Script 'mail_helper' called by obssrc Hello community, here is the log from the commit of package you-get for openSUSE:Factory checked in at 2024-06-24 20:56:26 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/you-get (Old) and /work/SRC/openSUSE:Factory/.you-get.new.18349 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Package is "you-get" Mon Jun 24 20:56:26 2024 rev:47 rq:1182973 version:0.4.1710 Changes: -------- --- /work/SRC/openSUSE:Factory/you-get/you-get.changes 2024-05-22 21:32:29.650016808 +0200 +++ /work/SRC/openSUSE:Factory/.you-get.new.18349/you-get.changes 2024-06-24 20:57:56.842489257 +0200 @@ -1,0 +2,6 @@ +Mon Jun 24 08:08:54 UTC 2024 - Luigi Baldoni <aloisio@gmx.com> + +- Update to version 0.4.1710 + * YouTube: Fix 403 error and throttling + +------------------------------------------------------------------- Old: ---- you-get-0.4.1700.tar.gz New: ---- you-get-0.4.1710.tar.gz ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ you-get.spec ++++++ --- /var/tmp/diff_new_pack.moGdY6/_old 2024-06-24 20:57:57.230503435 +0200 +++ /var/tmp/diff_new_pack.moGdY6/_new 2024-06-24 20:57:57.234503582 +0200 @@ -17,7 +17,7 @@ Name: you-get -Version: 0.4.1700 +Version: 0.4.1710 Release: 0 Summary: Dumb downloader that scrapes the web License: MIT ++++++ you-get-0.4.1700.tar.gz -> you-get-0.4.1710.tar.gz ++++++ diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/you-get-0.4.1700/.github/workflows/python-package.yml new/you-get-0.4.1710/.github/workflows/python-package.yml --- old/you-get-0.4.1700/.github/workflows/python-package.yml 2024-05-22 01:58:47.000000000 +0200 +++ new/you-get-0.4.1710/.github/workflows/python-package.yml 2024-06-23 21:04:52.000000000 +0200 @@ -26,7 +26,7 @@ - name: Install dependencies run: | python -m pip install --upgrade pip setuptools - pip install flake8 pytest + pip install flake8 if [ -f requirements.txt ]; then pip install -r requirements.txt; fi - name: Lint with flake8 run: | diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/you-get-0.4.1700/.gitignore new/you-get-0.4.1710/.gitignore --- old/you-get-0.4.1700/.gitignore 2024-05-22 01:58:47.000000000 +0200 +++ new/you-get-0.4.1710/.gitignore 2024-06-23 21:04:52.000000000 +0200 @@ -79,6 +79,7 @@ *.ts *.webm *.xml +*.json /.env /.idea *.m4a @@ -88,5 +89,5 @@ *.zip +.emacs* .vscode - diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/you-get-0.4.1700/Makefile new/you-get-0.4.1710/Makefile --- old/you-get-0.4.1700/Makefile 2024-05-22 01:58:47.000000000 +0200 +++ new/you-get-0.4.1710/Makefile 2024-06-23 21:04:52.000000000 +0200 @@ -8,7 +8,7 @@ @(cd src/; python3 -i -c 'import you_get; print("You-Get %s\n>>> import you_get" % you_get.version.__version__)') test: - $(SETUP) test + (cd src; python -m unittest discover -s ../tests) clean: zenity --question diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/you-get-0.4.1700/requirements.txt new/you-get-0.4.1710/requirements.txt --- old/you-get-0.4.1700/requirements.txt 1970-01-01 01:00:00.000000000 +0100 +++ new/you-get-0.4.1710/requirements.txt 2024-06-23 21:04:52.000000000 +0200 @@ -0,0 +1,2 @@ +# runtime dependencies +dukpy diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/you-get-0.4.1700/setup.py new/you-get-0.4.1710/setup.py --- old/you-get-0.4.1700/setup.py 2024-05-22 01:58:47.000000000 +0200 +++ new/you-get-0.4.1710/setup.py 2024-06-23 21:04:52.000000000 +0200 @@ -56,7 +56,8 @@ entry_points = {'console_scripts': proj_info['console_scripts']}, - extras_require={ + install_requires = ['dukpy'], + extras_require = { 'socks': ['PySocks'], } ) diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/you-get-0.4.1700/src/you_get/extractors/youtube.py new/you-get-0.4.1710/src/you_get/extractors/youtube.py --- old/you-get-0.4.1700/src/you_get/extractors/youtube.py 2024-05-22 01:58:47.000000000 +0200 +++ new/you-get-0.4.1710/src/you_get/extractors/youtube.py 2024-06-23 21:04:52.000000000 +0200 @@ -3,6 +3,13 @@ from ..common import * from ..extractor import VideoExtractor +try: + import dukpy +except ImportError: + log.e('Please install dukpy in order to extract videos from YouTube:') + log.e('$ pip install dukpy') + exit(0) +from urllib.parse import urlparse, parse_qs, urlencode from xml.dom.minidom import parseString class YouTube(VideoExtractor): @@ -68,45 +75,32 @@ 'audio_encoding': 'AAC', 'audio_bitrate': '24'}, ] + def dethrottle(js, url): + def n_to_n(js, n): + # Examples: + # yma - https://www.youtube.com/s/player/84314bef/player_ias.vflset/en_US/base.js + # Xka - https://www.youtube.com/s/player/dc0c6770/player_ias.vflset/sv_SE/base.js + f1 = match1(js, r'a\.set\("n",b\),[$\w]+\.length\|\|([$\w]+)\(""\)') + f1def = match1(js, r'\W%s=(function\(\w+\).+?\)});' % re.escape(f1)) + n = dukpy.evaljs('(%s)("%s")' % (f1def, n)) + return n + + u = urlparse(url) + qs = parse_qs(u.query) + n = n_to_n(js, qs['n'][0]) + qs['n'] = [n] + return u._replace(query=urlencode(qs, doseq=True)).geturl() + def s_to_sig(js, s): # Examples: - # - https://www.youtube.com/yts/jsbin/player-da_DK-vflWlK-zq/base.js - # - https://www.youtube.com/yts/jsbin/player-vflvABTsY/da_DK/base.js - # - https://www.youtube.com/yts/jsbin/player-vfls4aurX/da_DK/base.js - # - https://www.youtube.com/yts/jsbin/player_ias-vfl_RGK2l/en_US/base.js - # - https://www.youtube.com/yts/jsbin/player-vflRjqq_w/da_DK/base.js - # - https://www.youtube.com/yts/jsbin/player_ias-vfl-jbnrr/da_DK/base.js - # - https://www.youtube.com/s/player/0b643cd1/player_ias.vflset/sv_SE/base.js - # - https://www.youtube.com/s/player/50e823fc/player_ias.vflset/sv_SE/base.js - # - https://www.youtube.com/s/player/3b5d5649/player_ias.vflset/sv_SE/base.js - # - https://www.youtube.com/s/player/dc0c6770/player_ias.vflset/sv_SE/base.js - def tr_js(code): - code = re.sub(r'function', r'def', code) - # add prefix '_sig_' to prevent namespace pollution - code = re.sub(r'(\W)([$\w][$\w][$\w]?)\(', r'\1_sig_\2(', code) - code = re.sub(r'\$', '_dollar', code) - code = re.sub(r'\{', r': ', code) - code = re.sub(r'\}', r'\n', code) - code = re.sub(r'var\s+', r'', code) - code = re.sub(r'(\w+).join\(""\)', r'"".join(\1)', code) - code = re.sub(r'(\w+).length', r'len(\1)', code) - code = re.sub(r'(\w+).slice\((\w+)\)', r'\1[\2:]', code) - code = re.sub(r'(\w+).splice\((\w+),(\w+)\)', r'del \1[\2:\2+\3]', code) - code = re.sub(r'(\w+).split\(""\)', r'list(\1)', code) - return code - - js = js.replace('\n', ' ') - f1 = match1(js, r'\.set\(\w+\.sp,encodeURIComponent\(([$\w]+)') or \ - match1(js, r'\.set\(\w+\.sp,\(0,window\.encodeURIComponent\)\(([$\w]+)') or \ - match1(js, r'\.set\(\w+\.sp,([$\w]+)\(\w+\.s\)\)') or \ - match1(js, r'"signature",([$\w]+)\(\w+\.\w+\)') or \ - match1(js, r'=([$\w]+)\(decodeURIComponent\(') - f1def = match1(js, r'function %s(\(\w+\)\{[^\{]+\})' % re.escape(f1)) or \ - match1(js, r'\W%s=function(\(\w+\)\{[^\{]+\})' % re.escape(f1)) - f1def = re.sub(r'([$\w]+\.)