From 2181983a0c97c6fd3bb681c86d64699051061c1c Mon Sep 17 00:00:00 2001 From: pukkandan Date: Thu, 4 Feb 2021 13:26:01 +0530 Subject: [PATCH] Update to ytdl-2021.02.04.1 except youtube --- youtube_dlc/extractor/abcnews.py | 128 +++++----- youtube_dlc/extractor/adn.py | 38 ++- youtube_dlc/extractor/aenetworks.py | 2 +- youtube_dlc/extractor/amp.py | 3 +- youtube_dlc/extractor/awaan.py | 2 + youtube_dlc/extractor/azmedien.py | 2 +- youtube_dlc/extractor/bleacherreport.py | 10 +- youtube_dlc/extractor/bravotv.py | 14 +- youtube_dlc/extractor/ccma.py | 65 ++++- youtube_dlc/extractor/cda.py | 2 +- youtube_dlc/extractor/egghead.py | 29 ++- youtube_dlc/extractor/extractors.py | 3 +- youtube_dlc/extractor/generic.py | 23 ++ youtube_dlc/extractor/googledrive.py | 8 +- youtube_dlc/extractor/medialaan.py | 303 ++++++------------------ youtube_dlc/extractor/pornhub.py | 173 ++++++++++---- youtube_dlc/extractor/svt.py | 4 +- youtube_dlc/extractor/tv2.py | 82 ++++++- youtube_dlc/extractor/tv4.py | 6 +- youtube_dlc/extractor/vidio.py | 86 ++++--- youtube_dlc/extractor/vlive.py | 2 +- youtube_dlc/extractor/vtm.py | 62 +++++ youtube_dlc/extractor/vvvvid.py | 35 ++- youtube_dlc/extractor/zype.py | 15 +- 24 files changed, 663 insertions(+), 434 deletions(-) create mode 100644 youtube_dlc/extractor/vtm.py diff --git a/youtube_dlc/extractor/abcnews.py b/youtube_dlc/extractor/abcnews.py index 8b407bf9c..908c83377 100644 --- a/youtube_dlc/extractor/abcnews.py +++ b/youtube_dlc/extractor/abcnews.py @@ -1,14 +1,15 @@ # coding: utf-8 from __future__ import unicode_literals -import calendar import re -import time from .amp import AMPIE from .common import InfoExtractor -from .youtube import YoutubeIE -from ..compat import compat_urlparse +from ..utils import ( + parse_duration, + parse_iso8601, + try_get, +) class AbcNewsVideoIE(AMPIE): @@ -18,8 +19,8 @@ class AbcNewsVideoIE(AMPIE): (?: abcnews\.go\.com/ (?: - [^/]+/video/(?P[0-9a-z-]+)-| - video/embed\?.*?\bid= + (?:[^/]+/)*video/(?P[0-9a-z-]+)-| + video/(?:embed|itemfeed)\?.*?\bid= )| fivethirtyeight\.abcnews\.go\.com/video/embed/\d+/ ) @@ -36,6 +37,8 @@ class AbcNewsVideoIE(AMPIE): 'description': 'George Stephanopoulos goes one-on-one with Iranian Foreign Minister Dr. Javad Zarif.', 'duration': 180, 'thumbnail': r're:^https?://.*\.jpg$', + 'timestamp': 1380454200, + 'upload_date': '20130929', }, 'params': { # m3u8 download @@ -47,6 +50,12 @@ class AbcNewsVideoIE(AMPIE): }, { 'url': 'http://abcnews.go.com/2020/video/2020-husband-stands-teacher-jail-student-affairs-26119478', 'only_matching': True, + }, { + 'url': 'http://abcnews.go.com/video/itemfeed?id=46979033', + 'only_matching': True, + }, { + 'url': 'https://abcnews.go.com/GMA/News/video/history-christmas-story-67894761', + 'only_matching': True, }] def _real_extract(self, url): @@ -67,28 +76,23 @@ class AbcNewsIE(InfoExtractor): _VALID_URL = r'https?://abcnews\.go\.com/(?:[^/]+/)+(?P[0-9a-z-]+)/story\?id=(?P\d+)' _TESTS = [{ - 'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY', + # Youtube Embeds + 'url': 'https://abcnews.go.com/Entertainment/peter-billingsley-child-actor-christmas-story-hollywood-power/story?id=51286501', 'info_dict': { - 'id': '10505354', - 'ext': 'flv', - 'display_id': 'dramatic-video-rare-death-job-america', - 'title': 'Occupational Hazards', - 'description': 'Nightline investigates the dangers that lurk at various jobs.', - 'thumbnail': r're:^https?://.*\.jpg$', - 'upload_date': '20100428', - 'timestamp': 1272412800, + 'id': '51286501', + 'title': "Peter Billingsley: From child actor in 'A Christmas Story' to Hollywood power player", + 'description': 'Billingsley went from a child actor to Hollywood power player.', }, - 'add_ie': ['AbcNewsVideo'], + 'playlist_count': 5, }, { 'url': 'http://abcnews.go.com/Entertainment/justin-timberlake-performs-stop-feeling-eurovision-2016/story?id=39125818', 'info_dict': { 'id': '38897857', 'ext': 'mp4', - 'display_id': 'justin-timberlake-performs-stop-feeling-eurovision-2016', 'title': 'Justin Timberlake Drops Hints For Secret Single', 'description': 'Lara Spencer reports the buzziest stories of the day in "GMA" Pop News.', - 'upload_date': '20160515', - 'timestamp': 1463329500, + 'upload_date': '20160505', + 'timestamp': 1462442280, }, 'params': { # m3u8 download @@ -100,49 +104,55 @@ class AbcNewsIE(InfoExtractor): }, { 'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343', 'only_matching': True, + }, { + # inline.type == 'video' + 'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343', + 'only_matching': True, }] def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - display_id = mobj.group('display_id') - video_id = mobj.group('id') + story_id = self._match_id(url) + webpage = self._download_webpage(url, story_id) + story = self._parse_json(self._search_regex( + r"window\['__abcnews__'\]\s*=\s*({.+?});", + webpage, 'data'), story_id)['page']['content']['story']['everscroll'][0] + article_contents = story.get('articleContents') or {} - webpage = self._download_webpage(url, video_id) - video_url = self._search_regex( - r'window\.abcnvideo\.url\s*=\s*"([^"]+)"', webpage, 'video URL') - full_video_url = compat_urlparse.urljoin(url, video_url) + def entries(): + featured_video = story.get('featuredVideo') or {} + feed = try_get(featured_video, lambda x: x['video']['feed']) + if feed: + yield { + '_type': 'url', + 'id': featured_video.get('id'), + 'title': featured_video.get('name'), + 'url': feed, + 'thumbnail': featured_video.get('images'), + 'description': featured_video.get('description'), + 'timestamp': parse_iso8601(featured_video.get('uploadDate')), + 'duration': parse_duration(featured_video.get('duration')), + 'ie_key': AbcNewsVideoIE.ie_key(), + } - youtube_url = YoutubeIE._extract_url(webpage) + for inline in (article_contents.get('inlines') or []): + inline_type = inline.get('type') + if inline_type == 'iframe': + iframe_url = try_get(inline, lambda x: x['attrs']['src']) + if iframe_url: + yield self.url_result(iframe_url) + elif inline_type == 'video': + video_id = inline.get('id') + if video_id: + yield { + '_type': 'url', + 'id': video_id, + 'url': 'http://abcnews.go.com/video/embed?id=' + video_id, + 'thumbnail': inline.get('imgSrc') or inline.get('imgDefault'), + 'description': inline.get('description'), + 'duration': parse_duration(inline.get('duration')), + 'ie_key': AbcNewsVideoIE.ie_key(), + } - timestamp = None - date_str = self._html_search_regex( - r']+class="timestamp">([^<]+)', - webpage, 'timestamp', fatal=False) - if date_str: - tz_offset = 0 - if date_str.endswith(' ET'): # Eastern Time - tz_offset = -5 - date_str = date_str[:-3] - date_formats = ['%b. %d, %Y', '%b %d, %Y, %I:%M %p'] - for date_format in date_formats: - try: - timestamp = calendar.timegm(time.strptime(date_str.strip(), date_format)) - except ValueError: - continue - if timestamp is not None: - timestamp -= tz_offset * 3600 - - entry = { - '_type': 'url_transparent', - 'ie_key': AbcNewsVideoIE.ie_key(), - 'url': full_video_url, - 'id': video_id, - 'display_id': display_id, - 'timestamp': timestamp, - } - - if youtube_url: - entries = [entry, self.url_result(youtube_url, ie=YoutubeIE.ie_key())] - return self.playlist_result(entries) - - return entry + return self.playlist_result( + entries(), story_id, article_contents.get('headline'), + article_contents.get('subHead')) diff --git a/youtube_dlc/extractor/adn.py b/youtube_dlc/extractor/adn.py index d611ee237..a55ebbcbd 100644 --- a/youtube_dlc/extractor/adn.py +++ b/youtube_dlc/extractor/adn.py @@ -26,6 +26,7 @@ strip_or_none, try_get, unified_strdate, + urlencode_postdata, ) @@ -51,9 +52,12 @@ class ADNIE(InfoExtractor): } } + _NETRC_MACHINE = 'animedigitalnetwork' _BASE_URL = 'http://animedigitalnetwork.fr' _API_BASE_URL = 'https://gw.api.animedigitalnetwork.fr/' _PLAYER_BASE_URL = _API_BASE_URL + 'player/' + _HEADERS = {} + _LOGIN_ERR_MESSAGE = 'Unable to log in' _RSA_KEY = (0x9B42B08905199A5CCE2026274399CA560ECB209EE9878A708B1C0812E1BB8CB5D1FB7441861147C1A1F2F3A0476DD63A9CAC20D3E983613346850AA6CB38F16DC7D720FD7D86FC6E5B3D5BBC72E14CD0BF9E869F2CEA2CCAD648F1DCE38F1FF916CEFB2D339B64AA0264372344BC775E265E8A852F88144AB0BD9AA06C1A4ABB, 65537) _POS_ALIGN_MAP = { 'start': 1, @@ -129,19 +133,42 @@ def _get_subtitles(self, sub_url, video_id): }]) return subtitles + def _real_initialize(self): + username, password = self._get_login_info() + if not username: + return + try: + access_token = (self._download_json( + self._API_BASE_URL + 'authentication/login', None, + 'Logging in', self._LOGIN_ERR_MESSAGE, fatal=False, + data=urlencode_postdata({ + 'password': password, + 'rememberMe': False, + 'source': 'Web', + 'username': username, + })) or {}).get('accessToken') + if access_token: + self._HEADERS = {'authorization': 'Bearer ' + access_token} + except ExtractorError as e: + message = None + if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401: + resp = self._parse_json( + e.cause.read().decode(), None, fatal=False) or {} + message = resp.get('message') or resp.get('code') + self.report_warning(message or self._LOGIN_ERR_MESSAGE) + def _real_extract(self, url): video_id = self._match_id(url) video_base_url = self._PLAYER_BASE_URL + 'video/%s/' % video_id player = self._download_json( video_base_url + 'configuration', video_id, - 'Downloading player config JSON metadata')['player'] + 'Downloading player config JSON metadata', + headers=self._HEADERS)['player'] options = player['options'] user = options['user'] if not user.get('hasAccess'): - raise ExtractorError( - 'This video is only available for paying users', expected=True) - # self.raise_login_required() # FIXME: Login is not implemented + self.raise_login_required() token = self._download_json( user.get('refreshTokenUrl') or (self._PLAYER_BASE_URL + 'refresh/token'), @@ -188,8 +215,7 @@ def _real_extract(self, url): message = error.get('message') if e.cause.code == 403 and error.get('code') == 'player-bad-geolocation-country': self.raise_geo_restricted(msg=message) - else: - raise ExtractorError(message) + raise ExtractorError(message) else: raise ExtractorError('Giving up retrying') diff --git a/youtube_dlc/extractor/aenetworks.py b/youtube_dlc/extractor/aenetworks.py index a5d88ebbe..e55c03fd7 100644 --- a/youtube_dlc/extractor/aenetworks.py +++ b/youtube_dlc/extractor/aenetworks.py @@ -252,7 +252,7 @@ class AENetworksShowIE(AENetworksListBaseIE): _TESTS = [{ 'url': 'http://www.history.com/shows/ancient-aliens', 'info_dict': { - 'id': 'SH012427480000', + 'id': 'SERIES1574', 'title': 'Ancient Aliens', 'description': 'md5:3f6d74daf2672ff3ae29ed732e37ea7f', }, diff --git a/youtube_dlc/extractor/amp.py b/youtube_dlc/extractor/amp.py index 7ff098cfa..24c684cad 100644 --- a/youtube_dlc/extractor/amp.py +++ b/youtube_dlc/extractor/amp.py @@ -8,6 +8,7 @@ int_or_none, mimetype2ext, parse_iso8601, + unified_timestamp, url_or_none, ) @@ -88,7 +89,7 @@ def get_media_node(name, default=None): self._sort_formats(formats) - timestamp = parse_iso8601(item.get('pubDate'), ' ') or parse_iso8601(item.get('dc-date')) + timestamp = unified_timestamp(item.get('pubDate'), ' ') or parse_iso8601(item.get('dc-date')) return { 'id': video_id, diff --git a/youtube_dlc/extractor/awaan.py b/youtube_dlc/extractor/awaan.py index a2603bbff..3a7700cd4 100644 --- a/youtube_dlc/extractor/awaan.py +++ b/youtube_dlc/extractor/awaan.py @@ -48,6 +48,7 @@ def _parse_video_data(self, video_data, video_id, is_live): 'duration': int_or_none(video_data.get('duration')), 'timestamp': parse_iso8601(video_data.get('create_time'), ' '), 'is_live': is_live, + 'uploader_id': video_data.get('user_id'), } @@ -107,6 +108,7 @@ class AWAANLiveIE(AWAANBaseIE): 'title': 're:Dubai Al Oula [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'upload_date': '20150107', 'timestamp': 1420588800, + 'uploader_id': '71', }, 'params': { # m3u8 download diff --git a/youtube_dlc/extractor/azmedien.py b/youtube_dlc/extractor/azmedien.py index b1e20def5..930266990 100644 --- a/youtube_dlc/extractor/azmedien.py +++ b/youtube_dlc/extractor/azmedien.py @@ -47,7 +47,7 @@ class AZMedienIE(InfoExtractor): 'url': 'https://www.telebaern.tv/telebaern-news/montag-1-oktober-2018-ganze-sendung-133531189#video=0_7xjo9lf1', 'only_matching': True }] - _API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/cb9f2f81ed22e9b47f4ca64ea3cc5a5d13e88d1d' + _API_TEMPL = 'https://www.%s/api/pub/gql/%s/NewsArticleTeaser/a4016f65fe62b81dc6664dd9f4910e4ab40383be' _PARTNER_ID = '1719221' def _real_extract(self, url): diff --git a/youtube_dlc/extractor/bleacherreport.py b/youtube_dlc/extractor/bleacherreport.py index dc60224d0..d1bf8e829 100644 --- a/youtube_dlc/extractor/bleacherreport.py +++ b/youtube_dlc/extractor/bleacherreport.py @@ -90,13 +90,19 @@ class BleacherReportCMSIE(AMPIE): _VALID_URL = r'https?://(?:www\.)?bleacherreport\.com/video_embed\?id=(?P[0-9a-f-]{36}|\d{5})' _TESTS = [{ 'url': 'http://bleacherreport.com/video_embed?id=8fd44c2f-3dc5-4821-9118-2c825a98c0e1&library=video-cms', - 'md5': '2e4b0a997f9228ffa31fada5c53d1ed1', + 'md5': '670b2d73f48549da032861130488c681', 'info_dict': { 'id': '8fd44c2f-3dc5-4821-9118-2c825a98c0e1', - 'ext': 'flv', + 'ext': 'mp4', 'title': 'Cena vs. Rollins Would Expose the Heavyweight Division', 'description': 'md5:984afb4ade2f9c0db35f3267ed88b36e', + 'upload_date': '20150723', + 'timestamp': 1437679032, + }, + 'expected_warnings': [ + 'Unable to download f4m manifest' + ] }] def _real_extract(self, url): diff --git a/youtube_dlc/extractor/bravotv.py b/youtube_dlc/extractor/bravotv.py index b9715df00..bae2aedce 100644 --- a/youtube_dlc/extractor/bravotv.py +++ b/youtube_dlc/extractor/bravotv.py @@ -12,7 +12,7 @@ class BravoTVIE(AdobePassIE): - _VALID_URL = r'https?://(?:www\.)?bravotv\.com/(?:[^/]+/)+(?P[^/?#]+)' + _VALID_URL = r'https?://(?:www\.)?(?Pbravotv|oxygen)\.com/(?:[^/]+/)+(?P[^/?#]+)' _TESTS = [{ 'url': 'https://www.bravotv.com/top-chef/season-16/episode-15/videos/the-top-chef-season-16-winner-is', 'md5': 'e34684cfea2a96cd2ee1ef3a60909de9', @@ -28,10 +28,13 @@ class BravoTVIE(AdobePassIE): }, { 'url': 'http://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1', 'only_matching': True, + }, { + 'url': 'https://www.oxygen.com/in-ice-cold-blood/season-2/episode-16/videos/handling-the-horwitz-house-after-the-murder-season-2', + 'only_matching': True, }] def _real_extract(self, url): - display_id = self._match_id(url) + site, display_id = re.match(self._VALID_URL, url).groups() webpage = self._download_webpage(url, display_id) settings = self._parse_json(self._search_regex( r']+data-drupal-selector="drupal-settings-json"[^>]*>({.+?