Hello community, here is the log from the commit of package youtube-dl for openSUSE:Factory checked in at 2019-06-01 09:50:21 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Comparing /work/SRC/openSUSE:Factory/youtube-dl (Old) and /work/SRC/openSUSE:Factory/.youtube-dl.new.5148 (New) ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Package is "youtube-dl" Sat Jun 1 09:50:21 2019 rev:106 rq:706059 version:2019.05.20 Changes: -------- --- /work/SRC/openSUSE:Factory/youtube-dl/youtube-dl.changes 2019-05-12 11:46:13.172126152 +0200 +++ /work/SRC/openSUSE:Factory/.youtube-dl.new.5148/youtube-dl.changes 2019-06-01 09:50:25.707305263 +0200 @@ -1,0 +2,6 @@ +Tue May 21 07:54:10 UTC 2019 - Jan Engelhardt <[email protected]> + +- Update to new upstream release 2019.05.20 + * svtplay: Update API URL + +------------------------------------------------------------------- Old: ---- youtube-dl-2019.05.11.tar.gz youtube-dl-2019.05.11.tar.gz.sig New: ---- youtube-dl-2019.05.20.tar.gz youtube-dl-2019.05.20.tar.gz.sig ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ Other differences: ------------------ ++++++ python-youtube-dl.spec ++++++ --- /var/tmp/diff_new_pack.LiALoJ/_old 2019-06-01 09:50:26.691304927 +0200 +++ /var/tmp/diff_new_pack.LiALoJ/_new 2019-06-01 09:50:26.715304919 +0200 @@ -19,7 +19,7 @@ %define modname youtube-dl %{?!python_module:%define python_module() python-%{**} python3-%{**}} Name: python-youtube-dl -Version: 2019.05.11 +Version: 2019.05.20 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.LiALoJ/_old 2019-06-01 09:50:26.775304898 +0200 +++ /var/tmp/diff_new_pack.LiALoJ/_new 2019-06-01 09:50:26.775304898 +0200 @@ -17,7 +17,7 @@ Name: youtube-dl -Version: 2019.05.11 +Version: 2019.05.20 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-2019.05.11.tar.gz -> youtube-dl-2019.05.20.tar.gz ++++++ diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/youtube-dl/ChangeLog new/youtube-dl/ChangeLog --- old/youtube-dl/ChangeLog 2019-05-11 01:07:24.000000000 +0200 +++ new/youtube-dl/ChangeLog 2019-05-20 18:29:46.000000000 +0200 @@ -1,3 +1,22 @@ +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 diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/youtube-dl/docs/supportedsites.md new/youtube-dl/docs/supportedsites.md --- old/youtube-dl/docs/supportedsites.md 2019-05-11 01:07:28.000000000 +0200 +++ new/youtube-dl/docs/supportedsites.md 2019-05-20 18:29:49.000000000 +0200 @@ -1071,7 +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** 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/canvas.py new/youtube-dl/youtube_dl/extractor/canvas.py --- old/youtube-dl/youtube_dl/extractor/canvas.py 2019-05-11 01:06:11.000000000 +0200 +++ new/youtube-dl/youtube_dl/extractor/canvas.py 2019-05-20 18:25:31.000000000 +0200 @@ -17,7 +17,7 @@ class CanvasIE(InfoExtractor): - _VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrtvideo)/assets/(?P<id>[^/?#&]+)' + _VALID_URL = r'https?://mediazone\.vrt\.be/api/v1/(?P<site_id>canvas|een|ketnet|vrt(?:video|nieuws)|sporza)/assets/(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'https://mediazone.vrt.be/api/v1/ketnet/assets/md-ast-4ac54990-ce66-4d00-a8ca-9eac86f4c475', 'md5': '90139b746a0a9bd7bb631283f6e2a64e', @@ -35,6 +35,10 @@ '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 @@ 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 -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/common.py new/youtube-dl/youtube_dl/extractor/common.py --- old/youtube-dl/youtube_dl/extractor/common.py 2019-05-11 01:06:22.000000000 +0200 +++ new/youtube-dl/youtube_dl/extractor/common.py 2019-05-20 18:25:31.000000000 +0200 @@ -2817,6 +2817,33 @@ self._downloader.cookiejar.add_cookie_header(req) return compat_cookies.SimpleCookie(req.get_header('Cookie')) + def _apply_first_set_cookie_header(self, url_handle, cookie): + """ + Apply first Set-Cookie header instead of the last. Experimental. + + Some sites (e.g. [1-3]) may serve two cookies under the same name + in Set-Cookie header and expect the first (old) one to be set rather + than second (new). However, as of RFC6265 the newer one cookie + should be set into cookie store what actually happens. + We will workaround this issue by resetting the cookie to + the first one manually. + 1. https://new.vk.com/ + 2. https://github.com/ytdl-org/youtube-dl/issues/9841#issuecomment-227871201 + 3. https://learning.oreilly.com/ + """ + for header, cookies in url_handle.headers.items(): + if header.lower() != 'set-cookie': + continue + if sys.version_info[0] >= 3: + cookies = cookies.encode('iso-8859-1') + cookies = cookies.decode('utf-8') + cookie_value = re.search( + r'%s=(.+?);.*?\b[Dd]omain=(.+?)(?:[,;]|$)' % cookie, cookies) + if cookie_value: + value, domain = cookie_value.groups() + self._set_cookie(domain, cookie, value) + break + def get_testcases(self, include_onlymatching=False): t = getattr(self, '_TEST', None) if t: diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/safari.py new/youtube-dl/youtube_dl/extractor/safari.py --- old/youtube-dl/youtube_dl/extractor/safari.py 2019-05-11 01:06:13.000000000 +0200 +++ new/youtube-dl/youtube_dl/extractor/safari.py 2019-05-20 18:25:31.000000000 +0200 @@ -1,15 +1,18 @@ # coding: utf-8 from __future__ import unicode_literals +import json import re from .common import InfoExtractor +from ..compat import ( + compat_parse_qs, + compat_str, + compat_urlparse, +) from ..utils import ( ExtractorError, - sanitized_Request, - std_headers, - urlencode_postdata, update_url_query, ) @@ -31,44 +34,52 @@ if username is None: return - headers = std_headers.copy() - if 'Referer' not in headers: - headers['Referer'] = self._LOGIN_URL - - login_page = self._download_webpage( - self._LOGIN_URL, None, 'Downloading login form', headers=headers) - - def is_logged(webpage): - return any(re.search(p, webpage) for p in ( - r'href=["\']/accounts/logout/', r'>Sign Out<')) + _, urlh = self._download_webpage_handle( + 'https://learning.oreilly.com/accounts/login-check/', None, + 'Downloading login page') + + def is_logged(urlh): + return 'learning.oreilly.com/home/' in compat_str(urlh.geturl()) - if is_logged(login_page): + if is_logged(urlh): self.LOGGED_IN = True return - csrf = self._html_search_regex( - r"name='csrfmiddlewaretoken'\s+value='([^']+)'", - login_page, 'csrf token') - - login_form = { - 'csrfmiddlewaretoken': csrf, - 'email': username, - 'password1': password, - 'login': 'Sign In', - 'next': '', - } + redirect_url = compat_str(urlh.geturl()) + parsed_url = compat_urlparse.urlparse(redirect_url) + qs = compat_parse_qs(parsed_url.query) + next_uri = compat_urlparse.urljoin( + 'https://api.oreilly.com', qs['next'][0]) + + auth, urlh = self._download_json_handle( + 'https://www.oreilly.com/member/auth/login/', None, 'Logging in', + data=json.dumps({ + 'email': username, + 'password': password, + 'redirect_uri': next_uri, + }).encode(), headers={ + 'Content-Type': 'application/json', + 'Referer': redirect_url, + }, expected_status=400) + + credentials = auth.get('credentials') + if (not auth.get('logged_in') and not auth.get('redirect_uri') + and credentials): + raise ExtractorError( + 'Unable to login: %s' % credentials, expected=True) - request = sanitized_Request( - self._LOGIN_URL, urlencode_postdata(login_form), headers=headers) - login_page = self._download_webpage( - request, None, 'Logging in') + # oreilly serves two same groot_sessionid cookies in Set-Cookie header + # and expects first one to be actually set + self._apply_first_set_cookie_header(urlh, 'groot_sessionid') - if not is_logged(login_page): - raise ExtractorError( - 'Login failed; make sure your credentials are correct and try again.', - expected=True) + _, urlh = self._download_webpage_handle( + auth.get('redirect_uri') or next_uri, None, 'Completing login',) + + if is_logged(urlh): + self.LOGGED_IN = True + return - self.LOGGED_IN = True + raise ExtractorError('Unable to log in') class SafariIE(SafariBaseIE): @@ -76,7 +87,7 @@ IE_DESC = 'safaribooksonline.com online video' _VALID_URL = r'''(?x) https?:// - (?