([$\w]+\(\w+,\d+\))', r'\2', f1def) + # BPa - https://www.youtube.com/s/player/84314bef/player_ias.vflset/en_US/base.js + # Xva - https://www.youtube.com/s/player/dc0c6770/player_ias.vflset/sv_SE/base.js + js_code = '' + f1 = match1(js, r'=([$\w]+)\(decodeURIComponent\(') + f1def = match1(js, r'\W%s=function(\(\w+\)\{[^\{]+\})' % re.escape(f1)) + f1def = re.sub(r'([$\w]+\.)([$\w]+\(\w+,\d+\))', r'\2', f1def) # remove . prefix f1def = 'function %s%s' % (f1, f1def) - code = tr_js(f1def) - f2s = set(re.findall(r'([$\w]+)\(\w+,\d+\)', f1def)) + f2s = set(re.findall(r'([$\w]+)\(\w+,\d+\)', f1def)) # find all invoked function names for f2 in f2s: f2e = re.escape(f2) f2def = re.search(r'[^$\w]%s:function\((\w+,\w+)\)(\{[^\{\}]+\})' % f2e, js) @@ -115,13 +109,10 @@ else: f2def = re.search(r'[^$\w]%s:function\((\w+)\)(\{[^\{\}]+\})' % f2e, js) f2def = 'function {}({},b){}'.format(f2e, f2def.group(1), f2def.group(2)) - f2 = re.sub(r'\$', '_dollar', f2) # replace dollar sign - code = code + 'global _sig_%s\n' % f2 + tr_js(f2def) - - f1 = re.sub(r'\$', '_dollar', f1) # replace dollar sign - code = code + '_sig=_sig_%s(s)' % f1 - exec(code, globals(), locals()) - return locals()['_sig'] + js_code += f2def + ';' + js_code += f1def + ';%s("%s")' % (f1, s) + sig = dukpy.evaljs(js_code) + return sig def chunk_by_range(url, size): urls = [] @@ -196,188 +187,67 @@ if re.search('\Wlist=', self.url) and not kwargs.get('playlist'): log.w('This video is from a playlist. (use --playlist to download all videos in the playlist.)') - # Get video info - # 'eurl' is a magic parameter that can bypass age restriction - # full form: 'eurl=https%3A%2F%2Fyoutube.googleapis.com%2Fv%2F{VIDEO_ID}' - #video_info = parse.parse_qs(get_content('https://www.youtube.com/get_video_info?video_id={}&eurl=https%3A%2F%2Fy'.format(self.vid))) - #logging.debug('STATUS: %s' % video_info['status'][0]) - video_info = {'status': ['ok'], 'use_cipher_signature': 'True'} - - ytplayer_config = None - if 'status' not in video_info: - log.wtf('[Failed] Unknown status.', exit_code=None) - raise - elif video_info['status'] == ['ok']: - if 'use_cipher_signature' not in video_info or video_info['use_cipher_signature'] == ['False']: - self.title = parse.unquote_plus(json.loads(video_info["player_response"][0])["videoDetails"]["title"]) - # Parse video page (for DASH) - video_page = get_content('https://www.youtube.com/watch?v=%s' % self.vid) - try: - try: - # Complete ytplayer_config - ytplayer_config = json.loads(re.search('ytplayer.config\s*=\s*([^\n]+?});', video_page).group(1)) - - # Workaround: get_video_info returns bad s. Why? - if 'url_encoded_fmt_stream_map' not in ytplayer_config['args']: - stream_list = json.loads(ytplayer_config['args']['player_response'])['streamingData']['formats'] - else: - stream_list = ytplayer_config['args']['url_encoded_fmt_stream_map'].split(',') - #stream_list = ytplayer_config['args']['adaptive_fmts'].split(',') - - if 'assets' in ytplayer_config: - self.html5player = 'https://www.youtube.com' + ytplayer_config['assets']['js'] - elif re.search('([^"]*/base\.js)"', video_page): - self.html5player = 'https://www.youtube.com' + re.search('([^"]*/base\.js)"', video_page).group(1) - self.html5player = self.html5player.replace('\/', '/') # unescape URL - else: - self.html5player = None - - except: - # ytplayer_config = {args:{raw_player_response:ytInitialPlayerResponse}} - try: # FIXME: we should extract ytInitialPlayerResponse more reliably - ytInitialPlayerResponse = json.loads(re.search('ytInitialPlayerResponse\s*=\s*([^\n]+?