@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/spreaker.py

@@ -0,0 +1,173 @@
+import itertools
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    str_or_none,
+    try_get,
+    unified_timestamp,
+    url_or_none,
+)
+
+
+def _extract_episode(data, episode_id=None):
+    title = data['title']
+    download_url = data['download_url']
+
+    series = try_get(data, lambda x: x['show']['title'], compat_str)
+    uploader = try_get(data, lambda x: x['author']['fullname'], compat_str)
+
+    thumbnails = []
+    for image in ('image_original', 'image_medium', 'image'):
+        image_url = url_or_none(data.get('%s_url' % image))
+        if image_url:
+            thumbnails.append({'url': image_url})
+
+    def stats(key):
+        return int_or_none(try_get(
+            data,
+            (lambda x: x['%ss_count' % key],
+             lambda x: x['stats']['%ss' % key])))
+
+    def duration(key):
+        return float_or_none(data.get(key), scale=1000)
+
+    return {
+        'id': compat_str(episode_id or data['episode_id']),
+        'url': download_url,
+        'display_id': data.get('permalink'),
+        'title': title,
+        'description': data.get('description'),
+        'timestamp': unified_timestamp(data.get('published_at')),
+        'uploader': uploader,
+        'uploader_id': str_or_none(data.get('author_id')),
+        'creator': uploader,
+        'duration': duration('duration') or duration('length'),
+        'view_count': stats('play'),
+        'like_count': stats('like'),
+        'comment_count': stats('message'),
+        'format': 'MPEG Layer 3',
+        'format_id': 'mp3',
+        'container': 'mp3',
+        'ext': 'mp3',
+        'thumbnails': thumbnails,
+        'series': series,
+        'extractor_key': SpreakerIE.ie_key(),
+    }
+
+
+class SpreakerIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        api\.spreaker\.com/
+                        (?:
+                            (?:download/)?episode|
+                            v2/episodes
+                        )/
+                        (?P<id>\d+)
+                    '''
+    _TESTS = [{
+        'url': 'https://api.spreaker.com/episode/12534508',
+        'info_dict': {
+            'id': '12534508',
+            'display_id': 'swm-ep15-how-to-market-your-music-part-2',
+            'ext': 'mp3',
+            'title': 'EP:15 | Music Marketing (Likes) - Part 2',
+            'description': 'md5:0588c43e27be46423e183076fa071177',
+            'timestamp': 1502250336,
+            'upload_date': '20170809',
+            'uploader': 'SWM',
+            'uploader_id': '9780658',
+            'duration': 1063.42,
+            'view_count': int,
+            'like_count': int,
+            'comment_count': int,
+            'series': 'Success With Music (SWM)',
+        },
+    }, {
+        'url': 'https://api.spreaker.com/download/episode/12534508/swm_ep15_how_to_market_your_music_part_2.mp3',
+        'only_matching': True,
+    }, {
+        'url': 'https://api.spreaker.com/v2/episodes/12534508?export=episode_segments',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        episode_id = self._match_id(url)
+        data = self._download_json(
+            'https://api.spreaker.com/v2/episodes/%s' % episode_id,
+            episode_id)['response']['episode']
+        return _extract_episode(data, episode_id)
+
+
+class SpreakerPageIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?spreaker\.com/user/[^/]+/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.spreaker.com/user/9780658/swm-ep15-how-to-market-your-music-part-2',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        episode_id = self._search_regex(
+            (r'data-episode_id=["\'](?P<id>\d+)',
+             r'episode_id\s*:\s*(?P<id>\d+)'), webpage, 'episode id')
+        return self.url_result(
+            'https://api.spreaker.com/episode/%s' % episode_id,
+            ie=SpreakerIE.ie_key(), video_id=episode_id)
+
+
+class SpreakerShowIE(InfoExtractor):
+    _VALID_URL = r'https?://api\.spreaker\.com/show/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://api.spreaker.com/show/4652058',
+        'info_dict': {
+            'id': '4652058',
+        },
+        'playlist_mincount': 118,
+    }]
+
+    def _entries(self, show_id):
+        for page_num in itertools.count(1):
+            episodes = self._download_json(
+                'https://api.spreaker.com/show/%s/episodes' % show_id,
+                show_id, note='Downloading JSON page %d' % page_num, query={
+                    'page': page_num,
+                    'max_per_page': 100,
+                })
+            pager = try_get(episodes, lambda x: x['response']['pager'], dict)
+            if not pager:
+                break
+            results = pager.get('results')
+            if not results or not isinstance(results, list):
+                break
+            for result in results:
+                if not isinstance(result, dict):
+                    continue
+                yield _extract_episode(result)
+            if page_num == pager.get('last_page'):
+                break
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+        return self.playlist_result(self._entries(show_id), playlist_id=show_id)
+
+
+class SpreakerShowPageIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?spreaker\.com/show/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.spreaker.com/show/success-with-music',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        show_id = self._search_regex(
+            r'show_id\s*:\s*(?P<id>\d+)', webpage, 'show id')
+        return self.url_result(
+            'https://api.spreaker.com/show/%s' % show_id,
+            ie=SpreakerShowIE.ie_key(), video_id=show_id)