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/ + (?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/ (?: library/view/[^/]+/(?P<course_id>[^/]+)/(?P<part>[^/?\#&]+)\.html| videos/[^/]+/[^/]+/(?P<reference_id>[^-]+-[^/?\#&]+) @@ -107,6 +118,9 @@ }, { 'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838/9780133392838-00_SeriesIntro', 'only_matching': True, + }, { + 'url': 'https://www.oreilly.com/library/view/hadoop-fundamentals-livelessons/9780133392838/00_SeriesIntro.html', + 'only_matching': True, }] _PARTNER_ID = '1926081' @@ -163,7 +177,7 @@ class SafariApiIE(SafariBaseIE): IE_NAME = 'safari:api' - _VALID_URL = r'https?://(?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html' + _VALID_URL = r'https?://(?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/api/v1/book/(?P<course_id>[^/]+)/chapter(?:-content)?/(?P<part>[^/?#&]+)\.html' _TESTS = [{ 'url': 'https://www.safaribooksonline.com/api/v1/book/9780133392838/chapter/part00.html', @@ -188,7 +202,7 @@ _VALID_URL = r'''(?x) https?:// (?: - (?:www\.)?(?:safaribooksonline|learning\.oreilly)\.com/ + (?:www\.)?(?:safaribooksonline|(?:learning\.)?oreilly)\.com/ (?: library/view/[^/]+| api/v1/book| @@ -219,6 +233,9 @@ }, { 'url': 'https://learning.oreilly.com/videos/hadoop-fundamentals-livelessons/9780133392838', 'only_matching': True, + }, { + 'url': 'https://www.oreilly.com/library/view/hadoop-fundamentals-livelessons/9780133392838/', + 'only_matching': True, }] @classmethod diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/svt.py new/youtube-dl/youtube_dl/extractor/svt.py --- old/youtube-dl/youtube_dl/extractor/svt.py 2019-05-11 01:06:13.000000000 +0200 +++ new/youtube-dl/youtube_dl/extractor/svt.py 2019-05-20 18:25:31.000000000 +0200 @@ -185,7 +185,7 @@ def _extract_by_video_id(self, video_id, webpage=None): data = self._download_json( - 'https://api.svt.se/video/%s' % video_id, + 'https://api.svt.se/videoplayer-api/video/%s' % video_id, video_id, headers=self.geo_verification_headers()) info_dict = self._extract_video(data, video_id) if not info_dict.get('title'): diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/tele5.py new/youtube-dl/youtube_dl/extractor/tele5.py --- old/youtube-dl/youtube_dl/extractor/tele5.py 2019-05-11 01:06:13.000000000 +0200 +++ new/youtube-dl/youtube_dl/extractor/tele5.py 2019-05-20 18:25:31.000000000 +0200 @@ -7,7 +7,7 @@ class Tele5IE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:mediathek|tv)/(?P<id>[^?#&]+)' + _VALID_URL = r'https?://(?:www\.)?tele5\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)' _TESTS = [{ 'url': 'https://www.tele5.de/mediathek/filme-online/videos?vid=1549416', 'info_dict': { @@ -21,10 +21,22 @@ 'skip_download': True, }, }, { - 'url': 'https://www.tele5.de/tv/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191', + 'url': 'https://www.tele5.de/kalkofes-mattscheibe/video-clips/politik-und-gesellschaft?ve_id=1551191', 'only_matching': True, }, { - 'url': 'https://www.tele5.de/tv/dark-matter/videos', + 'url': 'https://www.tele5.de/video-clip/?ve_id=1609440', + 'only_matching': True, + }, { + 'url': 'https://www.tele5.de/filme/schlefaz-dragon-crusaders/', + 'only_matching': True, + }, { + 'url': 'https://www.tele5.de/filme/making-of/avengers-endgame/', + 'only_matching': True, + }, { + 'url': 'https://www.tele5.de/star-trek/raumschiff-voyager/ganze-folge/das-vinculum/', + 