});</script>', video_page).group(1)) - except: - ytInitialPlayerResponse = json.loads(re.search('ytInitialPlayerResponse\s*=\s*([^\n]+?});', video_page).group(1)) - - stream_list = ytInitialPlayerResponse['streamingData']['formats'] - #stream_list = ytInitialPlayerResponse['streamingData']['adaptiveFormats'] - - if re.search('([^"]*/base\.js)"', video_page): - self.html5player = 'https://www.youtube.com' + re.search('([^"]*/base\.js)"', video_page).group(1) - else: - self.html5player = None - - except: - if 'url_encoded_fmt_stream_map' not in video_info: - stream_list = json.loads(video_info['player_response'][0])['streamingData']['formats'] - else: - stream_list = video_info['url_encoded_fmt_stream_map'][0].split(',') - - if re.search('([^"]*/base\.js)"', video_page): - self.html5player = 'https://www.youtube.com' + re.search('([^"]*/base\.js)"', video_page).group(1) - else: - self.html5player = None - - else: - # Parse video page instead - video_page = get_content('https://www.youtube.com/watch?v=%s' % self.vid) - - try: # FIXME: we should extract ytInitialPlayerResponse more reliably - ytInitialPlayerResponse = json.loads(re.search('ytInitialPlayerResponse\s*=\s*([^\n]+?});</script>', video_page).group(1)) - except: - ytInitialPlayerResponse = json.loads(re.search('ytInitialPlayerResponse\s*=\s*([^\n]+?});', video_page).group(1)) - - self.title = ytInitialPlayerResponse["videoDetails"]["title"] - if re.search('([^"]*/base\.js)"', video_page): - self.html5player = 'https://www.youtube.com' + re.search('([^"]*/base\.js)"', video_page).group(1) - else: - self.html5player = None - - stream_list = ytInitialPlayerResponse['streamingData']['formats'] + # Extract from video page + logging.debug('Extracting from the video page...') + video_page = get_content('https://www.youtube.com/watch?v=%s' % self.vid) - elif video_info['status'] == ['fail']: - logging.debug('ERRORCODE: %s' % video_info['errorcode'][0]) - if video_info['errorcode'] == ['150']: - # FIXME: still relevant? - if cookies: - # Load necessary cookies into headers (for age-restricted videos) - consent, ssid, hsid, sid = 'YES', '', '', '' - for cookie in cookies: - if cookie.domain.endswith('.youtube.com'): - if cookie.name == 'SSID': - ssid = cookie.value - elif cookie.name == 'HSID': - hsid = cookie.value - elif cookie.name == 'SID': - sid = cookie.value - cookie_str = 'CONSENT=%s; SSID=%s; HSID=%s; SID=%s' % (consent, ssid, hsid, sid) - - video_page = get_content('https://www.youtube.com/watch?v=%s' % self.vid, - headers={'Cookie': cookie_str}) - else: - video_page = get_content('https://www.youtube.com/watch?v=%s' % self.vid) - - try: - ytplayer_config = json.loads(re.search('ytplayer.config\s*=\s*([^\n]+});ytplayer', video_page).group(1)) - except: - msg = re.search('class="message">([^<]+)<', video_page).group(1) - log.wtf('[Failed] Got message "%s". Try to login with --cookies.' % msg.strip()) - - if 'title' in ytplayer_config['args']: - # 150 Restricted from playback on certain sites - # Parse video page instead - self.title = ytplayer_config['args']['title'] - self.html5player = 'https://www.youtube.com' + ytplayer_config['assets']['js'] - stream_list = ytplayer_config['args']['url_encoded_fmt_stream_map'].split(',') - else: - log.wtf('[Error] The uploader has not made this video available in your country.', exit_code=None) - raise - #self.title = re.search('<meta