diff --git a/.github/ISSUE_TEMPLATE/1_broken_site.md b/.github/ISSUE_TEMPLATE/1_broken_site.md index 0b8a124e6..dc303946e 100644 --- a/.github/ISSUE_TEMPLATE/1_broken_site.md +++ b/.github/ISSUE_TEMPLATE/1_broken_site.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support -- [ ] I've verified that I'm running youtube-dl version **2019.04.30** +- [ ] I've verified that I'm running youtube-dl version **2019.05.20** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar issues including closed ones @@ -41,7 +41,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.04.30 + [debug] youtube-dl version 2019.05.20 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/2_site_support_request.md b/.github/ISSUE_TEMPLATE/2_site_support_request.md index 79ed338cd..46e143c8a 100644 --- a/.github/ISSUE_TEMPLATE/2_site_support_request.md +++ b/.github/ISSUE_TEMPLATE/2_site_support_request.md @@ -19,7 +19,7 @@ labels: 'site-support-request' - [ ] I'm reporting a new site support request -- [ ] I've verified that I'm running youtube-dl version **2019.04.30** +- [ ] I've verified that I'm running youtube-dl version **2019.05.20** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that none of provided URLs violate any copyrights - [ ] I've searched the bugtracker for similar site support requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/3_site_feature_request.md b/.github/ISSUE_TEMPLATE/3_site_feature_request.md index f0a035c01..bc6c4694b 100644 --- a/.github/ISSUE_TEMPLATE/3_site_feature_request.md +++ b/.github/ISSUE_TEMPLATE/3_site_feature_request.md @@ -18,13 +18,13 @@ title: '' - [ ] I'm reporting a site feature request -- [ ] I've verified that I'm running youtube-dl version **2019.04.30** +- [ ] I've verified that I'm running youtube-dl version **2019.05.20** - [ ] I've searched the bugtracker for similar site feature requests including closed ones diff --git a/.github/ISSUE_TEMPLATE/4_bug_report.md b/.github/ISSUE_TEMPLATE/4_bug_report.md index 55f91d86f..bcc51f986 100644 --- a/.github/ISSUE_TEMPLATE/4_bug_report.md +++ b/.github/ISSUE_TEMPLATE/4_bug_report.md @@ -18,7 +18,7 @@ title: '' - [ ] I'm reporting a broken site support issue -- [ ] I've verified that I'm running youtube-dl version **2019.04.30** +- [ ] I've verified that I'm running youtube-dl version **2019.05.20** - [ ] I've checked that all provided URLs are alive and playable in a browser - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped - [ ] I've searched the bugtracker for similar bug reports including closed ones @@ -43,7 +43,7 @@ Add the `-v` flag to your command line you run youtube-dl with (`youtube-dl -v < [debug] User config: [] [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj'] [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251 - [debug] youtube-dl version 2019.04.30 + [debug] youtube-dl version 2019.05.20 [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2 [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4 [debug] Proxy map: {} diff --git a/.github/ISSUE_TEMPLATE/5_feature_request.md b/.github/ISSUE_TEMPLATE/5_feature_request.md index a521646b4..c8d16960e 100644 --- a/.github/ISSUE_TEMPLATE/5_feature_request.md +++ b/.github/ISSUE_TEMPLATE/5_feature_request.md @@ -19,13 +19,13 @@ labels: 'request' - [ ] I'm reporting a feature request -- [ ] I've verified that I'm running youtube-dl version **2019.04.30** +- [ ] I've verified that I'm running youtube-dl version **2019.05.20** - [ ] I've searched the bugtracker for