'only_matching': True, + }, { + 'url': 'https://www.tele5.de/anders-ist-sevda/', 'only_matching': True, }] @@ -36,8 +48,9 @@ display_id = self._match_id(url) webpage = self._download_webpage(url, display_id) video_id = self._html_search_regex( - r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)', - webpage, 'video id') + (r'id\s*=\s*["\']video-player["\'][^>]+data-id\s*=\s*["\'](\d+)', + r'\s+id\s*=\s*["\']player_(\d{6,})', + r'\bdata-id\s*=\s*["\'](\d{6,})'), webpage, 'video id') return self.url_result( 'https://api.nexx.cloud/v3/759/videos/byid/%s' % video_id, diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/vk.py new/youtube-dl/youtube_dl/extractor/vk.py --- old/youtube-dl/youtube_dl/extractor/vk.py 2019-05-11 01:06:22.000000000 +0200 +++ new/youtube-dl/youtube_dl/extractor/vk.py 2019-05-20 18:25:31.000000000 +0200 @@ -3,7 +3,6 @@ import collections import re -import sys from .common import InfoExtractor from ..compat import compat_urlparse @@ -45,24 +44,9 @@ 'pass': password.encode('cp1251'), }) - # https://new.vk.com/ serves two same remixlhk cookies in Set-Cookie header - # and expects the first one to be set rather than second (see - # https://github.com/ytdl-org/youtube-dl/issues/9841#issuecomment-227871201). - # As of RFC6265 the newer one cookie should be set into cookie store - # what actually happens. - # We will workaround this VK issue by resetting the remixlhk cookie to - # the first one manually. - for header, cookies in url_handle.headers.items(): - if header.lower() != 'set-cookie': - continue - if sys.version_info[0] >= 3: - cookies = cookies.encode('iso-8859-1') - cookies = cookies.decode('utf-8') - remixlhk = re.search(r'remixlhk=(.+?);.*?\bdomain=(.+?)(?:[,;]|$)', cookies) - if remixlhk: - value, domain = remixlhk.groups() - self._set_cookie(domain, 'remixlhk', value) - break + # vk serves two same remixlhk cookies in Set-Cookie header and expects + # first one to be actually set + self._apply_first_set_cookie_header(url_handle, 'remixlhk') login_page = self._download_webpage( 'https://login.vk.com/?act=login', None, diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/vrt.py new/youtube-dl/youtube_dl/extractor/vrt.py --- old/youtube-dl/youtube_dl/extractor/vrt.py 2019-05-11 01:06:14.000000000 +0200 +++ new/youtube-dl/youtube_dl/extractor/vrt.py 2019-05-20 18:25:31.000000000 +0200 @@ -5,150 +5,83 @@ from .common import InfoExtractor from ..utils import ( + extract_attributes, float_or_none, + get_element_by_class, + strip_or_none, + unified_timestamp, ) class VRTIE(InfoExtractor): - IE_DESC = 'deredactie.be, sporza.be, cobra.be and cobra.canvas.be' - _VALID_URL = r'https?://(?:deredactie|sporza|cobra(?:\.canvas)?)\.be/cm/(?:[^/]+/)+(?P<id>[^/]+)/*' - _TESTS = [ - # deredactie.be - { - 'url': 'http://deredactie.be/cm/vrtnieuws/videozone/programmas/journaal/EP_141025_JOL', - 'md5': '4cebde1eb60a53782d4f3992cbd46ec8', - 'info_dict': { - 'id': '2129880', - 'ext': 'flv', - 'title': 'Het journaal L - 25/10/14', - 'description': None, - 'timestamp': 1414271750.949, - 'upload_date': '20141025', - 'duration': 929, - }, - 'skip': 'HTTP Error 404: Not Found', + IE_DESC = 'VRT NWS, Flanders News, Flandern Info and Sporza' + _VALID_URL = r'https?://(?:www\.)?(?P<site>vrt\.be/vrtnws|sporza\.be)/[a-z]{2}/\d{4}/\d{2}/\d{2}/(?P<id>[^/?