name="title" content="([^"]+)"', video_page).group(1) - #stream_list = [] - - elif video_info['errorcode'] == ['100']: - log.wtf('[Failed] This video does not exist.', exit_code=None) #int(video_info['errorcode'][0]) - raise - - else: - log.wtf('[Failed] %s' % video_info['reason'][0], exit_code=None) #int(video_info['errorcode'][0]) - raise - - else: - log.wtf('[Failed] Invalid status.', exit_code=None) - raise - - # YouTube Live - if ytplayer_config and (ytplayer_config['args'].get('livestream') == '1' or ytplayer_config['args'].get('live_playback') == '1'): - if 'hlsvp' in ytplayer_config['args']: - hlsvp = ytplayer_config['args']['hlsvp'] - else: - player_response= json.loads(ytplayer_config['args']['player_response']) - log.e('[Failed] %s' % player_response['playabilityStatus']['reason'], exit_code=1) + try: + jsUrl = re.search('([^"]*/base\.js)"', video_page).group(1) + except: + log.wtf('[Failed] Unable to find base.js on the video page') + self.html5player = 'https://www.youtube.com' + jsUrl + logging.debug('Retrieving the player code...') + self.js = get_content(self.html5player).replace('\n', ' ') + + logging.debug('Loading ytInitialPlayerResponse...') + ytInitialPlayerResponse = json.loads(re.search('ytInitialPlayerResponse\s*=\s*([^\n]+?});(\n|</script>)', video_page).group(1)) + + # Get the video title + self.title = ytInitialPlayerResponse["videoDetails"]["title"] + + # Check the status + playabilityStatus = ytInitialPlayerResponse['playabilityStatus'] + status = playabilityStatus['status'] + logging.debug('status: %s' % status) + if status != 'OK': + # If cookies are loaded, status should be OK + try: + subreason = playabilityStatus['errorScreen']['playerErrorMessageRenderer']['subreason']['runs'][0]['text'] + log.e('[Error] %s (%s)' % (playabilityStatus['reason'], subreason)) + except: + log.e('[Error] %s' % playabilityStatus['reason']) + if status == 'LOGIN_REQUIRED': + log.e('View the video from a browser and export the cookies, then use --cookies to load cookies.') + exit(1) - if 'info_only' in kwargs and kwargs['info_only']: - return - else: - download_url_ffmpeg(hlsvp, self.title, 'mp4') - exit(0) + stream_list = ytInitialPlayerResponse['streamingData']['formats'] for stream in stream_list: - if isinstance(stream, str): - metadata = parse.parse_qs(stream) - stream_itag = metadata['itag'][0] - self.streams[stream_itag] = { - 'itag': metadata['itag'][0], - 'url': metadata['url'][0], - 'sig': metadata['sig'][0] if 'sig' in metadata else None, - 's': metadata['s'][0] if 's' in metadata else None, - 'quality': metadata['quality'][0] if 'quality' in metadata else None, - #'quality': metadata['quality_label'][0] if 'quality_label' in metadata else None, - 'type': metadata['type'][0], - 'mime': metadata['type'][0].split(';')[0], - 'container': mime_to_container(metadata['type'][0].split(';')[0]), - } + if 'signatureCipher' in stream: + logging.debug('Parsing signatureCipher for itag=%s...' % stream['itag']) + qs = parse_qs(stream['signatureCipher']) + #logging.debug(qs) + sp = qs['sp'][0] + sig = self.__class__.s_to_sig(self.js, qs['s'][0]) + url = qs['url'][0] + '&{}={}'.format(sp, sig) + elif 'url' in stream: + url = stream['url'] else: - stream_itag = str(stream['itag']) - self.streams[stream_itag] = { - 'itag': str(stream['itag']), - 'url': stream['url'] if 'url' in stream else None, - 'sig': None, - 's': None, - 'quality': stream['quality'], - 'type': stream['mimeType'], - 'mime': stream['mimeType'].split(';')[0], - 'container': mime_to_container(stream['mimeType'].split(';')[0]), - } - if 'signatureCipher' in stream: - self.streams[stream_itag].update(dict([(_.split('=')[0], parse.unquote(_.split('=')[1])) - for _ in stream['signatureCipher'].split('&')])) + log.wtf('No signatureCipher or url for itag=%s' % stream['itag']) + url = self.