@tushar-br/desktop 1.0.282 → 1.0.283

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/bostonglobe.py

@@ -0,0 +1,69 @@
+import re
+
+from .common import InfoExtractor
+
+from ..utils import (
+    extract_attributes,
+)
+
+
+class BostonGlobeIE(InfoExtractor):
+    _VALID_URL = r'(?i)https?://(?:www\.)?bostonglobe\.com/.*/(?P<id>[^/]+)/\w+(?:\.html)?'
+    _TESTS = [
+        {
+            'url': 'http://www.bostonglobe.com/metro/2017/02/11/tree-finally-succumbs-disease-leaving-hole-neighborhood/h1b4lviqzMTIn9sVy8F3gP/story.html',
+            'md5': '0a62181079c85c2d2b618c9a738aedaf',
+            'info_dict': {
+                'title': 'A tree finally succumbs to disease, leaving a hole in a neighborhood',
+                'id': '5320421710001',
+                'ext': 'mp4',
+                'description': 'It arrived as a sapling when the Back Bay was in its infancy, a spindly American elm tamped down into a square of dirt cut into the brick sidewalk of 1880s Marlborough Street, no higher than the first bay window of the new brownstone behind it.',
+                'timestamp': 1486877593,
+                'upload_date': '20170212',
+                'uploader_id': '245991542',
+            },
+        },
+        {
+            # Embedded youtube video; we hand it off to the Generic extractor.
+            'url': 'https://www.bostonglobe.com/lifestyle/names/2017/02/17/does-ben-affleck-play-matt-damon-favorite-version-batman/ruqkc9VxKBYmh5txn1XhSI/story.html',
+            'md5': '582b40327089d5c0c949b3c54b13c24b',
+            'info_dict': {
+                'title': "Who Is Matt Damon's Favorite Batman?",
+                'id': 'ZW1QCnlA6Qc',
+                'ext': 'mp4',
+                'upload_date': '20170217',
+                'description': 'md5:3b3dccb9375867e0b4d527ed87d307cb',
+                'uploader': 'The Late Late Show with James Corden',
+                'uploader_id': 'TheLateLateShow',
+            },
+            'expected_warnings': ['404'],
+        },
+    ]
+
+    def _real_extract(self, url):
+        page_id = self._match_id(url)
+        webpage = self._download_webpage(url, page_id)
+
+        page_title = self._og_search_title(webpage, default=None)
+
+        # <video data-brightcove-video-id="5320421710001" data-account="245991542" data-player="SJWAiyYWg" data-embed="default" class="video-js" controls itemscope itemtype="http://schema.org/VideoObject">
+        entries = []
+        for video in re.findall(r'(?i)(<video[^>]+>)', webpage):
+            attrs = extract_attributes(video)
+
+            video_id = attrs.get('data-brightcove-video-id')
+            account_id = attrs.get('data-account')
+            player_id = attrs.get('data-player')
+            embed = attrs.get('data-embed')
+
+            if video_id and account_id and player_id and embed:
+                entries.append(
+                    'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
+                    % (account_id, player_id, embed, video_id))
+
+        if len(entries) == 0:
+            return self.url_result(url, 'Generic')
+        elif len(entries) == 1:
+            return self.url_result(entries[0], 'BrightcoveNew')
+        else:
+            return self.playlist_from_matches(entries, page_id, page_title, ie='BrightcoveNew')

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/box.py

@@ -0,0 +1,83 @@
+import json
+import urllib.parse
+
+from .common import InfoExtractor
+from ..utils import (
+    parse_iso8601,
+    update_url_query,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class BoxIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^.]+\.)?app\.box\.com/s/(?P<shared_name>[^/?#]+)/file/(?P<id>\d+)'
+    _TEST = {
+        'url': 'https://mlssoccer.app.box.com/s/0evd2o3e08l60lr4ygukepvnkord1o1x/file/510727257538',
