 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None, - 'width': int_or_none(fmt.get('width')), - } - formats = [] - for url_data_str in encoded_url_map.split(','): - url_data = compat_parse_qs(url_data_str) - if 'itag' not in url_data or 'url' not in url_data or url_data.get('drm_families'): + for fmt in streaming_formats: + itag = str_or_none(fmt.get('itag')) + if not itag: continue + quality = fmt.get('quality') + quality_label = fmt.get('qualityLabel') or quality + formats_spec[itag] = { + 'asr': int_or_none(fmt.get('audioSampleRate')), + 'filesize': int_or_none(fmt.get('contentLength')), + 'format_note': quality_label, + 'fps': int_or_none(fmt.get('fps')), + 'height': int_or_none(fmt.get('height')), + # bitrate for itag 43 is always 2147483647 + 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None, + 'width': int_or_none(fmt.get('width')), + } + + for fmt in streaming_formats: + if fmt.get('drm_families'): + continue + url = url_or_none(fmt.get('url')) + + if not url: + cipher = fmt.get('cipher') + if not cipher: + continue + url_data = compat_parse_qs(cipher) + url = url_or_none(try_get(url_data, lambda x: x['url'][0], compat_str)) + if not url: + continue + else: + cipher = None + url_data = compat_parse_qs(compat_urllib_parse_urlparse(url).query) + stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0])) # Unsupported FORMAT_STREAM_TYPE_OTF if stream_type == 3: continue - format_id = url_data['itag'][0] - url = url_data['url'][0] - if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True): - ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' - jsplayer_url_json = self._search_regex( - ASSETS_RE, - embed_webpage if age_gate else video_webpage, - 'JS player URL (1)', default=None) - if not jsplayer_url_json and not age_gate: - # We need the embed website after all - if embed_webpage is None: - embed_url = proto + '://www.youtube.com/embed/%s' % video_id - embed_webpage = self._download_webpage( - embed_url, video_id, 'Downloading embed webpage') - jsplayer_url_json = self._search_regex( - ASSETS_RE, embed_webpage, 'JS player URL') + format_id = fmt.get('itag') or url_data['itag'][0] + if not format_id: + continue + format_id = compat_str(format_id) - player_url = json.loads(jsplayer_url_json) - if player_url is None: - player_url_json = self._search_regex( - r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', - video_webpage, 'age gate player URL') - player_url = json.loads(player_url_json) - - if 'sig' in url_data: - url += '&signature=' + url_data['sig'][0] - elif 's' in url_data: - encrypted_sig = url_data['s'][0] + if cipher: + if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True): + ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' + jsplayer_url_json = self._search_regex( + ASSETS_RE, + embed_webpage if age_gate else video_webpage, + 'JS player URL (1)', default=None) + if not jsplayer_url_json and not age_gate: + # We need the embed website after all + if embed_webpage is None: + embed_url = proto + '://www.youtube.com/embed/%s' % video_id + embed_webpage = self._download_webpage( + embed_url, video_id, 'Downloading embed webpage') + jsplayer_url_json = self._search_regex( + ASSETS_RE, embed_webpage, 'JS player URL') - if self._downloader.params.get('verbose'): + player_url = json.loads(jsplayer_url_json) if player_url is None: - player_version = 'unknown' - player_desc = 'unknown' - else: - if player_url.endswith('swf'): - player_version = self._search_regex( - r'-(.+?)(?:/watch_as3)?\.swf$', player_url, - 'flash player', fatal=False) - player_desc = 'flash player %s' % player_version + player_url_json = self._search_regex( + r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', + video_webpage, 'age gate player URL') + player_url = json.loads(player_url_json) + + if 'sig' in url_data: + url += '&signature=' + url_data['sig'][0] + elif 's' in url_data: + encrypted_sig = url_data['s'][0] + + if self._downloader.params.get('verbose'): + if player_url is None: + player_version = 'unknown' + player_desc = 'unknown' else: - player_version = self._search_regex( - [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', - r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'], - player_url, - 'html5 player', fatal=False) - player_desc = 'html5 player %s' % player_version - - parts_sizes = self._signature_cache_id(encrypted_sig) - self.to_screen('{%s} signature length %s, %s' % - (format_id, parts_sizes, player_desc)) - - signature = self._decrypt_signature( - encrypted_sig, video_id, player_url, age_gate) - sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature' - url += '&%s=%s' % (sp, signature) + if player_url.endswith('swf'): + player_version = self._search_regex( + r'-(.+?)(?:/watch_as3)?\.swf$', player_url, + 'flash player', fatal=False) + player_desc = 'flash player %s' % player_version + else: + player_version = self._search_regex( + [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', + r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'], + player_url, + 'html5 player', fatal=False) + player_desc = 'html5 player %s' % player_version + + parts_sizes = self._signature_cache_id(encrypted_sig) + self.to_screen('{%s} signature length %s, %s' % + (format_id, parts_sizes, player_desc)) + + signature = self._decrypt_signature( + encrypted_sig, video_id, player_url, age_gate) + sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature' + url += '&%s=%s' % (sp, signature) if 'ratebypass' not in url: url += '&ratebypass=yes' @@ -2038,24 +2060,33 @@ mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0]) width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None) + if width is None: + width = int_or_none(fmt.get('width')) + if height is None: + height = int_or_none(fmt.get('height')) + filesize = int_or_none(url_data.get( 'clen', [None])[0]) or _extract_filesize(url) - quality = url_data.get('quality', [None])[0] + quality = url_data.get('quality', [None])[0] or fmt.get('quality') + quality_label = url_data.get('quality_label', [None])[0] or fmt.get('qualityLabel') + + tbr = (float_or_none(url_data.get('bitrate', [None])[0], 1000) + or float_or_none(fmt.get('bitrate'), 1000)) if format_id != '43' else None + fps = int_or_none(url_data.get('fps', [None])[0]) or int_or_none(fmt.get('fps')) more_fields = { 'filesize': filesize, - 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000), + 'tbr': tbr, 'width': width, 'height': height, - 'fps': int_or_none(url_data.get('fps', [None])[0]), - 'format_note': url_data.get('quality_label', [None])[0] or quality, - 'quality': q(quality), + 'fps': fps, + 'format_note': quality_label or quality, } for key, value in more_fields.items(): if value: dct[key] = value - type_ = url_data.get('type', [None])[0] + type_ = url_data.get('type', [None])[0] or fmt.get('mimeType') if type_: type_split = type_.split(';') kind_ext = type_split[0].split('/') diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/youtube-dl/youtube_dl/version.py new/youtube-dl/youtube_dl/version.py --- old/youtube-dl/youtube_dl/version.py 2019-08-31 22:32:58.000000000 +0200 +++ new/youtube-dl/youtube_dl/version.py 2019-09-11 21:53:49.000000000 +0200 @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.09.01' +__version__ = '2019.09.12.1'