})', webpage, 'drupal settings'), @@ -53,11 +56,14 @@ def _real_extract(self, url): tp_path = release_pid = tve['release_pid'] if tve.get('entitlement') == 'auth': adobe_pass = settings.get('tve_adobe_auth', {}) + if site == 'bravotv': + site = 'bravo' resource = self._get_mvpd_resource( - adobe_pass.get('adobePassResourceId', 'bravo'), + adobe_pass.get('adobePassResourceId') or site, tve['title'], release_pid, tve.get('rating')) query['auth'] = self._extract_mvpd_auth( - url, release_pid, adobe_pass.get('adobePassRequestorId', 'bravo'), resource) + url, release_pid, + adobe_pass.get('adobePassRequestorId') or site, resource) else: shared_playlist = settings['ls_playlist'] account_pid = shared_playlist['account_pid'] diff --git a/youtube_dlc/extractor/ccma.py b/youtube_dlc/extractor/ccma.py index 544647f92..4db51e650 100644 --- a/youtube_dlc/extractor/ccma.py +++ b/youtube_dlc/extractor/ccma.py @@ -1,6 +1,7 @@ # coding: utf-8 from __future__ import unicode_literals +import datetime import re from .common import InfoExtractor @@ -8,8 +9,8 @@ clean_html, int_or_none, parse_duration, - parse_iso8601, parse_resolution, + try_get, url_or_none, ) @@ -24,8 +25,9 @@ class CCMAIE(InfoExtractor): 'ext': 'mp4', 'title': 'L\'espot de La Marató de TV3', 'description': 'md5:f12987f320e2f6e988e9908e4fe97765', - 'timestamp': 1470918540, - 'upload_date': '20160811', + 'timestamp': 1478608140, + 'upload_date': '20161108', + 'age_limit': 0, } }, { 'url': 'http://www.ccma.cat/catradio/alacarta/programa/el-consell-de-savis-analitza-el-derbi/audio/943685/', @@ -35,8 +37,24 @@ class CCMAIE(InfoExtractor): 'ext': 'mp3', 'title': 'El Consell de Savis analitza el derbi', 'description': 'md5:e2a3648145f3241cb9c6b4b624033e53', - 'upload_date': '20171205', - 'timestamp': 1512507300, + 'upload_date': '20170512', + 'timestamp': 1494622500, + 'vcodec': 'none', + 'categories': ['Esports'], + } + }, { + 'url': 'http://www.ccma.cat/tv3/alacarta/crims/crims-josep-tallada-lespereu-me-capitol-1/video/6031387/', + 'md5': 'b43c3d3486f430f3032b5b160d80cbc3', + 'info_dict': { + 'id': '6031387', + 'ext': 'mp4', + 'title': 'Crims - Josep Talleda, l\'"Espereu-me" (capítol 1)', + 'description': 'md5:7cbdafb640da9d0d2c0f62bad1e74e60', + 'timestamp': 1582577700, + 'upload_date': '20200224', + 'subtitles': 'mincount:4', + 'age_limit': 16, + 'series': 'Crims', } }] @@ -72,17 +90,27 @@ def _real_extract(self, url): informacio = media['informacio'] title = informacio['titol'] - durada = informacio.get('durada', {}) + durada = informacio.get('durada') or {} duration = int_or_none(durada.get('milisegons'), 1000) or parse_duration(durada.get('text')) - timestamp = parse_iso8601(informacio.get('data_emissio', {}).get('utc')) + tematica = try_get(informacio, lambda x: x['tematica']['text']) + + timestamp = None + data_utc = try_get(informacio, lambda x: x['data_emissio']['utc']) + try: + timestamp = datetime.datetime.strptime( + data_utc, '%Y-%d-%mT%H:%M:%S%z').timestamp() + except TypeError: + pass subtitles = {} - subtitols = media.get('subtitols', {}) - if subtitols: - sub_url = subtitols.get('url') + subtitols = media.get('subtitols') or [] + if isinstance(subtitols, dict): + subtitols = [subtitols] + for st in subtitols: + sub_url = st.get('url') if sub_url: subtitles.setdefault( - subtitols.get('iso') or subtitols.get('text') or 'ca', []).append({ + st.get('iso') or st.get('text') or 'ca', []).append({ 'url': sub_url, }) @@ -97,6 +125,16 @@ def _real_extract(self, url): 'height': int_or_none(imatges.get('alcada')), }] + age_limit = None + codi_etic = try_get(informacio, lambda x: x['codi_etic']['id']) + if codi_etic: + codi_etic_s = codi_etic.split('_') + if len(codi_etic_s) == 2: + if codi_etic_s[1] == 'TP': + age_limit = 0 + else: + age_limit = int_or_none(codi_etic_s[1]) + return { 'id': media_id, 'title': title, @@ -106,4 +144,9 @@ def _real_extract(self, url): 'thumbnails': thumbnails, 'subtitles': subtitles, 'formats': formats, + 'age_limit': age_limit, + 'alt_title': informacio.get('titol_complet'), + 'episode_number': int_or_none(informacio.get('capitol')), + 'categories': [tematica] if tematica else None, + 'series': informacio.get('programa'), } diff --git a/youtube_dlc/extractor/cda.py b/youtube_dlc/extractor/cda.py index d67900e62..6429454fb 100644 --- a/youtube_dlc/extractor/cda.py +++ b/youtube_dlc/extractor/cda.py @@ -96,7 +96,7 @@ def _real_extract(self, url): raise ExtractorError('This video is only available for premium users.', expected=True) need_confirm_age = False - if self._html_search_regex(r'(]+action="/a/validatebirth")', + if self._html_search_regex(r'(]+action="[^"]*/a/validatebirth[^"]*")', webpage, 'birthday validate form', default=None): webpage = self._download_age_confirm_page( url, video_id, note='Confirming age') diff --git a/youtube_dlc/extractor/egghead.py b/youtube_dlc/extractor/egghead.py index df11dc206..aff9b88c0 100644 --- a/youtube_dlc/extractor/egghead.py +++ b/youtube_dlc/extractor/egghead.py @@ -12,7 +12,14 @@ ) -class EggheadCourseIE(InfoExtractor): +class EggheadBaseIE(InfoExtractor): + def _call_api(self, path, video_id, resource, fatal=True): + return self._download_json( + 'https://app.egghead.io/api/v1/' + path, + video_id, 'Downloading %s JSON' % resource, fatal=fatal) + + +class EggheadCourseIE(EggheadBaseIE): IE_DESC = 'egghead.io course' IE_NAME = 'egghead:course' _VALID_URL = r'https://egghead\.io/courses/(?P[^/?#&]+)' @@ -28,10 +35,9 @@ class EggheadCourseIE(InfoExtractor): def _real_extract(self, url): playlist_id = self._match_id(url) - - lessons = self._download_json( - 'https://egghead.io/api/v1/series/%s/lessons' % playlist_id, - playlist_id, 'Downloading course lessons JSON') + series_path = 'series/' + playlist_id + lessons = self._call_api( + series_path + '/lessons', playlist_id, 'course lessons') entries = [] for lesson in lessons: @@ -44,9 +50,8 @@ def _real_extract(self, url): entries.append(self.url_result( lesson_url, ie=EggheadLessonIE.ie_key(), video_id=lesson_id)) - course = self._download_json( - 'https://egghead.io/api/v1/series/%s' % playlist_id, - playlist_id, 'Downloading course JSON', fatal=False) or {} + course = self._call_api( + series_path, playlist_id, 'course', False) or {} playlist_id = course.get('id') if playlist_id: @@ -57,7 +62,7 @@ def _real_extract(self, url): course.get('description')) -class EggheadLessonIE(InfoExtractor): +class EggheadLessonIE(EggheadBaseIE): IE_DESC = 'egghead.io lesson' IE_NAME = 'egghead:lesson' _VALID_URL = r'https://egghead\.io/(?:api/v1/)?lessons/(?P[^/?