+        'md5': '1f81b2fd3960f38a40a3b8823e5fcd43',
+        'info_dict': {
+            'id': '510727257538',
+            'ext': 'mp4',
+            'title': 'Garber   St. Louis will be 28th MLS team  +scarving.mp4',
+            'uploader': '',
+            'timestamp': 1566320259,
+            'upload_date': '20190820',
+            'uploader_id': '235196876',
+        },
+        'params': {'skip_download': 'dash fragment too small'},
+    }
+
+    def _real_extract(self, url):
+        shared_name, file_id = self._match_valid_url(url).groups()
+        webpage = self._download_webpage(url, file_id)
+        request_token = self._parse_json(self._search_regex(
+            r'Box\.config\s*=\s*({.+?});', webpage,
+            'Box config'), file_id)['requestToken']
+        access_token = self._download_json(
+            'https://app.box.com/app-api/enduserapp/elements/tokens', file_id,
+            'Downloading token JSON metadata',
+            data=json.dumps({'fileIDs': [file_id]}).encode(), headers={
+                'Content-Type': 'application/json',
+                'X-Request-Token': request_token,
+                'X-Box-EndUser-API': 'sharedName=' + shared_name,
+            })[file_id]['read']
+        shared_link = 'https://app.box.com/s/' + shared_name
+        f = self._download_json(
+            'https://api.box.com/2.0/files/' + file_id, file_id,
+            'Downloading file JSON metadata', headers={
+                'Authorization': 'Bearer ' + access_token,
+                'BoxApi': 'shared_link=' + shared_link,
+                'X-Rep-Hints': '[dash]',  # TODO: extract `hls` formats
+            }, query={
+                'fields': 'authenticated_download_url,created_at,created_by,description,extension,is_download_available,name,representations,size'
+            })
+        title = f['name']
+
+        query = {
+            'access_token': access_token,
+            'shared_link': shared_link
+        }
+
+        formats = []
+
+        for url_tmpl in traverse_obj(f, (
+            'representations', 'entries', lambda _, v: v['representation'] == 'dash',
+            'content', 'url_template', {url_or_none}
+        )):
+            manifest_url = update_url_query(url_tmpl.replace('{+asset_path}', 'manifest.mpd'), query)
+            fmts = self._extract_mpd_formats(manifest_url, file_id)
+            for fmt in fmts:
+                fmt['extra_param_to_segment_url'] = urllib.parse.urlparse(manifest_url).query
+            formats.extend(fmts)
+
+        creator = f.get('created_by') or {}
+
+        return {
+            'id': file_id,
+            'title': title,
+            'formats': formats,
+            'description': f.get('description') or None,
+            'uploader': creator.get('name'),
+            'timestamp': parse_iso8601(f.get('created_at')),
+            'uploader_id': creator.get('id'),
+        }

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/boxcast.py

@@ -0,0 +1,102 @@
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    traverse_obj,
+    unified_timestamp
+)
+
+
+class BoxCastVideoIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://boxcast\.tv/(?:
+            view-embed/|
+            channel/\w+\?(?:[^#]+&)?b=|
+            video-portal/(?:\w+/){2}
+        )(?P<id>[\w-]+)'''
+    _EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>https?://boxcast\.tv/view-embed/[\w-]+)']
+    _TESTS = [{
+        'url': 'https://boxcast.tv/view-embed/in-the-midst-of-darkness-light-prevails-an-interdisciplinary-symposium-ozmq5eclj50ujl4bmpwx',
+        'info_dict': {
+            'id': 'da1eqqgkacngd5djlqld',
+            'ext': 'mp4',
+            'thumbnail': r're:https?://uploads\.boxcast\.com/(?:[\w+-]+/){3}.+\.png$',
+            'title': 'In the Midst of Darkness Light Prevails: An Interdisciplinary Symposium',