similar feature requests including closed ones diff --git a/.travis.yml b/.travis.yml index 82e81d078..6d16c2955 100644 --- a/.travis.yml +++ b/.travis.yml @@ -9,6 +9,7 @@ python: - "3.6" - "pypy" - "pypy3" +dist: trusty env: - YTDL_TEST_SET=core - YTDL_TEST_SET=download diff --git a/ChangeLog b/ChangeLog index 3de97cc78..3babb6f48 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,45 @@ +version 2019.05.20 + +Core ++ [extractor/common] Move workaround for applying first Set-Cookie header + into a separate _apply_first_set_cookie_header method + +Extractors +* [safari] Fix authentication (#21090) +* [vk] Use _apply_first_set_cookie_header +* [vrt] Fix extraction (#20527) ++ [canvas] Add support for vrtnieuws and sporza site ids and extract + AES HLS formats ++ [vrv] Extract captions (#19238) +* [tele5] Improve video id extraction +* [tele5] Relax URL regular expression (#21020, #21063) +* [svtplay] Update API URL (#21075) ++ [yahoo:gyao] Add X-User-Agent header to dam proxy requests (#21071) + + +version 2019.05.11 + +Core +* [utils] Transliterate "þ" as "th" (#20897) + +Extractors ++ [cloudflarestream] Add support for videodelivery.net (#21049) ++ [byutv] Add support for DVR videos (#20574, #20676) ++ [gfycat] Add support for URLs with tags (#20696, #20731) ++ [openload] Add support for verystream.com (#20701, #20967) +* [youtube] Use sp field value for signature field name (#18841, #18927, + #21028) ++ [yahoo:gyao] Extend URL regular expression (#21008) +* [youtube] Fix channel id extraction (#20982, #21003) ++ [sky] Add support for news.sky.com (#13055) ++ [youtube:entrylistbase] Retry on 5xx HTTP errors (#20965) ++ [francetvinfo] Extend video id extraction (#20619, #20740) +* [4tube] Update token hosts (#20918) +* [hotstar] Move to API v2 (#20931) +* [fox] Fix API error handling under python 2 (#20925) ++ [redbulltv] Extend URL regular expression (#20922) + + version 2019.04.30 Extractors diff --git a/devscripts/check-porn.py b/devscripts/check-porn.py index 72b2ee422..740f04de0 100644 --- a/devscripts/check-porn.py +++ b/devscripts/check-porn.py @@ -45,12 +45,12 @@ for test in gettestcases(): RESULT = ('.' + domain + '\n' in LIST or '\n' + domain + '\n' in LIST) - if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict'] or - test['info_dict']['age_limit'] != 18): + if RESULT and ('info_dict' not in test or 'age_limit' not in test['info_dict'] + or test['info_dict']['age_limit'] != 18): print('\nPotential missing age_limit check: {0}'.format(test['name'])) - elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict'] and - test['info_dict']['age_limit'] == 18): + elif not RESULT and ('info_dict' in test and 'age_limit' in test['info_dict'] + and test['info_dict']['age_limit'] == 18): print('\nPotential false negative: {0}'.format(test['name'])) else: diff --git a/docs/supportedsites.md b/docs/supportedsites.md index cc95ea981..404a2f0a4 100644 --- a/docs/supportedsites.md +++ b/docs/supportedsites.md @@ -805,6 +805,7 @@ - **ShowRoomLive** - **Sina** - **SkylineWebcams** + - **SkyNews** - **skynewsarabia:article** - **skynewsarabia:video** - **SkySports** @@ -999,6 +1000,7 @@ - **Vbox7** - **VeeHD** - **Veoh** + - **verystream** - **Vessel** - **Vesti**: Вести.Ru - **Vevo** @@ -1069,7 +1071,7 @@ - **VoxMediaVolume** - **vpro**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl - **Vrak** - - **VRT**: deredactie.be, sporza.be, cobra.be and cobra.canvas.be + - **VRT**: VRT NWS, Flanders News, Flandern Info and Sporza - **VrtNU**: VrtNU.be - **vrv** - **vrv:series** diff --git a/setup.cfg b/setup.cfg index af9a554c6..da78a9c47 100644 --- a/setup.cfg +++ b/setup.cfg @@ -3,4 +3,4 @@ universal = True [flake8] exclude = youtube_dl/extractor/__init__.py,devscripts/buildserver.py,devscripts/lazy_load_template.py,devscripts/make_issue_template.py,setup.py,build,.git,venv -ignore = E402,E501,E731,E741 +ignore = E402,E501,E731,E741,W503 diff --git a/test/test_aes.py b/test/test_aes.py index 78a28751b..cc89fb6ab 100644 --- a/test/test_aes.py +++ b/test/test_aes.py @@ -44,16 +44,16 @@ class TestAES(unittest.TestCase): def test_decrypt_text(self): password = intlist_to_bytes(self.key).decode('utf-8') encrypted = base64.b64encode( - intlist_to_bytes(self.iv[:8]) + - b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae' + intlist_to_bytes(self.iv[:8]) + + b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae' ).decode('utf-8') decrypted = (aes_decrypt_text(encrypted, password, 16)) self.assertEqual(decrypted, self.secret_msg) password = intlist_to_bytes(self.key).decode('utf-8') encrypted = base64.b64encode( - intlist_to_bytes(self.iv[:8]) + - b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83' + intlist_to_bytes(self.iv[:8]) + + b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83' ).decode('utf-8') decrypted = (aes_decrypt_text(encrypted, password, 32)) self.assertEqual(decrypted, self.secret_msg) diff --git a/test/test_swfinterp.py b/test/test_swfinterp.py index f1e899819..9f18055e6 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 ca6d832a4..71980b3fc 100644 --- a/test/test_utils.py +++ b/test/test_utils.py @@ -73,6 +73,7 @@ from youtube_dl.utils import ( smuggle_url, str_to_int, strip_jsonp, + strip_or_none, timeconvert, unescapeHTML, unified_strdate, @@ -183,7 +184,7 @@ class TestUtil(unittest.TestCase): self.assertEqual(sanitize_filename( 'ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ', restricted=True), - 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYPssaaaaaaaeceeeeiiiionooooooooeuuuuuypy') + 'AAAAAAAECEEEEIIIIDNOOOOOOOOEUUUUUYTHssaaaaaaaeceeeeiiiionooooooooeuuuuuythy') def test_sanitize_ids(self): self.assertEqual(sanitize_filename('_n_cd26wFpw', is_id=True), '_n_cd26wFpw') @@ -752,6 +753,18 @@ class TestUtil(unittest.TestCase): d = json.loads(stripped) self.assertEqual(d, {'status': 'success'}) + def test_strip_or_none(self): + self.assertEqual(strip_or_none(' abc'), 'abc') + self.assertEqual(strip_or_none('abc '), 'abc') + self.assertEqual(strip_or_none(' abc '), 'abc') + self.assertEqual(strip_or_none('\tabc\t'), 'abc') + self.assertEqual(strip_or_none('\n\tabc\n\t'), 'abc') + self.assertEqual(strip_or_none('abc'), 'abc') + self.assertEqual(strip_or_none(''), '') + self.assertEqual(strip_or_none(None), None) + self.assertEqual(strip_or_none(42), None) + self.assertEqual(strip_or_none([]), None) + def test_uppercase_escape(self): self.assertEqual(uppercase_escape('aä'), 'aä') self.assertEqual(uppercase_escape('\\U0001d550'), '𝕐') diff --git a/youtube_dl/YoutubeDL.py b/youtube_dl/YoutubeDL.py index 57f52f888..3e832fec2 100755 --- a/youtube_dl/YoutubeDL.py +++ b/youtube_dl/YoutubeDL.py @@ -400,9 +400,9 @@ class YoutubeDL(object): else: raise - if (sys.platform != 'win32' and - sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968'] and - not params.get('restrictfilenames', False)): + if (sys.platform != 'win32' + and sys.getfilesystemencoding() in ['ascii', 'ANSI_X3.4-1968'] + and not