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

@@ -0,0 +1,113 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    xpath_attr,
+    xpath_text,
+    xpath_element,
+    unescapeHTML,
+    unified_timestamp,
+)
+
+
+class SpringboardPlatformIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        cms\.springboardplatform\.com/
+                        (?:
+                            (?:previews|embed_iframe)/(?P<index>\d+)/video/(?P<id>\d+)|
+                            xml_feeds_advanced/index/(?P<index_2>\d+)/rss3/(?P<id_2>\d+)
+                        )
+                    '''
+    _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//cms\.springboardplatform\.com/embed_iframe/\d+/video/\d+.*?)\1']
+    _TESTS = [{
+        'url': 'http://cms.springboardplatform.com/previews/159/video/981017/0/0/1',
+        'md5': '5c3cb7b5c55740d482561099e920f192',
+        'info_dict': {
+            'id': '981017',
+            'ext': 'mp4',
+            'title': 'Redman "BUD like YOU" "Usher Good Kisser" REMIX',
+            'description': 'Redman "BUD like YOU" "Usher Good Kisser" REMIX',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'timestamp': 1409132328,
+            'upload_date': '20140827',
+            'duration': 193,
+        },
+    }, {
+        'url': 'http://cms.springboardplatform.com/embed_iframe/159/video/981017/rab007/rapbasement.com/1/1',
+        'only_matching': True,
+    }, {
+        'url': 'http://cms.springboardplatform.com/embed_iframe/20/video/1731611/ki055/kidzworld.com/10',
+        'only_matching': True,
+    }, {
+        'url': 'http://cms.springboardplatform.com/xml_feeds_advanced/index/159/rss3/981017/0/0/1/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        video_id = mobj.group('id') or mobj.group('id_2')
+        index = mobj.group('index') or mobj.group('index_2')
+
+        video = self._download_xml(
+            'http://cms.springboardplatform.com/xml_feeds_advanced/index/%s/rss3/%s'
+            % (index, video_id), video_id)
+
+        item = xpath_element(video, './/item', 'item', fatal=True)
+
+        content = xpath_element(
+            item, './{http://search.yahoo.com/mrss/}content', 'content',
+            fatal=True)
+        title = unescapeHTML(xpath_text(item, './title', 'title', fatal=True))
+
+        video_url = content.attrib['url']
+
+        if 'error_video.mp4' in video_url:
+            raise ExtractorError(
+                'Video %s no longer exists' % video_id, expected=True)
+
+        duration = int_or_none(content.get('duration'))
+        tbr = int_or_none(content.get('bitrate'))
+        filesize = int_or_none(content.get('fileSize'))
+        width = int_or_none(content.get('width'))
+        height = int_or_none(content.get('height'))
+
+        description = unescapeHTML(xpath_text(
+            item, './description', 'description'))
+        thumbnail = xpath_attr(
+            item, './{http://search.yahoo.com/mrss/}thumbnail', 'url',
+            'thumbnail')
+
+        timestamp = unified_timestamp(xpath_text(
+            item, './{http://cms.springboardplatform.com/namespaces.html}created',
+            'timestamp'))
+
+        formats = [{
+            'url': video_url,
+            'format_id': 'http',
+            'tbr': tbr,
+            'filesize': filesize,
+            'width': width,
+            'height': height,
+        }]
+
+        m3u8_format = formats[0].copy()
+        m3u8_format.update({
+            'url': re.sub(r'(https?://)cdn\.', r'\1hls.', video_url) + '.m3u8',
+            'ext': 'mp4',
+            'format_id': 'hls',
+            'protocol': 'm3u8_native',
+        })
+        formats.append(m3u8_format)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'duration': duration,
+            'formats': formats,
+        }

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

@@ -0,0 +1,61 @@
+from .adobepass import AdobePassIE
+from ..utils import (
+    int_or_none,
+    smuggle_url,
+    update_url_query,
+)
+
+
+class SproutIE(AdobePassIE):
+    _VALID_URL = r'https?://(?:www\.)?(?:sproutonline|universalkids)\.com/(?:watch|(?:[^/]+/)*videos)/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://www.universalkids.com/shows/remy-and-boo/season/1/videos/robot-bike-race',
+        'info_dict': {
+            'id': 'bm0foJFaTKqb',
+            'ext': 'mp4',
+            'title': 'Robot Bike Race',
+            'description': 'md5:436b1d97117cc437f54c383f4debc66d',
+            'timestamp': 1606148940,
+            'upload_date': '20201123',
+            'uploader': 'NBCU-MPAT',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.sproutonline.com/watch/cowboy-adventure',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.universalkids.com/watch/robot-bike-race',
+        'only_matching': True,
+    }]
+    _GEO_COUNTRIES = ['US']
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        mpx_metadata = self._download_json(
+            # http://nbcuunikidsprod.apps.nbcuni.com/networks/universalkids/content/videos/
+            'https://www.universalkids.com/_api/videos/' + display_id,
+            display_id)['mpxMetadata']
+        media_pid = mpx_metadata['mediaPid']
+        theplatform_url = 'https://link.theplatform.com/s/HNK2IC/' + media_pid
+        query = {
+            'mbr': 'true',
+            'manifest': 'm3u',
+        }
+        if mpx_metadata.get('entitlement') == 'auth':
+            query['auth'] = self._extract_mvpd_auth(url, media_pid, 'sprout', 'sprout')
+        theplatform_url = smuggle_url(
+            update_url_query(theplatform_url, query), {
+                'force_smil_url': True,
+                'geo_countries': self._GEO_COUNTRIES,
+            })
+        return {
+            '_type': 'url_transparent',
+            'id': media_pid,
+            'url': theplatform_url,
+            'series': mpx_metadata.get('seriesName'),
+            'season_number': int_or_none(mpx_metadata.get('seasonNumber')),
+            'episode_number': int_or_none(mpx_metadata.get('episodeNumber')),
+            'ie_key': 'ThePlatform',
+        }