+            'release_timestamp': 1670686812,
+            'release_date': '20221210',
+            'uploader_id': 're8w0v8hohhvpqtbskpe',
+            'uploader': 'Children\'s Health Defense',
+        }
+    }, {
+        'url': 'https://boxcast.tv/video-portal/vctwevwntun3o0ikq7af/rvyblnn0fxbfjx5nwxhl/otbpltj2kzkveo2qz3ad',
+        'info_dict': {
+            'id': 'otbpltj2kzkveo2qz3ad',
+            'ext': 'mp4',
+            'uploader_id': 'vctwevwntun3o0ikq7af',
+            'uploader': 'Legacy Christian Church',
+            'title': 'The Quest | 1: Beginner\'s Bay | Jamie Schools',
+            'thumbnail': r're:https?://uploads.boxcast.com/(?:[\w-]+/){3}.+\.jpg'
+        }
+    }, {
+        'url': 'https://boxcast.tv/channel/z03fqwaeaby5lnaawox2?b=ssihlw5gvfij2by8tkev',
+        'info_dict': {
+            'id': 'ssihlw5gvfij2by8tkev',
+            'ext': 'mp4',
+            'thumbnail': r're:https?://uploads.boxcast.com/(?:[\w-]+/){3}.+\.jpg$',
+            'release_date': '20230101',
+            'uploader_id': 'ds25vaazhlu4ygcvffid',
+            'release_timestamp': 1672543201,
+            'uploader': 'Lighthouse Ministries International  - Beltsville, Maryland',
+            'description': 'md5:ac23e3d01b0b0be592e8f7fe0ec3a340',
+            'title': 'New Year\'s Eve CROSSOVER Service at LHMI | December 31, 2022',
+        }
+    }]
+    _WEBPAGE_TESTS = [{
+        'url': 'https://childrenshealthdefense.eu/live-stream/',
+        'info_dict': {
+            'id': 'da1eqqgkacngd5djlqld',
+            'ext': 'mp4',
+            'thumbnail': r're:https?://uploads\.boxcast\.com/(?:[\w+-]+/){3}.+\.png$',
+            'title': 'In the Midst of Darkness Light Prevails: An Interdisciplinary Symposium',
+            'release_timestamp': 1670686812,
+            'release_date': '20221210',
+            'uploader_id': 're8w0v8hohhvpqtbskpe',
+            'uploader': 'Children\'s Health Defense',
+        }
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        webpage_json_data = self._search_json(
+            r'var\s*BOXCAST_PRELOAD\s*=', webpage, 'broadcast data', display_id,
+            transform_source=js_to_json, default={})
+
+        # Ref: https://support.boxcast.com/en/articles/4235158-build-a-custom-viewer-experience-with-boxcast-api
+        broadcast_json_data = (
+            traverse_obj(webpage_json_data, ('broadcast', 'data'))
+            or self._download_json(f'https://api.boxcast.com/broadcasts/{display_id}', display_id))
+        view_json_data = (
+            traverse_obj(webpage_json_data, ('view', 'data'))
+            or self._download_json(f'https://api.boxcast.com/broadcasts/{display_id}/view',
+                                   display_id, fatal=False) or {})
+
+        formats, subtitles = [], {}
+        if view_json_data.get('status') == 'recorded':
+            formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+                view_json_data['playlist'], display_id)
+
+        return {
+            'id': str(broadcast_json_data['id']),
+            'title': (broadcast_json_data.get('name')
+                      or self._html_search_meta(['og:title', 'twitter:title'], webpage)),
+            'description': (broadcast_json_data.get('description')
+                            or self._html_search_meta(['og:description', 'twitter:description'], webpage)
+                            or None),
+            'thumbnail': (broadcast_json_data.get('preview')
+                          or self._html_search_meta(['og:image', 'twitter:image'], webpage)),
+            'formats': formats,
+            'subtitles': subtitles,
+            'release_timestamp': unified_timestamp(broadcast_json_data.get('streamed_at')),
+            'uploader': broadcast_json_data.get('account_name'),
+            'uploader_id': broadcast_json_data.get('account_id'),
+        }