#&]+)' @@ -74,7 +79,7 @@ class EggheadLessonIE(InfoExtractor): 'upload_date': '20161209', 'duration': 304, 'view_count': 0, - 'tags': ['javascript', 'free'], + 'tags': 'count:2', }, 'params': { 'skip_download': True, @@ -88,8 +93,8 @@ class EggheadLessonIE(InfoExtractor): def _real_extract(self, url): display_id = self._match_id(url) - lesson = self._download_json( - 'https://egghead.io/api/v1/lessons/%s' % display_id, display_id) + lesson = self._call_api( + 'lessons/' + display_id, display_id, 'lesson') lesson_id = compat_str(lesson['id']) title = lesson['title'] diff --git a/youtube_dlc/extractor/extractors.py b/youtube_dlc/extractor/extractors.py index d9e48680e..752e7bee5 100644 --- a/youtube_dlc/extractor/extractors.py +++ b/youtube_dlc/extractor/extractors.py @@ -1308,6 +1308,7 @@ TV2IE, TV2ArticleIE, KatsomoIE, + MTVUutisetArticleIE, ) from .tv2dk import ( TV2DKIE, @@ -1448,7 +1449,6 @@ VidmeUserIE, VidmeUserLikesIE, ) -from .vidzi import VidziIE from .vier import VierIE, VierVideosIE from .viewlift import ( ViewLiftIE, @@ -1508,6 +1508,7 @@ VRVSeriesIE, ) from .vshare import VShareIE +from .vtm import VTMIE from .medialaan import MedialaanIE from .vube import VubeIE from .vuclip import VuClipIE diff --git a/youtube_dlc/extractor/generic.py b/youtube_dlc/extractor/generic.py index 6b4c84261..d5d8ed94b 100644 --- a/youtube_dlc/extractor/generic.py +++ b/youtube_dlc/extractor/generic.py @@ -131,6 +131,7 @@ from .rcs import RCSEmbedsIE from .bitchute import BitChuteIE from .arcpublishing import ArcPublishingIE +from .medialaan import MedialaanIE class GenericIE(InfoExtractor): @@ -2224,6 +2225,20 @@ class GenericIE(InfoExtractor): 'duration': 1581, }, }, + { + # MyChannels SDK embed + # https://www.24kitchen.nl/populair/deskundige-dit-waarom-sommigen-gevoelig-zijn-voor-voedselallergieen + 'url': 'https://www.demorgen.be/nieuws/burgemeester-rotterdam-richt-zich-in-videoboodschap-tot-relschoppers-voelt-het-goed~b0bcfd741/', + 'md5': '90c0699c37006ef18e198c032d81739c', + 'info_dict': { + 'id': '194165', + 'ext': 'mp4', + 'title': 'Burgemeester Aboutaleb spreekt relschoppers toe', + 'timestamp': 1611740340, + 'upload_date': '20210127', + 'duration': 159, + }, + }, ] def report_following_redirect(self, new_url): @@ -2463,6 +2478,9 @@ def _real_extract(self, url): webpage = self._webpage_read_content( full_response, url, video_id, prefix=first_bytes) + if 'DPG Media Privacy Gate' in webpage: + webpage = self._download_webpage(url, video_id) + self.report_extraction(video_id) # Is it an RSS feed, a SMIL file, an XSPF playlist or a MPD manifest? @@ -2594,6 +2612,11 @@ def _real_extract(self, url): if arc_urls: return self.playlist_from_matches(arc_urls, video_id, video_title, ie=ArcPublishingIE.ie_key()) + mychannels_urls = MedialaanIE._extract_urls(webpage) + if mychannels_urls: + return self.playlist_from_matches( + mychannels_urls, video_id, video_title, ie=MedialaanIE.ie_key()) + # Look for embedded rtl.nl player matches = re.findall( r']+?src="((?:https?:)?//(?:(?:www|static)\.)?rtl\.nl/(?:system/videoplayer/[^"]+(?:video_)?)?embed[^"]+)"', diff --git a/youtube_dlc/extractor/googledrive.py b/youtube_dlc/extractor/googledrive.py index fdb15795a..4eefcb70c 100644 --- a/youtube_dlc/extractor/googledrive.py +++ b/youtube_dlc/extractor/googledrive.py @@ -7,6 +7,7 @@ from ..utils import ( determine_ext, ExtractorError, + get_element_by_class, int_or_none, lowercase_escape, try_get, @@ -237,7 +238,7 @@ def add_source_format(urlh): if confirmation_webpage: confirm = self._search_regex( r'confirm=([^&"\']+)', confirmation_webpage, - 'confirmation code', fatal=False) + 'confirmation code', default=None) if confirm: confirmed_source_url = update_url_query(source_url, { 'confirm': confirm, @@ -245,6 +246,11 @@ def add_source_format(urlh): urlh = request_source_file(confirmed_source_url, 'confirmed source') if urlh and urlh.headers.get('Content-Disposition'): add_source_format(urlh) + else: + self.report_warning( + get_element_by_class('uc-error-subcaption', confirmation_webpage) + or get_element_by_class('uc-error-caption', confirmation_webpage) + or 'unable to extract confirmation code') if not formats and reason: raise ExtractorError(reason, expected=True) diff --git a/youtube_dlc/extractor/medialaan.py b/youtube_dlc/extractor/medialaan.py index 50d5db802..788acf7fb 100644 --- a/youtube_dlc/extractor/medialaan.py +++ b/youtube_dlc/extractor/medialaan.py @@ -2,268 +2,113 @@ import re -from .gigya import GigyaBaseIE - -from ..compat import compat_str +from .common import InfoExtractor from ..utils import ( + extract_attributes, int_or_none, - parse_duration, - try_get, - unified_timestamp, + mimetype2ext, + parse_iso8601, ) -class MedialaanIE(GigyaBaseIE): +class MedialaanIE(InfoExtractor): _VALID_URL = r'''(?x) https?:// - (?:www\.|nieuws\.)? (?: - (?Pvtm|q2|vtmkzoom)\.be/ - (?: - video(?:/[^/]+/id/|/?\?.*?\baid=)| - (?:[^/]+/)* - ) + (?:embed\.)?mychannels.video/embed/| + embed\.mychannels\.video/(?:s(?:dk|cript)/)?production/| + (?:www\.)?(?: + (?: + 7sur7| + demorgen| + hln| + joe| + qmusic + )\.be| + (?: + [abe]d| + bndestem| + destentor| + gelderlander| + pzc| + tubantia| + volkskrant + )\.nl + )/video/(?:[^/]+/)*[^/?&#]+~p ) - (?P[^/?#&]+) + (?P\d+) ''' - _NETRC_MACHINE = 'medialaan' - _APIKEY = '3_HZ0FtkMW_gOyKlqQzW5_0FHRC7Nd5XpXJZcDdXY4pk5eES2ZWmejRW5egwVm4ug-' - _SITE_TO_APP_ID = { - 'vtm': 'vtm_watch', - 'q2': 'q2', - 'vtmkzoom': 'vtmkzoom', - } _TESTS = [{ - # vod - 'url': 'http://vtm.be/video/volledige-afleveringen/id/vtm_20170219_VM0678361_vtmwatch', + 'url': 'https://www.bndestem.nl/video/de-terugkeer-van-ally-de-aap-en-wie-vertrekt-er-nog-bij-nac~p193993', 'info_dict': { - 'id': 'vtm_20170219_VM0678361_vtmwatch', + 'id': '193993', 'ext': 'mp4', - 'title': 'Allemaal Chris afl. 6', - 'description': 'md5:4be86427521e7b07e0adb0c9c554ddb2', - 'timestamp': 1487533280, - 'upload_date': '20170219', - 'duration': 2562, - 'series': 'Allemaal Chris', - 'season': 'Allemaal Chris', - 'season_number': 1, - 'season_id': '256936078124527', - 'episode': 'Allemaal Chris afl. 6', - 'episode_number': 6, - 'episode_id': '256936078591527', + 'title': 'De terugkeer van Ally de Aap en wie vertrekt er nog bij NAC?', + 'timestamp': 1611663540, + 'upload_date': '20210126', + 'duration': 238, }, 'params': { 'skip_download': True, }, - 'skip': 'Requires account credentials', }, { - # clip - 'url': 'http://vtm.be/video?aid=168332', - 'info_dict': { - 'id': '168332', - 'ext': 'mp4', - 'title': '"Veronique liegt!"', - 'description': 'md5:1385e2b743923afe54ba4adc38476155', - 'timestamp': 1489002029, - 'upload_date': '20170308', - 'duration': 96, - }, - }, { - # vod - 'url': 'http://vtm.be/video/volledige-afleveringen/id/257107153551000', + 'url': 'https://www.gelderlander.nl/video/kanalen/degelderlander~c320/series/snel-nieuws~s984/noodbevel-in-doetinchem-politie-stuurt-mensen-centrum-uit~p194093', 'only_matching': True, }, { - # vod - 'url': 'http://vtm.be/video?aid=163157', + 'url': 'https://embed.mychannels.video/sdk/production/193993?options=TFTFF_default', 'only_matching': True, }, { - # vod - 'url': 'http://www.q2.be/video/volledige-afleveringen/id/2be_20170301_VM0684442_q2', + 'url': 'https://embed.mychannels.video/script/production/193993', 'only_matching': True, }, { - # clip - 'url': 'http://vtmkzoom.be/k3-dansstudio/een-nieuw-seizoen-van-k3-dansstudio', + 'url': 'https://embed.mychannels.video/production/193993', 'only_matching': True, }, { - # http/s redirect - 'url': 'https://vtmkzoom.be/video?aid=45724', - 'info_dict': { - 'id': '257136373657000', - 'ext': 'mp4', - 'title': 'K3 Dansstudio Ushuaia afl.6', - }, - 'params': { - 'skip_download': True, - }, - 'skip': 'Requires account credentials', + 'url': 'https://mychannels.video/embed/193993', + 'only_matching': True, }, { - # nieuws.vtm.be - 'url': 'https://nieuws.vtm.be/stadion/stadion/genk-nog-moeilijk-programma', + 'url': 'https://embed.mychannels.video/embed/193993', 'only_matching': True, }] - def _real_initialize(self): - self._logged_in = False - - def _login(self): - username, password = self._get_login_info() - if username is None: - self.raise_login_required() - - auth_data = { - 'APIKey': self._APIKEY, - 'sdk': 'js_6.1', - 'format': 'json', - 'loginID': username, - 'password': password, - } - - auth_info = self._gigya_login(auth_data) - - self._uid = auth_info['UID'] - self._uid_signature = auth_info['UIDSignature'] - self._signature_timestamp = auth_info['signatureTimestamp'] - - self._logged_in = True + @staticmethod + def _extract_urls(webpage): + entries = [] + for element in re.findall(r'(]+data-mychannels-type="video"[^>]*>)', webpage): + mychannels_id = extract_attributes(element).get('data-mychannels-id') + if mychannels_id: + entries.append('https://mychannels.video/embed/' + mychannels_id) + return entries def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id, site_id = mobj.group('id', 'site_id') + production_id = self._match_id(url) + production = self._download_json( + 'https://embed.mychannels.video/sdk/production/' + production_id, + production_id, query={'options': 'UUUU_default'})['productions'][0] + title = production['title'] - webpage = self._download_webpage(url, video_id) - - config = self._parse_json( - self._search_regex( - r'videoJSConfig\s*=\s*JSON\.parse\(\'({.