params.get('restrictfilenames', False)): # Unicode filesystem API will throw errors (#1474, #13027) self.report_warning( 'Assuming --restrict-filenames since file system encoding ' @@ -440,9 +440,9 @@ class YoutubeDL(object): if re.match(r'^-[0-9A-Za-z_-]{10}$', a)] if idxs: correct_argv = ( - ['youtube-dl'] + - [a for i, a in enumerate(argv) if i not in idxs] + - ['--'] + [argv[i] for i in idxs] + ['youtube-dl'] + + [a for i, a in enumerate(argv) if i not in idxs] + + ['--'] + [argv[i] for i in idxs] ) self.report_warning( 'Long argument string detected. ' @@ -850,8 +850,8 @@ class YoutubeDL(object): if result_type in ('url', 'url_transparent'): ie_result['url'] = sanitize_url(ie_result['url']) extract_flat = self.params.get('extract_flat', False) - if ((extract_flat == 'in_playlist' and 'playlist' in extra_info) or - extract_flat is True): + if ((extract_flat == 'in_playlist' and 'playlist' in extra_info) + or extract_flat is True): if self.params.get('forcejson', False): self.to_stdout(json.dumps(ie_result)) return ie_result @@ -1619,9 +1619,9 @@ class YoutubeDL(object): # https://github.com/ytdl-org/youtube-dl/issues/10083). incomplete_formats = ( # All formats are video-only or - all(f.get('vcodec') != 'none' and f.get('acodec') == 'none' for f in formats) or + all(f.get('vcodec') != 'none' and f.get('acodec') == 'none' for f in formats) # all formats are audio-only - all(f.get('vcodec') == 'none' and f.get('acodec') != 'none' for f in formats)) + or all(f.get('vcodec') == 'none' and f.get('acodec') != 'none' for f in formats)) ctx = { 'formats': formats, @@ -1947,8 +1947,8 @@ class YoutubeDL(object): else: assert fixup_policy in ('ignore', 'never') - if (info_dict.get('requested_formats') is None and - info_dict.get('container') == 'm4a_dash'): + if (info_dict.get('requested_formats') is None + and info_dict.get('container') == 'm4a_dash'): if fixup_policy == 'warn': self.report_warning( '%s: writing DASH m4a. ' @@ -1967,9 +1967,9 @@ class YoutubeDL(object): else: assert fixup_policy in ('ignore', 'never') - if (info_dict.get('protocol') == 'm3u8_native' or - info_dict.get('protocol') == 'm3u8' and - self.params.get('hls_prefer_native')): + if (info_dict.get('protocol') == 'm3u8_native' + or info_dict.get('protocol') == 'm3u8' + and self.params.get('hls_prefer_native')): if fixup_policy == 'warn': self.report_warning('%s: malformed AAC bitstream detected.' % ( info_dict['id'])) @@ -1995,10 +1995,10 @@ class YoutubeDL(object): def download(self, url_list): """Download a given list of URLs.""" outtmpl = self.params.get('outtmpl', DEFAULT_OUTTMPL) - if (len(url_list) > 1 and - outtmpl != '-' and - '%' not in outtmpl and - self.params.get('max_downloads') != 1): + if (len(url_list) > 1 + and outtmpl != '-' + and '%' not in outtmpl + and self.params.get('max_downloads') != 1): raise SameFileError(outtmpl) for url in url_list: @@ -2143,8 +2143,8 @@ class YoutubeDL(object): if res: res += ', ' res += '%s container' % fdict['container'] - if (fdict.get('vcodec') is not None and - fdict.get('vcodec') != 'none'): + if (fdict.get('vcodec') is not None + and fdict.get('vcodec') != 'none'): if res: res += ', ' res += fdict['vcodec'] diff --git a/youtube_dl/__init__.py b/youtube_dl/__init__.py index 9d4859bcf..165c975dd 100644 --- a/youtube_dl/__init__.py +++ b/youtube_dl/__init__.py @@ -230,14 +230,14 @@ def _real_main(argv=None): if opts.allsubtitles and not opts.writeautomaticsub: opts.writesubtitles = True - 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' diff --git a/youtube_dl/compat.py b/youtube_dl/compat.py index 7992a23ca..c75ab131b 100644 --- a/youtube_dl/compat.py +++ b/youtube_dl/compat.py @@ -2649,9 +2649,9 @@ else: try: args = shlex.split('中文') - assert (isinstance(args, list) and - isinstance(args[0], compat_str) and - args[0] == '中文') + assert (isinstance(args, list) + and isinstance(args[0], compat_str) + and args[0] == '中文') compat_shlex_split = shlex.split except (AssertionError, UnicodeEncodeError): # Working around shlex issue with unicode strings on some python 2 diff --git a/youtube_dl/downloader/common.py b/youtube_dl/downloader/common.py index 5979833c0..646d7f779 100644 --- a/youtube_dl/downloader/common.py +++ b/youtube_dl/downloader/common.py @@ -330,15 +330,15 @@ 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)) ) if not hasattr(filename, 'write'): continuedl_and_exists = ( - self.params.get('continuedl', True) and - os.path.isfile(encodeFilename(filename)) and - not self.params.get('nopart', False) + self.params.get('continuedl', True) + 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 9b15a0e15..8dd3c2eeb 100644 --- a/youtube_dl/downloader/f4m.py +++ b/youtube_dl/downloader/f4m.py @@ -238,8 +238,8 @@ def write_metadata_tag(stream, metadata): def remove_encrypted_media(media): - return list(filter(lambda e: 'drmAdditionalHeaderId' not in e.attrib and - 'drmAdditionalHeaderSetId' not in e.attrib, + return list(filter(lambda e: 'drmAdditionalHeaderId' not in e.attrib + and 'drmAdditionalHeaderSetId' not in e.attrib, media)) @@ -267,8 +267,8 @@ class F4mFD(FragmentFD): media = doc.findall(_add_ns('media')) if not media: self.report_error('No media found') - for e in (doc.findall(_add_ns('drmAdditionalHeader')) + - doc.findall(_add_ns('drmAdditionalHeaderSet'))): + for e in (doc.findall(_add_ns('drmAdditionalHeader')) + + doc.findall(_add_ns('drmAdditionalHeaderSet'))): # If id attribute is missing it's valid for all media nodes # without drmAdditionalHeaderId or drmAdditionalHeaderSetId attribute if 'id' not in e.attrib: diff --git a/youtube_dl/downloader/fragment.py b/youtube_dl/downloader/fragment.py index 917f6dc01..f2e5733b6 100644 --- a/youtube_dl/downloader/fragment.py +++ b/youtube_dl/downloader/fragment.py @@ -219,8 +219,8 @@ class FragmentFD(FileDownloader): frag_total_bytes = s.get('total_bytes') or 0 if not ctx['live']: estimated_size = ( - (ctx['complete_frags_downloaded_bytes'] + frag_total_bytes) / - (state['fragment_index'] + 1) * total_frags) + (ctx['complete_frags_downloaded_bytes'] + frag_total_bytes) + / (state['fragment_index'] + 1) * total_frags) state['total_bytes_estimate'] = estimated_size if s['status'] == 'finished': diff --git a/youtube_dl/downloader/hls.py b/youtube_dl/downloader/hls.py index 419e73576..b59aad73f 100644 --- a/youtube_dl/downloader/hls.py +++ b/youtube_dl/downloader/hls.py @@ -76,12 +76,12 @@ class HlsFD(FragmentFD): return fd.real_download(filename, info_dict) def is_ad_fragment_start(s): - return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s or - s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad')) + return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s + or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',ad')) def is_ad_fragment_end(s): - return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s or - s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment')) + return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s + or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment')) media_frags = 0 ad_frags = 0 diff --git a/youtube_dl/downloader/http.py b/youtube_dl/downloader/http.py index 08670ee3c..3c72ea18b 100644 --- a/youtube_dl/downloader/http.py +++ b/youtube_dl/downloader/http.py @@ -46,8 +46,8 @@ class HttpFD(FileDownloader): is_test = self.params.get('test', False) chunk_size = self._TEST_FILE_SIZE if is_test else ( - info_dict.get('downloader_options', {}).get('http_chunk_size') or - self.params.get('http_chunk_size') or 0) + info_dict.get('downloader_options', {}).get('http_chunk_size') + or self.params.get('http_chunk_size') or 0) ctx.open_mode = 'wb' ctx.resume_len = 0 @@ -123,11 +123,11 @@ class HttpFD(FileDownloader): content_len = int_or_none(content_range_m.group(3)) accept_content_len = ( # Non-chunked download - not ctx.chunk_size or + not ctx.chunk_size # Chunked download and requested piece or # its part is promised to be served - content_range_end == range_end or - content_len < range_end) + or content_range_end == range_end + or content_len < range_end) if accept_content_len: ctx.data_len = content_len return @@ -152,8 +152,8 @@ class HttpFD(FileDownloader): raise else: # Examine the reported length - if (content_length is not None and - (ctx.resume_len - 100 < int(content_length) < ctx.resume_len + 100)): + if (content_length is not None + and (ctx.resume_len - 100 < int(content_length) < ctx.resume_len + 100)): # The file had already been fully downloaded. # Explanation to the above condition: in issue #175 it was revealed that # YouTube sometimes adds or removes a few bytes from the end of the file, diff --git a/youtube_dl/extractor/addanime.py b/youtube_dl/extractor/addanime.py index 9f8a71262..5e7c0724e 100644 --- a/youtube_dl/extractor/addanime.py +++ b/youtube_dl/extractor/addanime.py @@ -59,9 +59,9 @@ class AddAnimeIE(InfoExtractor): parsed_url = compat_urllib_parse_urlparse(url) av_val = av_res + len(parsed_url.netloc) confirm_url = ( - parsed_url.scheme + '://' + parsed_url.netloc + - action + '?' + - compat_urllib_parse_urlencode({ + parsed_url.scheme + '://' + parsed_url.netloc + + action + '?' + + compat_urllib_parse_urlencode({ 'jschl_vc': vc, 'jschl_answer': compat_str(av_val)})) self._download_webpage( confirm_url, video_id, diff --git a/youtube_dl/extractor/bitchute.py b/youtube_dl/extractor/bitchute.py index 4f39424f5..1d69dafbd 100644 --- a/youtube_dl/extractor/bitchute.py +++ b/youtube_dl/extractor/bitchute.py @@ -65,8 +65,9 @@ class BitChuteIE(InfoExtractor): webpage, default=None) or self._html_search_meta( 'twitter:image:src', webpage, 'thumbnail') uploader = self._html_search_regex( - r'(?s)]+\bclass=["\']video-author[^>]+>(.+?)

', webpage, - 'uploader', fatal=False) + (r'(?s)
]+\bclass=["\']name[^>]+>(.+?)

', + r'(?s)]+\bclass=["\']video-author[^>]+>(.+?)

'), + webpage, 'uploader', fatal=False) return { 'id': video_id, diff --git a/youtube_dl/extractor/blinkx.py b/youtube_dl/extractor/blinkx.py index 3b8eabe8f..db5e12b21 100644 --- a/youtube_dl/extractor/blinkx.py +++ b/youtube_dl/extractor/blinkx.py @@ -32,8 +32,8 @@ class BlinkxIE(InfoExtractor): video_id = self._match_id(url) display_id = video_id[:8] - api_url = ('https://apib4.blinkx.com/api.php?action=play_video&' + - 'video=%s' % video_id) + api_url = ('https://apib4.blinkx.com/api.php?action=play_video&' + + 'video=%s' % video_id) data_json = self._download_webpage(api_url, display_id) data = json.loads(data_json)['api']['results'][0] duration = None diff --git a/youtube_dl/extractor/byutv.py b/youtube_dl/extractor/byutv.py index 4bf4efe1f..562c83af9 100644 --- a/youtube_dl/extractor/byutv.py +++ b/youtube_dl/extractor/byutv.py @@ -3,11 +3,13 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..utils import parse_duration class BYUtvIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?byutv\.org/(?:watch|player)/(?!event/)(?P[0-9a-f-]+)(?:/(?P[^/?