__class__.dethrottle(self.js, url) + + self.streams[str(stream['itag'])] = { + 'itag': str(stream['itag']), + 'url': url, + 'quality': stream['quality'], + 'type': stream['mimeType'], + 'mime': stream['mimeType'].split(';')[0], + 'container': mime_to_container(stream['mimeType'].split(';')[0]), + } - # Prepare caption tracks + # FIXME: Prepare caption tracks try: - try: - caption_tracks = json.loads(ytplayer_config['args']['player_response'])['captions']['playerCaptionsTracklistRenderer']['captionTracks'] - except: - caption_tracks = ytInitialPlayerResponse['captions']['playerCaptionsTracklistRenderer']['captionTracks'] + caption_tracks = ytInitialPlayerResponse['captions']['playerCaptionsTracklistRenderer']['captionTracks'] for ct in caption_tracks: ttsurl, lang = ct['baseUrl'], ct['languageCode'] @@ -406,151 +276,62 @@ self.caption_tracks[lang] = srt except: pass - # Prepare DASH streams (NOTE: not every video has DASH streams!) - try: - dashmpd = ytplayer_config['args']['dashmpd'] - dash_xml = parseString(get_content(dashmpd)) - for aset in dash_xml.getElementsByTagName('AdaptationSet'): - mimeType = aset.getAttribute('mimeType') - if mimeType == 'audio/mp4': - rep = aset.getElementsByTagName('Representation')[-1] - burls = rep.getElementsByTagName('BaseURL') - dash_mp4_a_url = burls[0].firstChild.nodeValue - dash_mp4_a_size = burls[0].getAttribute('yt:contentLength') - if not dash_mp4_a_size: - try: dash_mp4_a_size = url_size(dash_mp4_a_url) - except: continue - elif mimeType == 'audio/webm': - rep = aset.getElementsByTagName('Representation')[-1] - burls = rep.getElementsByTagName('BaseURL') - dash_webm_a_url = burls[0].firstChild.nodeValue - dash_webm_a_size = burls[0].getAttribute('yt:contentLength') - if not dash_webm_a_size: - try: dash_webm_a_size = url_size(dash_webm_a_url) - except: continue - elif mimeType == 'video/mp4': - for rep in aset.getElementsByTagName('Representation'): - w = int(rep.getAttribute('width')) - h = int(rep.getAttribute('height')) - itag = rep.getAttribute('id') - burls = rep.getElementsByTagName('BaseURL') - dash_url = burls[0].firstChild.nodeValue - dash_size = burls[0].getAttribute('yt:contentLength') - if not dash_size: - try: dash_size = url_size(dash_url) - except: continue - dash_urls = self.__class__.chunk_by_range(dash_url, int(dash_size)) - dash_mp4_a_urls = self.__class__.chunk_by_range(dash_mp4_a_url, int(dash_mp4_a_size)) - self.dash_streams[itag] = { - 'quality': '%sx%s' % (w, h), - 'itag': itag, - 'type': mimeType, - 'mime': mimeType, - 'container': 'mp4', - 'src': [dash_urls, dash_mp4_a_urls], - 'size': int(dash_size) + int(dash_mp4_a_size) - } - elif mimeType == 'video/webm': - for rep in aset.getElementsByTagName('Representation'): - w = int(rep.getAttribute('width')) - h = int(rep.getAttribute('height')) - itag = rep.getAttribute('id') - burls = rep.getElementsByTagName('BaseURL') - dash_url = burls[0].firstChild.nodeValue - dash_size = burls[0].getAttribute('yt:contentLength') - if not dash_size: - try: dash_size = url_size(dash_url) - except: continue - dash_urls = self.