+?})\'\);', - webpage, 'config', default='{}'), video_id, - transform_source=lambda s: s.replace( - '\\\\', '\\').replace(r'\"', '"').replace(r"\'", "'")) - - vod_id = config.get('vodId') or self._search_regex( - (r'\\"vodId\\"\s*:\s*\\"(.+?)\\"', - r'"vodId"\s*:\s*"(.+?)"', - r'<[^>]+id=["\']vod-(\d+)'), - webpage, 'video_id', default=None) - - # clip, no authentication required - if not vod_id: - player = self._parse_json( - self._search_regex( - r'vmmaplayer\(({.+?})\);', webpage, 'vmma player', - default=''), - video_id, transform_source=lambda s: '[%s]' % s, fatal=False) - if player: - video = player[-1] - if video['videoUrl'] in ('http', 'https'): - return self.url_result(video['url'], MedialaanIE.ie_key()) - info = { - 'id': video_id, - 'url': video['videoUrl'], - 'title': video['title'], - 'thumbnail': video.get('imageUrl'), - 'timestamp': int_or_none(video.get('createdDate')), - 'duration': int_or_none(video.get('duration')), - } + formats = [] + for source in (production.get('sources') or []): + src = source.get('src') + if not src: + continue + ext = mimetype2ext(source.get('type')) + if ext == 'm3u8': + formats.extend(self._extract_m3u8_formats( + src, production_id, 'mp4', 'm3u8_native', + m3u8_id='hls', fatal=False)) else: - info = self._parse_html5_media_entries( - url, webpage, video_id, m3u8_id='hls')[0] - info.update({ - 'id': video_id, - 'title': self._html_search_meta('description', webpage), - 'duration': parse_duration(self._html_search_meta('duration', webpage)), + formats.append({ + 'ext': ext, + 'url': src, }) - # vod, authentication required - else: - if not self._logged_in: - self._login() + self._sort_formats(formats) - settings = self._parse_json( - self._search_regex( - r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', - webpage, 'drupal settings', default='{}'), - video_id) - - def get(container, item): - return try_get( - settings, lambda x: x[container][item], - compat_str) or self._search_regex( - r'"%s"\s*:\s*"([^"]+)' % item, webpage, item, - default=None) - - app_id = get('vod', 'app_id') or self._SITE_TO_APP_ID.get(site_id, 'vtm_watch') - sso = get('vod', 'gigyaDatabase') or 'vtm-sso' - - data = self._download_json( - 'http://vod.medialaan.io/api/1.0/item/%s/video' % vod_id, - video_id, query={ - 'app_id': app_id, - 'user_network': sso, - 'UID': self._uid, - 'UIDSignature': self._uid_signature, - 'signatureTimestamp': self._signature_timestamp, - }) - - formats = self._extract_m3u8_formats( - data['response']['uri'], video_id, entry_protocol='m3u8_native', - ext='mp4', m3u8_id='hls') - - self._sort_formats(formats) - - info = { - 'id': vod_id, - 'formats': formats, - } - - api_key = get('vod', 'apiKey') - channel = get('medialaanGigya', 'channel') - - if api_key: - videos = self._download_json( - 'http://vod.medialaan.io/vod/v2/videos', video_id, fatal=False, - query={ - 'channels': channel, - 'ids': vod_id, - 'limit': 1, - 'apikey': api_key, - }) - if videos: - video = try_get( - videos, lambda x: x['response']['videos'][0], dict) - if video: - def get(container, item, expected_type=None): - return try_get( - video, lambda x: x[container][item], expected_type) - - def get_string(container, item): - return get(container, item, compat_str) - - info.update({ - 'series': get_string('program', 'title'), - 'season': get_string('season', 'title'), - 'season_number': int_or_none(get('season', 'number')), - 'season_id': get_string('season', 'id'), - 'episode': get_string('episode', 'title'), - 'episode_number': int_or_none(get('episode', 'number')), - 'episode_id': get_string('episode', 'id'), - 'duration': int_or_none( - video.get('duration')) or int_or_none( - video.get('durationMillis'), scale=1000), - 'title': get_string('episode', 'title'), - 'description': get_string('episode', 'text'), - 'timestamp': unified_timestamp(get_string( - 'publication', 'begin')), - }) - - if not info.get('title'): - info['title'] = try_get( - config, lambda x: x['videoConfig']['title'], - compat_str) or self._html_search_regex( - r'\\"title\\"\s*:\s*\\"(.+?)\\"', webpage, 'title', - default=None) or self._og_search_title(webpage) - - if not info.get('description'): - info['description'] = self._html_search_regex( - r']+class="field-item\s+even">\s*

(.+?)

', - webpage, 'description', default=None) - - return info + return { + 'id': production_id, + 'title': title, + 'formats': formats, + 'thumbnail': production.get('posterUrl'), + 'timestamp': parse_iso8601(production.get('publicationDate'), ' '), + 'duration': int_or_none(production.get('duration')) or None, + } diff --git a/youtube_dlc/extractor/pornhub.py b/youtube_dlc/extractor/pornhub.py index 2fcbd186f..b7631e4e1 100644 --- a/youtube_dlc/extractor/pornhub.py +++ b/youtube_dlc/extractor/pornhub.py @@ -22,11 +22,15 @@ orderedSet, remove_quotes, str_to_int, + update_url_query, + urlencode_postdata, url_or_none, ) class PornHubBaseIE(InfoExtractor): + _NETRC_MACHINE = 'pornhub' + def _download_webpage_handle(self, *args, **kwargs): def dl(*args, **kwargs): return super(PornHubBaseIE, self)._download_webpage_handle(*args, **kwargs) @@ -52,6 +56,66 @@ def dl(*args, **kwargs): return webpage, urlh + def _real_initialize(self): + self._logged_in = False + + def _login(self, host): + if self._logged_in: + return + + site = host.split('.')[0] + + # Both sites pornhub and pornhubpremium have separate accounts + # so there should be an option to provide credentials for both. + # At the same time some videos are available under the same video id + # on both sites so that we have to identify them as the same video. + # For that purpose we have to keep both in the same extractor + # but under different netrc machines. + username, password = self._get_login_info(netrc_machine=site) + if username is None: + return + + login_url = 'https://www.%s/%slogin' % (host, 'premium/' if 'premium' in host else '') + login_page = self._download_webpage( + login_url, None, 'Downloading %s login page' % site) + + def is_logged(webpage): + return any(re.search(p, webpage) for p in ( + r'class=["\']signOut', + r'>Sign\s+[Oo]ut\s*<')) + + if is_logged(login_page): + self._logged_in = True + return + + login_form = self._hidden_inputs(login_page) + + login_form.update({ + 'username': username, + 'password': password, + }) + + response = self._download_json( + 'https://www.