#&]+))?' _TESTS = [{ + # ooyalaVOD 'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5', 'info_dict': { 'id': 'ZvanRocTpW-G5_yZFeltTAMv6jxOU9KH', @@ -22,6 +24,20 @@ class BYUtvIE(InfoExtractor): 'skip_download': True, }, 'add_ie': ['Ooyala'], + }, { + # dvr + 'url': 'https://www.byutv.org/player/8f1dab9b-b243-47c8-b525-3e2d021a3451/byu-softball-pacific-vs-byu-41219---game-2', + 'info_dict': { + 'id': '8f1dab9b-b243-47c8-b525-3e2d021a3451', + 'display_id': 'byu-softball-pacific-vs-byu-41219---game-2', + 'ext': 'mp4', + 'title': 'Pacific vs. BYU (4/12/19)', + 'description': 'md5:1ac7b57cb9a78015910a4834790ce1f3', + 'duration': 11645, + }, + 'params': { + 'skip_download': True + }, }, { 'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d', 'only_matching': True, @@ -35,24 +51,42 @@ class BYUtvIE(InfoExtractor): video_id = mobj.group('id') display_id = mobj.group('display_id') or video_id - ep = self._download_json( - 'https://api.byutv.org/api3/catalog/getvideosforcontent', video_id, - query={ + info = self._download_json( + 'https://api.byutv.org/api3/catalog/getvideosforcontent', + display_id, query={ 'contentid': video_id, 'channel': 'byutv', 'x-byutv-context': 'web$US', }, headers={ 'x-byutv-context': 'web$US', 'x-byutv-platformkey': 'xsaaw9c7y5', - })['ooyalaVOD'] + }) + ep = info.get('ooyalaVOD') + if ep: + return { + '_type': 'url_transparent', + 'ie_key': 'Ooyala', + 'url': 'ooyala:%s' % ep['providerId'], + 'id': video_id, + 'display_id': display_id, + 'title': ep.get('title'), + 'description': ep.get('description'), + 'thumbnail': ep.get('imageThumbnail'), + } + + ep = info['dvr'] + title = ep['title'] + formats = self._extract_m3u8_formats( + ep['videoUrl'], video_id, 'mp4', entry_protocol='m3u8_native', + m3u8_id='hls') + self._sort_formats(formats) return { - '_type': 'url_transparent', - 'ie_key': 'Ooyala', - 'url': 'ooyala:%s' % ep['providerId'], 'id': video_id, 'display_id': display_id, - 'title': ep.get('title'), + 'title': title, 'description': ep.get('description'), 'thumbnail': ep.get('imageThumbnail'), + 'duration': parse_duration(ep.get('length')), + 'formats': formats, } diff --git a/youtube_dl/extractor/canvas.py b/youtube_dl/extractor/canvas.py index 174fd9e2b..c506bc5dd 100644 --- a/youtube_dl/extractor/canvas.py +++ b/youtube_dl/extractor/canvas.py @@ -17,7 +17,7 @@ from ..utils import ( class CanvasIE(InfoExtractor): - _VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?Pcanvas|een|ketnet|vrtvideo)/assets/(?P[^/?#&]+)' + _VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?Pcanvas|een|ketnet|vrt(?:video|nieuws)|sporza)/assets/(?P[^/?