&#]+)' + _TESTS = [{ + 'url': 'https://www.vrt.be/vrtnws/nl/2019/05/15/beelden-van-binnenkant-notre-dame-een-maand-na-de-brand/', + 'md5': 'e1663accf5cf13f375f3cd0d10476669', + 'info_dict': { + 'id': 'pbs-pub-7855fc7b-1448-49bc-b073-316cb60caa71$vid-2ca50305-c38a-4762-9890-65cbd098b7bd', + 'ext': 'mp4', + 'title': 'Beelden van binnenkant Notre-Dame, één maand na de brand', + 'description': 'Op maandagavond 15 april ging een deel van het dakgebinte van de Parijse kathedraal in vlammen op.', + 'timestamp': 1557924660, + 'upload_date': '20190515', + 'duration': 31.2, }, - # sporza.be - { - 'url': 'http://sporza.be/cm/sporza/videozone/programmas/extratime/EP_141020_Extra_time', - 'md5': '11f53088da9bf8e7cfc42456697953ff', - 'info_dict': { - 'id': '2124639', - 'ext': 'flv', - 'title': 'Bekijk Extra Time van 20 oktober', - 'description': 'md5:83ac5415a4f1816c6a93f8138aef2426', - 'timestamp': 1413835980.560, - 'upload_date': '20141020', - 'duration': 3238, - }, - 'skip': 'HTTP Error 404: Not Found', + }, { + 'url': 'https://sporza.be/nl/2019/05/15/de-belgian-cats-zijn-klaar-voor-het-ek/', + 'md5': '910bba927566e9ab992278f647eb4b75', + 'info_dict': { + 'id': 'pbs-pub-f2c86a46-8138-413a-a4b9-a0015a16ce2c$vid-1f112b31-e58e-4379-908d-aca6d80f8818', + 'ext': 'mp4', + 'title': 'De Belgian Cats zijn klaar voor het EK mét Ann Wauters', + 'timestamp': 1557923760, + 'upload_date': '20190515', + 'duration': 115.17, }, - # cobra.be - { - 'url': 'http://cobra.be/cm/cobra/videozone/rubriek/film-videozone/141022-mv-ellis-cafecorsari', - 'md5': '78a2b060a5083c4f055449a72477409d', - 'info_dict': { - 'id': '2126050', - 'ext': 'flv', - 'title': 'Bret Easton Ellis in Café Corsari', - 'description': 'md5:f699986e823f32fd6036c1855a724ee9', - 'timestamp': 1413967500.494, - 'upload_date': '20141022', - 'duration': 661, - }, - 'skip': 'HTTP Error 404: Not Found', - }, - { - # YouTube video - 'url': 'http://deredactie.be/cm/vrtnieuws/videozone/nieuws/cultuurenmedia/1.2622957', - 'md5': 'b8b93da1df1cea6c8556255a796b7d61', - 'info_dict': { - 'id': 'Wji-BZ0oCwg', - 'ext': 'mp4', - 'title': 'ROGUE ONE: A STAR WARS STORY Official Teaser Trailer', - 'description': 'md5:8e468944dce15567a786a67f74262583', - 'uploader': 'Star Wars', - 'uploader_id': 'starwars', - 'upload_date': '20160407', - }, - 'add_ie': ['Youtube'], - }, - { - 'url': 'http://cobra.canvas.be/cm/cobra/videozone/rubriek/film-videozone/1.2377055', - 'info_dict': { - 'id': '2377055', - 'ext': 'mp4', - 'title': 'Cafe Derby', - 'description': 'Lenny Van Wesemael debuteert met de langspeelfilm Café Derby. Een waar gebeurd maar ook verzonnen verhaal.', - 'upload_date': '20150626', - 'timestamp': 1435305240.769, - }, - 'params': { - # m3u8 download - 'skip_download': True, - } - } - ] + }, { + 'url': 'https://www.vrt.be/vrtnws/en/2019/05/15/belgium_s-eurovision-entry-falls-at-the-first-hurdle/', + 'only_matching': True, + }, { + 'url': 'https://www.vrt.be/vrtnws/de/2019/05/15/aus-fuer-eliott-im-halbfinale-des-eurosongfestivals/', + 'only_matching': True, + }] + _CLIENT_MAP = { + 'vrt.be/vrtnws': 'vrtnieuws', + 'sporza.be': 'sporza', + } def _real_extract(self, url): - video_id = self._match_id(url) - - webpage = self._download_webpage(url, video_id) - - video_id = self._search_regex( - r'data-video-id="([^"]+)_[^"]+"', webpage, 'video id', fatal=False) - - src = self._search_regex( - r'data-video-src="([^"]+)"', webpage, 'video src', default=None) - - video_type = self._search_regex( - r'data-video-type="([^"]+)"', webpage, 'video type', default=None) - - if video_type == 'YouTubeVideo': - return self.url_result(src, 'Youtube') - - formats = [] - - mobj = re.search( - r'data-video-iphone-server="(?P<server>[^"]+)"\s+data-video-iphone-path="(?P<path>[^"]+)"', - webpage) - if mobj: - formats.extend(self._extract_m3u8_formats( - '%s/%s' % (mobj.group('server'), mobj.group('path')), - video_id, 'mp4', m3u8_id='hls', fatal=False)) - - if src: - formats = self._extract_wowza_formats(src, video_id) - if 'data-video-geoblocking="true"' not in webpage: - for f in formats: - if f['url'].startswith('rtsp://'): - http_format = f.copy() - http_format.update({ - 'url': f['url'].replace('rtsp://', 'http://').replace('vod.', 'download.').replace('/_definst_/', '/').replace('mp4:', ''), - 