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/bpb.py

@@ -0,0 +1,170 @@
+import functools
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    extract_attributes,
+    get_element_text_and_html_by_tag,
+    get_elements_by_class,
+    join_nonempty,
+    js_to_json,
+    mimetype2ext,
+    unified_strdate,
+    url_or_none,
+    urljoin,
+    variadic,
+)
+from ..utils.traversal import traverse_obj
+
+
+def html_get_element(tag=None, cls=None):
+    assert tag or cls, 'One of tag or class is required'
+
+    if cls:
+        func = functools.partial(get_elements_by_class, cls, tag=tag)
+    else:
+        func = functools.partial(get_element_text_and_html_by_tag, tag)
+
+    def html_get_element_wrapper(html):
+        return variadic(func(html))[0]
+
+    return html_get_element_wrapper
+
+
+class BpbIE(InfoExtractor):
+    IE_DESC = 'Bundeszentrale für politische Bildung'
+    _VALID_URL = r'https?://(?:www\.|m\.)?bpb\.de/(?:[^/?#]+/)*(?P<id>\d+)(?:[/?#]|$)'
+
+    _TESTS = [{
+        'url': 'http://www.bpb.de/mediathek/297/joachim-gauck-zu-1989-und-die-erinnerung-an-die-ddr',
+        'info_dict': {
+            'id': '297',
+            'ext': 'mp4',
+            'creator': 'Kooperative Berlin',
+            'description': 'md5:f4f75885ba009d3e2b156247a8941ce6',
+            'release_date': '20160115',
+            'series': 'Interview auf dem Geschichtsforum 1989 | 2009',
+            'tags': ['Friedliche Revolution', 'Erinnerungskultur', 'Vergangenheitspolitik', 'DDR 1949 - 1990', 'Freiheitsrecht', 'BStU', 'Deutschland'],
+            'thumbnail': 'https://www.bpb.de/cache/images/7/297_teaser_16x9_1240.jpg?8839D',
+            'title': 'Joachim Gauck zu 1989 und die Erinnerung an die DDR',
+            'uploader': 'Bundeszentrale für politische Bildung',
+        },
+    }, {
+        'url': 'https://www.bpb.de/mediathek/video/522184/krieg-flucht-und-falschmeldungen-wirstattdesinformation-2/',
+        'info_dict': {
+            'id': '522184',
+            'ext': 'mp4',
+            'creator': 'Institute for Strategic Dialogue Germany gGmbH (ISD)',
+            'description': 'md5:f83c795ff8f825a69456a9e51fc15903',
+            'release_date': '20230621',
+            'tags': ['Desinformation', 'Ukraine', 'Russland', 'Geflüchtete'],
+            'thumbnail': 'https://www.bpb.de/cache/images/4/522184_teaser_16x9_1240.png?EABFB',
+            'title': 'md5:9b01ccdbf58dbf9e5c9f6e771a803b1c',
+            'uploader': 'Bundeszentrale für politische Bildung',
+        },
+    }, {
+        'url': 'https://www.bpb.de/lernen/bewegtbild-und-politische-bildung/webvideo/518789/krieg-flucht-und-falschmeldungen-wirstattdesinformation-1/',
+        'info_dict': {
+            'id': '518789',
+            'ext': 'mp4',
+            'creator': 'Institute for Strategic Dialogue Germany gGmbH (ISD)',
+            'description': 'md5:85228aed433e84ff0ff9bc582abd4ea8',
+            'release_date': '20230302',
+            'tags': ['Desinformation', 'Ukraine', 'Russland', 'Geflüchtete'],
+            'thumbnail': 'https://www.bpb.de/cache/images/9/518789_teaser_16x9_1240.jpeg?56D0D',
+            'title': 'md5:3e956f264bb501f6383f10495a401da4',
+            'uploader': 'Bundeszentrale für politische Bildung',
+        },
+    }, {
+        'url': 'https://www.bpb.de/mediathek/podcasts/apuz-podcast/539727/apuz-20-china/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.bpb.de/mediathek/audio/315813/folge-1-eine-einfuehrung/',
+        'info_dict': {
+            'id': '315813',
+            'ext': 'mp3',
+            'creator': 'Axel Schröder',
+            'description': 'md5:eda9d1af34e5912efef5baf54fba4427',
+            'release_date': '20200921',
+            'series': 'Auf Endlagersuche. Der deutsche Weg zu einem sicheren Atommülllager',