%s/front/authenticate' % host, None, + 'Logging in to %s' % site, + data=urlencode_postdata(login_form), + headers={ + 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8', + 'Referer': login_url, + 'X-Requested-With': 'XMLHttpRequest', + }) + + if response.get('success') == '1': + self._logged_in = True + return + + message = response.get('message') + if message is not None: + raise ExtractorError( + 'Unable to login: %s' % message, expected=True) + + raise ExtractorError('Unable to log in') + class PornHubIE(PornHubBaseIE): IE_DESC = 'PornHub and Thumbzilla' @@ -163,12 +227,20 @@ class PornHubIE(PornHubBaseIE): }, { 'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5e4acdae54a82', 'only_matching': True, + }, { + # Some videos are available with the same id on both premium + # and non-premium sites (e.g. this and the following test) + 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5f75b0f4b18e3', + 'only_matching': True, + }, { + 'url': 'https://www.pornhubpremium.com/view_video.php?viewkey=ph5f75b0f4b18e3', + 'only_matching': True, }] @staticmethod def _extract_urls(webpage): return re.findall( - r']+?src=["\'](?P(?:https?:)?//(?:www\.)?pornhub\.(?:com|net|org)/embed/[\da-z]+)', + r']+?src=["\'](?P(?:https?:)?//(?:www\.)?pornhub(?:premium)?\.(?:com|net|org)/embed/[\da-z]+)', webpage) def _extract_count(self, pattern, webpage, name): @@ -180,12 +252,7 @@ def _real_extract(self, url): host = mobj.group('host') or 'pornhub.com' video_id = mobj.group('id') - if 'premium' in host: - if not self._downloader.params.get('cookiefile'): - raise ExtractorError( - 'PornHub Premium requires authentication.' - ' You may want to use --cookies.', - expected=True) + self._login(host) self._set_cookie(host, 'age_verified', '1') @@ -405,6 +472,10 @@ def extract_list(meta_key): class PornHubPlaylistBaseIE(PornHubBaseIE): + def _extract_page(self, url): + return int_or_none(self._search_regex( + r'\bpage=(\d+)', url, 'page', default=None)) + def _extract_entries(self, webpage, host): # Only process container div with main playlist content skipping # drop-down menu that uses similar pattern for videos (see @@ -422,26 +493,6 @@ def _extract_entries(self, webpage, host): container)) ] - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - host = mobj.group('host') - playlist_id = mobj.group('id') - - webpage = self._download_webpage(url, playlist_id) - - entries = self._extract_entries(webpage, host) - - playlist = self._parse_json( - self._search_regex( - r'(?:playlistObject|PLAYLIST_VIEW)\s*=\s*({.+?});', webpage, - 'playlist', default='{}'), - playlist_id, fatal=False) - title = playlist.get('title') or self._search_regex( - r'>Videos\s+in\s+(.+?)\s+[Pp]laylist<', webpage, 'title', fatal=False) - - return self.playlist_result( - entries, playlist_id, title, playlist.get('description')) - class PornHubUserIE(PornHubPlaylistBaseIE): _VALID_URL = r'(?Phttps?://(?:[^/]+\.)?(?Ppornhub(?:premium)?\.(?:com|net|org))/(?:(?:user|channel)s|model|pornstar)/(?P[^/?#&]+))(?:[?#&]|/(?!videos)|$)' @@ -463,14 +514,27 @@ class PornHubUserIE(PornHubPlaylistBaseIE): }, { 'url': 'https://www.pornhub.com/model/zoe_ph?abc=1', 'only_matching': True, + }, { + # Unavailable via /videos page, but available with direct pagination + # on pornstar page (see [1]), requires premium + # 1. https://github.com/ytdl-org/youtube-dl/issues/27853 + 'url': 'https://www.pornhubpremium.com/pornstar/sienna-west', + 'only_matching': True, + }, { + # Same as before, multi page + 'url': 'https://www.pornhubpremium.com/pornstar/lily-labeau', + 'only_matching': True, }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) user_id = mobj.group('id') + videos_url = '%s/videos' % mobj.group('url') + page = self._extract_page(url) + if page: + videos_url = update_url_query(videos_url, {'page': page}) return self.url_result( - '%s/videos' % mobj.group('url'), ie=PornHubPagedVideoListIE.ie_key(), - video_id=user_id) + videos_url, ie=PornHubPagedVideoListIE.ie_key(), video_id=user_id) class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE): @@ -483,32 +547,55 @@ def _has_more(webpage): ]+\bid=["\']moreDataBtn ''', webpage) is not None - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - host = mobj.group('host') - item_id = mobj.group('id') + def _entries(self, url, host, item_id): + page = self._extract_page(url) - page = int_or_none(self._search_regex( - r'\bpage=(\d+)', url, 'page', default=None)) + VIDEOS = '/videos' - entries = [] - for page_num in (page, ) if page is not None else itertools.count(1): + def download_page(base_url, num, fallback=False): + note = 'Downloading page %d%s' % (num, ' (switch to fallback)' if fallback else '') + return self._download_webpage( + base_url, item_id, note, query={'page': num}) + + def is_404(e): + return isinstance(e.cause, compat_HTTPError) and e.cause.code == 404 + + base_url = url + has_page = page is not None + first_page = page if has_page else 1 + for page_num in (first_page, ) if has_page else itertools.count(first_page): try: - webpage = self._download_webpage( - url, item_id, 'Downloading page %d' % page_num, - query={'page': page_num}) + try: + webpage = download_page(base_url, page_num) + except ExtractorError as e: + # Some sources may not be available via /videos page, + # trying to fallback to main page pagination (see [1]) + # 1. https://github.com/ytdl-org/youtube-dl/issues/27853 + if is_404(e) and page_num == first_page and VIDEOS in base_url: + base_url = base_url.replace(VIDEOS, '') + webpage = download_page(base_url, page_num, fallback=True) + else: + raise except ExtractorError as e: - if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: + if is_404(e) and page_num != first_page: break raise page_entries = self._extract_entries(webpage, host) if not page_entries: break - entries.extend(page_entries) + for e in page_entries: + yield e if not self._has_more(webpage): break - return self.playlist_result(orderedSet(entries), item_id) + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + host = mobj.group('host') + item_id = mobj.group('id') + + self._login(host) + + return self.playlist_result(self._entries(url, host, item_id), item_id) class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE): diff --git a/youtube_dlc/extractor/svt.py b/youtube_dlc/extractor/svt.py index a0b6ef4db..4acc29fce 100644 --- a/youtube_dlc/extractor/svt.py +++ b/youtube_dlc/extractor/svt.py @@ -255,8 +255,10 @@ def _real_extract(self, url): svt_id = self._search_regex( (r']+data-video-id=["\']([\da-zA-Z-]+)', r'["\']videoSvtId["\']\s*:\s*["\']([\da-zA-Z-]+)', + r'["\']videoSvtId\\?["\']\s*:\s*\\?["\']([\da-zA-Z-]+)', r'"content"\s*:\s*{.*?"id"\s*:\s*"([\da-zA-Z-]+)"', - r'["\']svtId["\']\s*:\s*["\']([\da-zA-Z-]+)'), + r'["\']svtId["\']\s*:\s*["\']([\da-zA-Z-]+)', + r'["\']svtId\\?["\']\s*:\s*\\?