'format_id': f['format_id'].replace('rtsp', 'http'), - 'protocol': 'http', - }) - formats.append(http_format) - - if not formats and 'data-video-geoblocking="true"' in webpage: - self.raise_geo_restricted('This video is only available in Belgium') - - self._sort_formats(formats) - - title = self._og_search_title(webpage) - description = self._og_search_description(webpage, default=None) - thumbnail = self._og_search_thumbnail(webpage) - timestamp = float_or_none(self._search_regex( - r'data-video-sitestat-pubdate="(\d+)"', webpage, 'timestamp', fatal=False), 1000) - duration = float_or_none(self._search_regex( - r'data-video-duration="(\d+)"', webpage, 'duration', fatal=False), 1000) + site, display_id = re.match(self._VALID_URL, url).groups() + webpage = self._download_webpage(url, display_id) + attrs = extract_attributes(self._search_regex( + r'(<[^>]+class="vrtvideo"[^>]*>)', webpage, 'vrt video')) + + asset_id = attrs['data-videoid'] + publication_id = attrs.get('data-publicationid') + if publication_id: + asset_id = publication_id + '$' + asset_id + client = attrs.get('data-client') or self._CLIENT_MAP[site] + + title = strip_or_none(get_element_by_class( + 'vrt-title', webpage) or self._html_search_meta( + ['og:title', 'twitter:title', 'name'], webpage)) + description = self._html_search_meta( + ['og:description', 'twitter:description', 'description'], webpage) + if description == '…': + description = None + timestamp = unified_timestamp(self._html_search_meta( + 'article:published_time', webpage)) return { - 'id': video_id, + '_type': 'url_transparent', + 'id': asset_id, + 'display_id': display_id, 'title': title, 'description': description, - 'thumbnail': thumbnail, + 'thumbnail': attrs.get('data-posterimage'), 'timestamp': timestamp, - 'duration': duration, - 'formats': formats, + 'duration': float_or_none(attrs.get('data-duration'), 1000), + 'url': 'https://mediazone.vrt.be/api/v1/%s/assets/%s' % (client, asset_id), + 'ie_key': 'Canvas', } diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/vrv.py new/youtube-dl/youtube_dl/extractor/vrv.py --- old/youtube-dl/youtube_dl/extractor/vrv.py 2019-05-11 01:06:14.000000000 +0200 +++ new/youtube-dl/youtube_dl/extractor/vrv.py 2019-05-20 18:25:31.000000000 +0200 @@ -198,14 +198,15 @@ self._sort_formats(formats) subtitles = {} - for subtitle in streams_json.get('subtitles', {}).values(): - subtitle_url = subtitle.get('url') - if not subtitle_url: - continue - subtitles.setdefault(subtitle.get('locale', 'en-US'), []).append({ - 'url': subtitle_url, - 'ext': subtitle.get('format', 'ass'), - }) + for k in ('captions', 'subtitles'): + for subtitle in streams_json.get(k, {}).values(): + subtitle_url = subtitle.get('url') + if not subtitle_url: + continue + subtitles.setdefault(subtitle.get('locale', 'en-US'), []).append({ + 'url': subtitle_url, + 'ext': subtitle.get('format', 'ass'), + }) thumbnails = [] for thumbnail in video_data.get('images', {}).get('thumbnails', []): diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' '--exclude=.svnignore' old/youtube-dl/youtube_dl/extractor/yahoo.py new/youtube-dl/youtube_dl/extractor/yahoo.py --- old/youtube-dl/youtube_dl/extractor/yahoo.py 2019-05-11 01:06:22.000000000 +0200 +++ new/youtube-dl/youtube_dl/extractor/yahoo.py 2019-05-20 18:25:31.000000000 +0200 @@ -511,6 +511,8 @@ 'https://gyao.yahoo.co.jp/dam/v1/videos/' + video_id, video_id, query={ 'fields': 'longDescription,title,videoId', + }, headers={ + 'X-User-Agent': 'Unknown Pc GYAO!/2.0.0 Web', }) return { '_type': 'url_transparent', 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 2019-05-11 01:07:24.000000000 +0200 +++ new/youtube-dl/youtube_dl/version.py 2019-05-20 18:29:46.000000000 +0200 @@ -1,3 +1,3 @@ from __future__ import unicode_literals -__version__ = '2019.05.11' +__version__ = '2019.05.20'