__class__.chunk_by_range(dash_url, int(dash_size)) - dash_webm_a_urls = self.__class__.chunk_by_range(dash_webm_a_url, int(dash_webm_a_size)) - self.dash_streams[itag] = { - 'quality': '%sx%s' % (w, h), - 'itag': itag, - 'type': mimeType, - 'mime': mimeType, - 'container': 'webm', - 'src': [dash_urls, dash_webm_a_urls], - 'size': int(dash_size) + int(dash_webm_a_size) - } - except: - # VEVO - if not self.html5player: return - self.html5player = self.html5player.replace('\/', '/') # unescape URL (for age-restricted videos) - self.js = get_content(self.html5player) + # Prepare DASH streams + if 'adaptiveFormats' in ytInitialPlayerResponse['streamingData']: + streams = ytInitialPlayerResponse['streamingData']['adaptiveFormats'] + + # FIXME: dead code? + # streams without contentLength got broken urls, just remove them (#2767) + streams = [stream for stream in streams if 'contentLength' in stream] + + for stream in streams: + stream['itag'] = str(stream['itag']) + if 'qualityLabel' in stream: + stream['quality_label'] = stream['qualityLabel'] + del stream['qualityLabel'] + if 'width' in stream: + stream['size'] = '{}x{}'.format(stream['width'], stream['height']) + del stream['width'] + del stream['height'] + stream['type'] = stream['mimeType'] + stream['clen'] = stream['contentLength'] + stream['init'] = '{}-{}'.format( + stream['initRange']['start'], + stream['initRange']['end']) + stream['index'] = '{}-{}'.format( + stream['indexRange']['start'], + stream['indexRange']['end']) + del stream['mimeType'] + del stream['contentLength'] + del stream['initRange'] + del stream['indexRange'] - try: - # Video info from video page (not always available) - streams = [dict([(i.split('=')[0], - parse.unquote(i.split('=')[1])) - for i in afmt.split('&')]) - for afmt in ytplayer_config['args']['adaptive_fmts'].split(',')] - except: - if 'adaptive_fmts' in video_info: - streams = [dict([(i.split('=')[0], - parse.unquote(i.split('=')[1])) - for i in afmt.split('&')]) - for afmt in video_info['adaptive_fmts'][0].split(',')] + if 'signatureCipher' in stream: + logging.debug('Parsing signatureCipher for itag=%s...' % stream['itag']) + qs = parse_qs(stream['signatureCipher']) + #logging.debug(qs) + sp = qs['sp'][0] + sig = self.__class__.s_to_sig(self.js, qs['s'][0]) + url = qs['url'][0] + '&ratebypass=yes&{}={}'.format(sp, sig) + elif 'url' in stream: + url = stream['url'] else: - try: - try: - streams = json.loads(video_info['player_response'][0])['streamingData']['adaptiveFormats'] - except: - streams = ytInitialPlayerResponse['streamingData']['adaptiveFormats'] - except: # no DASH stream at all - return - - # streams without contentLength got broken urls, just remove them (#2767) - streams = [stream for stream in streams if 'contentLength' in stream] - - for stream in streams: - stream['itag'] = str(stream['itag']) - if 'qualityLabel' in stream: - stream['quality_label'] = stream['qualityLabel'] - del stream['qualityLabel'] - if 'width' in stream: - stream['size'] = '{}x{}'.format(stream['width'], stream['height']) - del stream['width'] - del stream['height'] - stream['type'] = stream['mimeType'] - stream['clen'] = stream['contentLength'] - stream['init'] = '{}-{}'.format( - stream['initRange']['start'], - stream['initRange']['end']) - stream['index'] = '{}-{}'.format( - stream['indexRange']['start'], - stream['indexRange']['end']) - del stream['mimeType'] - del stream['contentLength'] - del stream['initRange'] - del stream['indexRange'] - if 'signatureCipher' in stream: - stream.update(dict([(_.split('=')[0], parse.unquote(_.split('=')[1])) - for _ in stream['signatureCipher'].split('&')])) - del stream['signatureCipher'] + log.wtf('No signatureCipher or url for itag=%s' % stream['itag']) + url = self.