["\']([\da-zA-Z-]+)'), webpage, 'video id') info_dict = self._extract_by_video_id(svt_id, webpage) diff --git a/youtube_dlc/extractor/tv2.py b/youtube_dlc/extractor/tv2.py index 4a19b9be6..334b7d540 100644 --- a/youtube_dlc/extractor/tv2.py +++ b/youtube_dlc/extractor/tv2.py @@ -20,7 +20,7 @@ class TV2IE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?tv2\.no/v/(?P\d+)' - _TEST = { + _TESTS = [{ 'url': 'http://www.tv2.no/v/916509/', 'info_dict': { 'id': '916509', @@ -33,7 +33,7 @@ class TV2IE(InfoExtractor): 'view_count': int, 'categories': list, }, - } + }] _API_DOMAIN = 'sumo.tv2.no' _PROTOCOLS = ('HDS', 'HLS', 'DASH') _GEO_COUNTRIES = ['NO'] @@ -42,6 +42,12 @@ def _real_extract(self, url): video_id = self._match_id(url) api_base = 'http://%s/api/web/asset/%s' % (self._API_DOMAIN, video_id) + asset = self._download_json( + api_base + '.json', video_id, + 'Downloading metadata JSON')['asset'] + title = asset.get('subtitle') or asset['title'] + is_live = asset.get('live') is True + formats = [] format_urls = [] for protocol in self._PROTOCOLS: @@ -81,7 +87,8 @@ def _real_extract(self, url): elif ext == 'm3u8': if not data.get('drmProtected'): formats.extend(self._extract_m3u8_formats( - video_url, video_id, 'mp4', entry_protocol='m3u8_native', + video_url, video_id, 'mp4', + 'm3u8' if is_live else 'm3u8_native', m3u8_id=format_id, fatal=False)) elif ext == 'mpd': formats.extend(self._extract_mpd_formats( @@ -99,11 +106,6 @@ def _real_extract(self, url): raise ExtractorError('This video is DRM protected.', expected=True) self._sort_formats(formats) - asset = self._download_json( - api_base + '.json', video_id, - 'Downloading metadata JSON')['asset'] - title = asset['title'] - thumbnails = [{ 'id': thumbnail.get('@type'), 'url': thumbnail.get('url'), @@ -112,7 +114,7 @@ def _real_extract(self, url): return { 'id': video_id, 'url': video_url, - 'title': title, + 'title': self._live_title(title) if is_live else title, 'description': strip_or_none(asset.get('description')), 'thumbnails': thumbnails, 'timestamp': parse_iso8601(asset.get('createTime')), @@ -120,6 +122,7 @@ def _real_extract(self, url): 'view_count': int_or_none(asset.get('views')), 'categories': asset.get('keywords', '').split(','), 'formats': formats, + 'is_live': is_live, } @@ -168,13 +171,13 @@ def _real_extract(self, url): class KatsomoIE(TV2IE): - _VALID_URL = r'https?://(?:www\.)?(?:katsomo|mtv)\.fi/(?:#!/)?(?:[^/]+/[0-9a-z-]+-\d+/[0-9a-z-]+-|[^/]+/\d+/[^/]+/)(?P\d+)' - _TEST = { + _VALID_URL = r'https?://(?:www\.)?(?:katsomo|mtv(uutiset)?)\.fi/(?:sarja/[0-9a-z-]+-\d+/[0-9a-z-]+-|(?:#!/)?jakso/(?:\d+/[^/]+/)?|video/prog)(?P\d+)' + _TESTS = [{ 'url': 'https://www.mtv.fi/sarja/mtv-uutiset-live-33001002003/lahden-pelicans-teki-kovan-ratkaisun-ville-nieminen-pihalle-1181321', 'info_dict': { 'id': '1181321', 'ext': 'mp4', - 'title': 'MTV Uutiset Live', + 'title': 'Lahden Pelicans teki kovan ratkaisun – Ville Nieminen pihalle', 'description': 'Päätöksen teki Pelicansin hallitus.', 'timestamp': 1575116484, 'upload_date': '20191130', @@ -186,7 +189,60 @@ class KatsomoIE(TV2IE): # m3u8 download 'skip_download': True, }, - } + }, { + 'url': 'http://www.katsomo.fi/#!/jakso/33001005/studio55-fi/658521/jukka-kuoppamaki-tekee-yha-lauluja-vaikka-lentokoneessa', + 'only_matching': True, + }, { + 'url': 'https://www.mtvuutiset.fi/video/prog1311159', + 'only_matching': True, + }, { + 'url': 'https://www.katsomo.fi/#!/jakso/1311159', + 'only_matching': True, + }] _API_DOMAIN = 'api.katsomo.fi' _PROTOCOLS = ('HLS', 'MPD') _GEO_COUNTRIES = ['FI'] + + +class MTVUutisetArticleIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)mtvuutiset\.fi/artikkeli/[^/]+/(?P\d+)' + _TESTS = [{ + 'url': 'https://www.mtvuutiset.fi/artikkeli/tallaisia-vaurioita-viking-amorellassa-on-useamman-osaston-alla-vetta/7931384', + 'info_dict': { + 'id': '1311159', + 'ext': 'mp4', + 'title': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla', + 'description': 'Viking Amorellan matkustajien evakuointi on alkanut – tältä operaatio näyttää laivalla', + 'timestamp': 1600608966, + 'upload_date': '20200920', + 'duration': 153.7886666, + 'view_count': int, + 'categories': list, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + # multiple Youtube embeds + 'url': 'https://www.mtvuutiset.fi/artikkeli/50-vuotta-subarun-vastaiskua/6070962', + 'only_matching': True, + }] + + def _real_extract(self, url): + article_id = self._match_id(url) + article = self._download_json( + 'http://api.mtvuutiset.fi/mtvuutiset/api/json/' + article_id, + article_id) + + def entries(): + for video in (article.get('videos') or []): + video_type = video.get('videotype') + video_url = video.get('url') + if not (video_url and video_type in ('katsomo', 'youtube')): + continue + yield self.url_result( + video_url, video_type.capitalize(), video.get('video_id')) + + return self.playlist_result( + entries(), article_id, article.get('title'), article.get('description')) diff --git a/youtube_dlc/extractor/tv4.py b/youtube_dlc/extractor/tv4.py index c498b0191..b73bab9a8 100644 --- a/youtube_dlc/extractor/tv4.py +++ b/youtube_dlc/extractor/tv4.py @@ -17,7 +17,7 @@ class TV4IE(InfoExtractor): tv4\.se/(?:[^/]+)/klipp/(?:.*)-| tv4play\.se/ (?: - (?:program|barn)/(?:[^/]+/|(?:[^\?]+)\?video_id=)| + (?:program|barn)/(?:(?:[^/]+/){1,2}|(?:[^\?]+)\?video_id=)| iframe/video/| film/| sport/| @@ -65,6 +65,10 @@ class TV4IE(InfoExtractor): { 'url': 'http://www.tv4play.se/program/farang/3922081', 'only_matching': True, + }, + { + 'url': 'https://www.tv4play.se/program/nyheterna/avsnitt/13315940', + 'only_matching': True, } ] diff --git a/youtube_dlc/extractor/vidio.py b/youtube_dlc/extractor/vidio.py index b48baf00b..b1243e847 100644 --- a/youtube_dlc/extractor/vidio.py +++ b/youtube_dlc/extractor/vidio.py @@ -4,7 +4,13 @@ import re from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import ( + int_or_none, + parse_iso8601, + str_or_none, + strip_or_none, + try_get, +) class VidioIE(InfoExtractor): @@ -21,57 +27,63 @@ class VidioIE(InfoExtractor): 'thumbnail': r're:^https?://.*\.jpg$', 'duration': 149, 'like_count': int, + 'uploader': 'TWELVE Pic', + 'timestamp': 1444902800, + 'upload_date': '20151015', + 'uploader_id': 'twelvepictures', + 'channel': 'Cover Music Video', + 'channel_id': '280236', + 'view_count': int, + 'dislike_count': int, + 'comment_count': int, + 'tags': 'count:4', }, }, { 'url': 'https://www.vidio.com/watch/77949-south-korea-test-fires-missile-that-can-strike-all-of-the-north', 'only_matching': True, }] + def _real_initialize(self): + self._api_key = self._download_json( + 'https://www.vidio.com/auth', None, data=b'')['api_key'] + def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id, display_id = mobj.group('id', 'display_id') + video_id, display_id = re.match(self._VALID_URL, url).groups() + data = self._download_json( + 'https://api.vidio.com/videos/' + video_id, display_id, headers={ + 'Content-Type': 'application/vnd.api+json', + 'X-API-KEY': self._api_key, + }) + video = data['videos'][0] + title = video['title'].strip() - webpage = self._download_webpage(url, display_id) - - title = self._og_search_title(webpage) - - m3u8_url, duration, thumbnail = [None] * 3 - - clips = self._parse_json( - self._html_search_regex( - r'data-json-clips\s*=\s*(["\'])(?P\[.+?\])\1', - webpage, 'video data', default='[]', group='data'), - display_id, fatal=False) - if clips: - clip = clips[0] - m3u8_url = clip.get('sources', [{}])[0].get('file') - duration = clip.get('clip_duration') - thumbnail = clip.get('image') - - m3u8_url = m3u8_url or self._search_regex( - r'data(?:-vjs)?-clip-hls-url=(["\'])(?P(?:(?!\1).)