+            'tags': ['Atomenergie', 'Endlager', 'hoch-radioaktiver Abfall', 'Endlagersuche', 'Atommüll', 'Atomendlager', 'Gorleben', 'Deutschland'],
+            'thumbnail': 'https://www.bpb.de/cache/images/3/315813_teaser_16x9_1240.png?92A94',
+            'title': 'Folge 1: Eine Einführung',
+            'uploader': 'Bundeszentrale für politische Bildung',
+        },
+    }, {
+        'url': 'https://www.bpb.de/517806/die-weltanschauung-der-neuen-rechten/',
+        'info_dict': {
+            'id': '517806',
+            'ext': 'mp3',
+            'creator': 'Bundeszentrale für politische Bildung',
+            'description': 'md5:594689600e919912aade0b2871cc3fed',
+            'release_date': '20230127',
+            'series': 'Vorträge des Fachtags "Modernisierer. Grenzgänger. Anstifter. Sechs Jahrzehnte \'Neue Rechte\'"',
+            'tags': ['Rechtsextremismus', 'Konservatismus', 'Konservativismus', 'neue Rechte', 'Rechtspopulismus', 'Schnellroda', 'Deutschland'],
+            'thumbnail': 'https://www.bpb.de/cache/images/6/517806_teaser_16x9_1240.png?7A7A0',
+            'title': 'Die Weltanschauung der "Neuen Rechten"',
+            'uploader': 'Bundeszentrale für politische Bildung',
+        },
+    }, {
+        'url': 'https://www.bpb.de/mediathek/reihen/zahlen-und-fakten-soziale-situation-filme/520153/zahlen-und-fakten-die-soziale-situation-in-deutschland-migration/',
+        'only_matching': True,
+    }]
+
+    _TITLE_RE = re.compile('(?P<title>[^<]*)<[^>]+>(?P<series>[^<]*)')
+
+    def _parse_vue_attributes(self, name, string, video_id):
+        attributes = extract_attributes(self._search_regex(rf'(<{name}(?:"[^"]*?"|[^>])*>)', string, name))
+
+        for key, value in attributes.items():
+            if key.startswith(':'):
+                attributes[key] = self._parse_json(value, video_id, transform_source=js_to_json, fatal=False)
+
+        return attributes
+
+    @staticmethod
+    def _process_source(source):
+        url = url_or_none(source['src'])
+        if not url:
+            return None
+
+        source_type = source.get('type', '')
+        extension = mimetype2ext(source_type)
+        is_video = source_type.startswith('video')
+        note = url.rpartition('.')[0].rpartition('_')[2] if is_video else None
+
+        return {
+            'url': url,
+            'ext': extension,
+            'vcodec': None if is_video else 'none',
+            'quality': 10 if note == 'high' else 0,
+            'format_note': note,
+            'format_id': join_nonempty(extension, note),
+        }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title_result = traverse_obj(webpage, ({html_get_element(cls='opening-header__title')}, {self._TITLE_RE.match}))
+        json_lds = list(self._yield_json_ld(webpage, video_id, fatal=False))
+
+        return {
+            'id': video_id,
+            'title': traverse_obj(title_result, ('title', {str.strip})) or None,
+            # This metadata could be interpreted otherwise, but it fits "series" the most
+            'series': traverse_obj(title_result, ('series', {str.strip})) or None,
+            'description': join_nonempty(*traverse_obj(webpage, [(
+                {html_get_element(cls='opening-intro')},
+                [{html_get_element(tag='bpb-accordion-item')}, {html_get_element(cls='text-content')}],
+            ), {clean_html}]), delim='\n\n') or None,
+            'creator': self._html_search_meta('author', webpage),
+            'uploader': self._html_search_meta('publisher', webpage),
+            'release_date': unified_strdate(self._html_search_meta('date', webpage)),
+            'tags': traverse_obj(json_lds, (..., 'keywords', {lambda x: x.split(',')}, ...)),
+            **traverse_obj(self._parse_vue_attributes('bpb-player', webpage, video_id), {
+                'formats': (':sources', ..., {self._process_source}),