__class__.dethrottle(self.js, url) + stream['url'] = url - for stream in streams: # get over speed limiting - stream['url'] += '&ratebypass=yes' for stream in streams: # audio if stream['type'].startswith('audio/mp4'): dash_mp4_a_url = stream['url'] - if 's' in stream: - sig = self.__class__.s_to_sig(self.js, stream['s']) - dash_mp4_a_url += '&sig={}'.format(sig) dash_mp4_a_size = stream['clen'] elif stream['type'].startswith('audio/webm'): dash_webm_a_url = stream['url'] - if 's' in stream: - sig = self.__class__.s_to_sig(self.js, stream['s']) - dash_webm_a_url += '&sig={}'.format(sig) dash_webm_a_size = stream['clen'] for stream in streams: # video if 'size' in stream: if stream['type'].startswith('video/mp4'): mimeType = 'video/mp4' dash_url = stream['url'] - if 's' in stream: - sig = self.__class__.s_to_sig(self.js, stream['s']) - dash_url += '&sig={}'.format(sig) dash_size = stream['clen'] itag = stream['itag'] dash_urls = self.__class__.chunk_by_range(dash_url, int(dash_size)) @@ -567,9 +348,6 @@ elif stream['type'].startswith('video/webm'): mimeType = 'video/webm' dash_url = stream['url'] - if 's' in stream: - sig = self.__class__.s_to_sig(self.js, stream['s']) - dash_url += '&sig={}'.format(sig) dash_size = stream['clen'] itag = stream['itag'] audio_url = None @@ -610,15 +388,6 @@ if stream_id in self.streams: src = self.streams[stream_id]['url'] - if self.streams[stream_id]['sig'] is not None: - sig = self.streams[stream_id]['sig'] - src += '&sig={}'.format(sig) - elif self.streams[stream_id]['s'] is not None: - if not hasattr(self, 'js'): - self.js = get_content(self.html5player) - s = self.streams[stream_id]['s'] - sig = self.__class__.s_to_sig(self.js, s) - src += '&sig={}'.format(sig) self.streams[stream_id]['src'] = [src] self.streams[stream_id]['size'] = urls_size(self.streams[stream_id]['src']) diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/you-get-0.4.1700/src/you_get/version.py new/you-get-0.4.1710/src/you_get/version.py --- old/you-get-0.4.1700/src/you_get/version.py 2024-05-22 01:58:47.000000000 +0200 +++ new/you-get-0.4.1710/src/you_get/version.py 2024-06-23 21:04:52.000000000 +0200 @@ -1,4 +1,4 @@ #!/usr/bin/env python script_name = 'you-get' -__version__ = '0.4.1700' +__version__ = '0.4.1710' diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/you-get-0.4.1700/tests/test.py new/you-get-0.4.1710/tests/test.py --- old/you-get-0.4.1700/tests/test.py 2024-05-22 01:58:47.000000000 +0200 +++ new/you-get-0.4.1710/tests/test.py 2024-06-23 21:04:52.000000000 +0200 @@ -36,15 +36,15 @@ # 'http://www.youtube.com/attribution_link?u=/watch?v%3DldAKIzq7bvs%26feature%3...', # noqa # info_only=True #) - #youtube.download( - # 'https://www.youtube.com/watch?v=Fpr4fQSh1cc', info_only=True - #) + youtube.download( + 'https://www.youtube.com/watch?v=oRdxUFDoQe0', info_only=True + ) def test_acfun(self): acfun.download('https://www.acfun.cn/v/ac44560432', info_only=True) - def test_bilibili(self): - bilibili.download('https://www.bilibili.com/video/BV1sL4y177sC', info_only=True) + #def test_bilibili(self): + #bilibili.download('https://www.bilibili.com/video/BV1sL4y177sC', info_only=True) #def test_soundcloud(self): ## single song