+)\1', - webpage, 'hls url', group='url') formats = self._extract_m3u8_formats( - m3u8_url, display_id, 'mp4', entry_protocol='m3u8_native') + data['clips'][0]['hls_url'], display_id, 'mp4', 'm3u8_native') self._sort_formats(formats) - duration = int_or_none(duration or self._search_regex( - r'data-video-duration=(["\'])(?P\d+)\1', webpage, - 'duration', fatal=False, group='duration')) - thumbnail = thumbnail or self._og_search_thumbnail(webpage) - - like_count = int_or_none(self._search_regex( - (r']+data-comment-vote-count=["\'](\d+)', - r']+class=["\'].*?\blike(?:__|-)count\b.*?["\'][^>]*>\s*(\d+)'), - webpage, 'like count', fatal=False)) + get_first = lambda x: try_get(data, lambda y: y[x + 's'][0], dict) or {} + channel = get_first('channel') + user = get_first('user') + username = user.get('username') + get_count = lambda x: int_or_none(video.get('total_' + x)) return { 'id': video_id, 'display_id': display_id, 'title': title, - 'description': self._og_search_description(webpage), - 'thumbnail': thumbnail, - 'duration': duration, - 'like_count': like_count, + 'description': strip_or_none(video.get('description')), + 'thumbnail': video.get('image_url_medium'), + 'duration': int_or_none(video.get('duration')), + 'like_count': get_count('likes'), 'formats': formats, + 'uploader': user.get('name'), + 'timestamp': parse_iso8601(video.get('created_at')), + 'uploader_id': username, + 'uploader_url': 'https://www.vidio.com/@' + username if username else None, + 'channel': channel.get('name'), + 'channel_id': str_or_none(channel.get('id')), + 'view_count': get_count('view_count'), + 'dislike_count': get_count('dislikes'), + 'comment_count': get_count('comments'), + 'tags': video.get('tag_list'), } diff --git a/youtube_dlc/extractor/vlive.py b/youtube_dlc/extractor/vlive.py index fde6c0149..533bfd5da 100644 --- a/youtube_dlc/extractor/vlive.py +++ b/youtube_dlc/extractor/vlive.py @@ -125,7 +125,7 @@ def _call_api(self, path_template, video_id, fields=None, limit=None): headers={'Referer': 'https://www.vlive.tv/'}, query=query) except ExtractorError as e: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403: - self.raise_login_required(json.loads(e.cause.read().decode())['message']) + self.raise_login_required(json.loads(e.cause.read().decode('utf-8'))['message']) raise def _real_extract(self, url): diff --git a/youtube_dlc/extractor/vtm.py b/youtube_dlc/extractor/vtm.py new file mode 100644 index 000000000..093f1aa69 --- /dev/null +++ b/youtube_dlc/extractor/vtm.py @@ -0,0 +1,62 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from .common import InfoExtractor +from ..utils import ( + int_or_none, + parse_iso8601, + try_get, +) + + +class VTMIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?vtm\.be/([^/?&#]+)~v(?P[0-9a-f]{8}(?:-[0-9a-f]{4}){3}-[0-9a-f]{12})' + _TEST = { + 'url': 'https://vtm.be/gast-vernielt-genkse-hotelkamer~ve7534523-279f-4b4d-a5c9-a33ffdbe23e1', + 'md5': '37dca85fbc3a33f2de28ceb834b071f8', + 'info_dict': { + 'id': '192445', + 'ext': 'mp4', + 'title': 'Gast vernielt Genkse hotelkamer', + 'timestamp': 1611060180, + 'upload_date': '20210119', + 'duration': 74, + # TODO: fix url _type result processing + # 'series': 'Op Interventie', + } + } + + def _real_extract(self, url): + uuid = self._match_id(url) + video = self._download_json( + 'https://omc4vm23offuhaxx6hekxtzspi.appsync-api.eu-west-1.amazonaws.com/graphql', + uuid, query={ + 'query': '''{ + getComponent(type: Video, uuid: "%s") { + ... on Video { + description + duration + myChannelsVideo + program { + title + } + publishedAt + title + } + } +}''' % uuid, + }, headers={ + 'x-api-key': 'da2-lz2cab4tfnah3mve6wiye4n77e', + })['data']['getComponent'] + + return { + '_type': 'url', + 'id': uuid, + 'title': video.get('title'), + 'url': 'http://mychannels.video/embed/%d' % video['myChannelsVideo'], + 'description': video.get('description'), + 'timestamp': parse_iso8601(video.get('publishedAt')), + 'duration': int_or_none(video.get('duration')), + 'series': try_get(video, lambda x: x['program']['title']), + 'ie_key': 'Medialaan', + } diff --git a/youtube_dlc/extractor/vvvvid.py b/youtube_dlc/extractor/vvvvid.py index f4cae7fe9..778ce8b76 100644 --- a/youtube_dlc/extractor/vvvvid.py +++ b/youtube_dlc/extractor/vvvvid.py @@ -4,6 +4,7 @@ import re from .common import InfoExtractor +from .youtube import YoutubeIE from ..utils import ( ExtractorError, int_or_none, @@ -47,6 +48,22 @@ class VVVVIDIE(InfoExtractor): 'params': { 'skip_download': True, }, + }, { + # video_type == 'video/youtube' + 'url': 'https://www.vvvvid.it/show/404/one-punch-man/406/486683/trailer', + 'md5': '33e0edfba720ad73a8782157fdebc648', + 'info_dict': { + 'id': 'RzmFKUDOUgw', + 'ext': 'mp4', + 'title': 'Trailer', + 'upload_date': '20150906', + 'description': 'md5:a5e802558d35247fee285875328c0b80', + 'uploader_id': 'BandaiVisual', + 'uploader': 'BANDAI NAMCO Arts Channel', + }, + 'params': { + 'skip_download': True, + }, }, { 'url': 'https://www.vvvvid.it/show/434/perche-dovrei-guardarlo-di-dario-moccia/437/489048', 'only_matching': True @@ -154,12 +171,13 @@ def metadata_from_url(r_url): if season_number: info['season_number'] = int(season_number) - for quality in ('_sd', ''): + video_type = video_data.get('video_type') + is_youtube = False + for quality in ('', '_sd'): embed_code = video_data.get('embed_info' + quality) if not embed_code: continue embed_code = ds(embed_code) - video_type = video_data.get('video_type') if video_type in ('video/rcs', 'video/kenc'): if video_type == 'video/kenc': kenc = self._download_json( @@ -172,19 +190,28 @@ def metadata_from_url(r_url): if kenc_message: embed_code += '?' + ds(kenc_message) formats.extend(self._extract_akamai_formats(embed_code, video_id)) + elif video_type == 'video/youtube': + info.update({ + '_type': 'url_transparent', + 'ie_key': YoutubeIE.ie_key(), + 'url': embed_code, + }) + is_youtube = True + break else: formats.extend(self._extract_wowza_formats( 'http://sb.top-ix.org/videomg/_definst_/mp4:%s/playlist.m3u8' % embed_code, video_id)) metadata_from_url(embed_code) - self._sort_formats(formats) + if not is_youtube: + self._sort_formats(formats) + info['formats'] = formats metadata_from_url(video_data.get('thumbnail')) info.update(self._extract_common_video_info(video_data)) info.update({ 'id': video_id, 'title': title, - 'formats': formats, 'duration': int_or_none(video_data.get('length')), 'series': video_data.get('show_title'), 'season_id': season_id, diff --git a/youtube_dlc/extractor/zype.py b/youtube_dlc/extractor/zype.py index 5288f40d8..f20f953cb 100644 --- a/youtube_dlc/extractor/zype.py +++ b/youtube_dlc/extractor/zype.py @@ -87,11 +87,16 @@ def _real_extract(self, url): r'(["\'])(?P(?:(?!\1).)+\.m3u8(?:(?!\1).)*)\1', body, 'm3u8 url', group='url', default=None) if not m3u8_url: - source = self._parse_json(self._search_regex( - r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', body, - 'source'), video_id, js_to_json) - if source.get('integration') == 'verizon-media': - m3u8_url = 'https://content.uplynk.com/%s.m3u8' % source['id'] + source = self._search_regex( + r'(?s)sources\s*:\s*\[\s*({.+?})\s*\]', body, 'source') + + def get_attr(key): + return self._search_regex( + r'\b%s\s*:\s*([\'"])(?P(?:(?!\1).)+)\1' % key, + source, key, group='val') + + if get_attr('integration') == 'verizon-media': + m3u8_url = 'https://content.uplynk.com/%s.m3u8' % get_attr('id') formats = self._extract_m3u8_formats( m3u8_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls') text_tracks = self._search_regex(