+                'thumbnail': ('poster', {lambda x: urljoin(url, x)}),
+            }),
+        }

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/br.py

@@ -0,0 +1,166 @@
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    parse_duration,
+    xpath_element,
+    xpath_text,
+)
+
+
+class BRIE(InfoExtractor):
+    _WORKING = False
+    IE_DESC = 'Bayerischer Rundfunk'
+    _VALID_URL = r'(?P<base_url>https?://(?:www\.)?br(?:-klassik)?\.de)/(?:[a-z0-9\-_]+/)+(?P<id>[a-z0-9\-_]+)\.html'
+
+    _TESTS = [
+        {
+            'url': 'http://www.br.de/mediathek/video/sendungen/abendschau/betriebliche-altersvorsorge-104.html',
+            'md5': '83a0477cf0b8451027eb566d88b51106',
+            'info_dict': {
+                'id': '48f656ef-287e-486f-be86-459122db22cc',
+                'ext': 'mp4',
+                'title': 'Die böse Überraschung',
+                'description': 'md5:ce9ac81b466ce775b8018f6801b48ac9',
+                'duration': 180,
+                'uploader': 'Reinhard Weber',
+                'upload_date': '20150422',
+            },
+            'skip': '404 not found',
+        },
+        {
+            'url': 'http://www.br.de/nachrichten/oberbayern/inhalt/muenchner-polizeipraesident-schreiber-gestorben-100.html',
+            'md5': 'af3a3a4aa43ff0ce6a89504c67f427ef',
+            'info_dict': {
+                'id': 'a4b83e34-123d-4b81-9f4e-c0d3121a4e05',
+                'ext': 'flv',
+                'title': 'Manfred Schreiber ist tot',
+                'description': 'md5:b454d867f2a9fc524ebe88c3f5092d97',
+                'duration': 26,
+            },
+            'skip': '404 not found',
+        },
+        {
+            'url': 'https://www.br-klassik.de/audio/peeping-tom-premierenkritik-dance-festival-muenchen-100.html',
+            'md5': '8b5b27c0b090f3b35eac4ab3f7a73d3d',
+            'info_dict': {
+                'id': '74c603c9-26d3-48bb-b85b-079aeed66e0b',
+                'ext': 'aac',
+                'title': 'Kurzweilig und sehr bewegend',
+                'description': 'md5:0351996e3283d64adeb38ede91fac54e',
+                'duration': 296,
+            },
+            'skip': '404 not found',
+        },
+        {
+            'url': 'http://www.br.de/radio/bayern1/service/team/videos/team-video-erdelt100.html',
+            'md5': 'dbab0aef2e047060ea7a21fc1ce1078a',
+            'info_dict': {
+                'id': '6ba73750-d405-45d3-861d-1ce8c524e059',
+                'ext': 'mp4',
+                'title': 'Umweltbewusster Häuslebauer',
+                'description': 'md5:d52dae9792d00226348c1dbb13c9bae2',
+                'duration': 116,
+            }
+        },
+        {
+            'url': 'http://www.br.de/fernsehen/br-alpha/sendungen/kant-fuer-anfaenger/kritik-der-reinen-vernunft/kant-kritik-01-metaphysik100.html',
+            'md5': '23bca295f1650d698f94fc570977dae3',
+            'info_dict': {
+                'id': 'd982c9ce-8648-4753-b358-98abb8aec43d',
+                'ext': 'mp4',
+                'title': 'Folge 1 - Metaphysik',
+                'description': 'md5:bb659990e9e59905c3d41e369db1fbe3',
+                'duration': 893,
+                'uploader': 'Eva Maria Steimle',
+                'upload_date': '20170208',
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        base_url, display_id = self._match_valid_url(url).groups()
+        page = self._download_webpage(url, display_id)
+        xml_url = self._search_regex(
+            r"return BRavFramework\.register\(BRavFramework\('avPlayer_(?:[a-f0-9-]{36})'\)\.setup\({dataURL:'(/(?:[a-z0-9\-]+/)+[a-z0-9/~_.-]+)'}\)\);", page, 'XMLURL')
+        xml = self._download_xml(base_url + xml_url, display_id)
+
+        medias = []
+
+        for xml_media in xml.findall('video') + xml.findall('audio'):
+            media_id = xml_media.get('externalId')