#&]+)' _TESTS = [{ 'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475', 'md5': '90139b746a0a9bd7bb631283f6e2a64e', @@ -35,6 +35,10 @@ class CanvasIE(InfoExtractor): 'url': 'https://mediazone.vrt.be/api/v1/canvas/assets/mz-ast-5e5f90b6-2d72-4c40-82c2-e134f884e93e', 'only_matching': True, }] + _HLS_ENTRY_PROTOCOLS_MAP = { + 'HLS': 'm3u8_native', + 'HLS_AES': 'm3u8', + } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -52,9 +56,9 @@ class CanvasIE(InfoExtractor): format_url, format_type = target.get('url'), target.get('type') if not format_url or not format_type: continue - if format_type == 'HLS': + if format_type in self._HLS_ENTRY_PROTOCOLS_MAP: formats.extend(self._extract_m3u8_formats( - format_url, video_id, 'mp4', entry_protocol='m3u8_native', + format_url, video_id, 'mp4', self._HLS_ENTRY_PROTOCOLS_MAP[format_type], m3u8_id=format_type, fatal=False)) elif format_type == 'HDS': formats.extend(self._extract_f4m_formats( diff --git a/youtube_dl/extractor/cloudflarestream.py b/youtube_dl/extractor/cloudflarestream.py index e6d92cca2..8ff2c6531 100644 --- a/youtube_dl/extractor/cloudflarestream.py +++ b/youtube_dl/extractor/cloudflarestream.py @@ -10,8 +10,8 @@ class CloudflareStreamIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// (?: - (?:watch\.)?cloudflarestream\.com/| - embed\.cloudflarestream\.com/embed/[^/]+\.js\?.*?\bvideo= + (?:watch\.)?(?:cloudflarestream\.com|videodelivery\.net)/| + embed\.(?:cloudflarestream\.com|videodelivery\.net)/embed/[^/]+\.js\?.*?\bvideo= ) (?P[\da-f]+) ''' @@ -31,6 +31,9 @@ class CloudflareStreamIE(InfoExtractor): }, { 'url': 'https://cloudflarestream.com/31c9291ab41fac05471db4e73aa11717/manifest/video.mpd', 'only_matching': True, + }, { + 'url': 'https://embed.videodelivery.net/embed/r4xu.fla9.latest.js?video=81d80727f3022488598f68d323c1ad5e', + 'only_matching': True, }] @staticmethod @@ -38,7 +41,7 @@ class CloudflareStreamIE(InfoExtractor): return [ mobj.group('url') for mobj in re.finditer( - r']+\bsrc=(["\'])(?P(?:https?:)?//embed\.cloudflarestream\.com/embed/[^/]+\.js\?.*?\bvideo=[\da-f]+?.*?)\1', + r']+\bsrc=(["\'])(?P(?:https?:)?//embed\.(?:cloudflarestream\.com|videodelivery\.net)/embed/[^/]+\.js\?.*?\bvideo=[\da-f]+?.*?)\1', webpage)] def _real_extract(self, url): diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index 59ad455c1..9c3e9eec6 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -67,6 +67,7 @@ from ..utils import ( sanitized_Request, sanitize_filename, str_or_none, + strip_or_none, unescapeHTML, unified_strdate, unified_timestamp, @@ -117,7 +118,7 @@ class InfoExtractor(object): unfragmented media) - URL of the MPD manifest or base URL representing the media if MPD manifest - is parsed froma string (in case of + is parsed from a string (in case of fragmented media) for MSS - URL of the ISM manifest. * manifest_url @@ -542,11 +543,11 @@ class InfoExtractor(object): raise ExtractorError('An extractor error has occurred.', cause=e) def __maybe_fake_ip_and_retry(self, countries): - if (not self._downloader.params.get('geo_bypass_country', None) and - self._GEO_BYPASS and - self._downloader.params.get('geo_bypass', True) and - not self._x_forwarded_for_ip and - countries): + if (not self._downloader.params.get('geo_bypass_country', None) + and self._GEO_BYPASS + and self._downloader.params.get('geo_bypass', True) + and not self._x_forwarded_for_ip + and countries): country_code = random.choice(countries) self._x_forwarded_for_ip = GeoUtils.random_ipv4(country_code) if self._x_forwarded_for_ip: @@ -682,8 +683,8 @@ class InfoExtractor(object): def __check_blocked(self, content): first_block = content[:512] - if ('Access to this site is blocked' in content and - 'Websense' in first_block): + if ('Access to this site is blocked' in content + and 'Websense' in first_block): msg = 'Access to this webpage has been blocked by Websense filtering software in your network.' blocked_iframe = self._html_search_regex( r'