+            media = {
+                'id': media_id,
+                'title': xpath_text(xml_media, 'title', 'title', True),
+                'duration': parse_duration(xpath_text(xml_media, 'duration')),
+                'formats': self._extract_formats(xpath_element(
+                    xml_media, 'assets'), media_id),
+                'thumbnails': self._extract_thumbnails(xpath_element(
+                    xml_media, 'teaserImage/variants'), base_url),
+                'description': xpath_text(xml_media, 'desc'),
+                'webpage_url': xpath_text(xml_media, 'permalink'),
+                'uploader': xpath_text(xml_media, 'author'),
+            }
+            broadcast_date = xpath_text(xml_media, 'broadcastDate')
+            if broadcast_date:
+                media['upload_date'] = ''.join(reversed(broadcast_date.split('.')))
+            medias.append(media)
+
+        if len(medias) > 1:
+            self.report_warning(
+                'found multiple medias; please '
+                'report this with the video URL to http://yt-dl.org/bug')
+        if not medias:
+            raise ExtractorError('No media entries found')
+        return medias[0]
+
+    def _extract_formats(self, assets, media_id):
+        formats = []
+        for asset in assets.findall('asset'):
+            format_url = xpath_text(asset, ['downloadUrl', 'url'])
+            asset_type = asset.get('type')
+            if asset_type.startswith('HDS'):
+                formats.extend(self._extract_f4m_formats(
+                    format_url + '?hdcore=3.2.0', media_id, f4m_id='hds', fatal=False))
+            elif asset_type.startswith('HLS'):
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, media_id, 'mp4', 'm3u8_native', m3u8_id='hds', fatal=False))
+            else:
+                format_info = {
+                    'ext': xpath_text(asset, 'mediaType'),
+                    'width': int_or_none(xpath_text(asset, 'frameWidth')),
+                    'height': int_or_none(xpath_text(asset, 'frameHeight')),
+                    'tbr': int_or_none(xpath_text(asset, 'bitrateVideo')),
+                    'abr': int_or_none(xpath_text(asset, 'bitrateAudio')),
+                    'vcodec': xpath_text(asset, 'codecVideo'),
+                    'acodec': xpath_text(asset, 'codecAudio'),
+                    'container': xpath_text(asset, 'mediaType'),
+                    'filesize': int_or_none(xpath_text(asset, 'size')),
+                }
+                format_url = self._proto_relative_url(format_url)
+                if format_url:
+                    http_format_info = format_info.copy()
+                    http_format_info.update({
+                        'url': format_url,
+                        'format_id': 'http-%s' % asset_type,
+                    })
+                    formats.append(http_format_info)
+                server_prefix = xpath_text(asset, 'serverPrefix')
+                if server_prefix:
+                    rtmp_format_info = format_info.copy()
+                    rtmp_format_info.update({
+                        'url': server_prefix,
+                        'play_path': xpath_text(asset, 'fileName'),
+                        'format_id': 'rtmp-%s' % asset_type,
+                    })
+                    formats.append(rtmp_format_info)
+        return formats
+
+    def _extract_thumbnails(self, variants, base_url):
+        thumbnails = [{
+            'url': base_url + xpath_text(variant, 'url'),
+            'width': int_or_none(xpath_text(variant, 'width')),
+            'height': int_or_none(xpath_text(variant, 'height')),
+        } for variant in variants.findall('variant') if xpath_text(variant, 'url')]
+        thumbnails.sort(key=lambda x: x['width'] * x['height'], reverse=True)
+        return thumbnails