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

@@ -0,0 +1,247 @@
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    int_or_none,
+    join_nonempty,
+    parse_iso8601,
+    qualities,
+    try_get,
+)
+
+
+class SRGSSRIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    (?:
+                        https?://tp\.srgssr\.ch/p(?:/[^/]+)+\?urn=urn|
+                        srgssr
+                    ):
+                    (?P<bu>
+                        srf|rts|rsi|rtr|swi
+                    ):(?:[^:]+:)?
+                    (?P<type>
+                        video|audio
+                    ):
+                    (?P<id>
+                        [0-9a-f\-]{36}|\d+
+                    )
+                    '''
+    _GEO_BYPASS = False
+    _GEO_COUNTRIES = ['CH']
+
+    _ERRORS = {
+        'AGERATING12': 'To protect children under the age of 12, this video is only available between 8 p.m. and 6 a.m.',
+        'AGERATING18': 'To protect children under the age of 18, this video is only available between 11 p.m. and 5 a.m.',
+        # 'ENDDATE': 'For legal reasons, this video was only available for a specified period of time.',
+        'GEOBLOCK': 'For legal reasons, this video is only available in Switzerland.',
+        'LEGAL': 'The video cannot be transmitted for legal reasons.',
+        'STARTDATE': 'This video is not yet available. Please try again later.',
+    }
+    _DEFAULT_LANGUAGE_CODES = {
+        'srf': 'de',
+        'rts': 'fr',
+        'rsi': 'it',
+        'rtr': 'rm',
+        'swi': 'en',
+    }
+
+    def _get_tokenized_src(self, url, video_id, format_id):
+        token = self._download_json(
+            'http://tp.srgssr.ch/akahd/token?acl=*',
+            video_id, 'Downloading %s token' % format_id, fatal=False) or {}
+        auth_params = try_get(token, lambda x: x['token']['authparams'])
+        if auth_params:
+            url += ('?' if '?' not in url else '&') + auth_params
+        return url
+
+    def _get_media_data(self, bu, media_type, media_id):
+        query = {'onlyChapters': True} if media_type == 'video' else {}
+        full_media_data = self._download_json(
+            'https://il.srgssr.ch/integrationlayer/2.0/%s/mediaComposition/%s/%s.json'
+            % (bu, media_type, media_id),
+            media_id, query=query)['chapterList']
+        try:
+            media_data = next(
+                x for x in full_media_data if x.get('id') == media_id)
+        except StopIteration:
+            raise ExtractorError('No media information found')
+
+        block_reason = media_data.get('blockReason')
+        if block_reason and block_reason in self._ERRORS:
+            message = self._ERRORS[block_reason]
+            if block_reason == 'GEOBLOCK':
+                self.raise_geo_restricted(
+                    msg=message, countries=self._GEO_COUNTRIES)
+            raise ExtractorError(
+                '%s said: %s' % (self.IE_NAME, message), expected=True)
+
+        return media_data
+
+    def _real_extract(self, url):
+        bu, media_type, media_id = self._match_valid_url(url).groups()
+        media_data = self._get_media_data(bu, media_type, media_id)
+        title = media_data['title']
+
+        formats = []
+        subtitles = {}
+        q = qualities(['SD', 'HD'])
+        for source in (media_data.get('resourceList') or []):
+            format_url = source.get('url')
+            if not format_url:
+                continue
+            protocol = source.get('protocol')
+            quality = source.get('quality')
+            format_id = join_nonempty(protocol, source.get('encoding'), quality)
+
+            if protocol in ('HDS', 'HLS'):
+                if source.get('tokenType') == 'AKAMAI':
+                    format_url = self._get_tokenized_src(
+                        format_url, media_id, format_id)
+                    fmts, subs = self._extract_akamai_formats_and_subtitles(
+                        format_url, media_id)
+                    formats.extend(fmts)
+                    subtitles = self._merge_subtitles(subtitles, subs)
+                elif protocol == 'HLS':
+                    m3u8_fmts, m3u8_subs = self._extract_m3u8_formats_and_subtitles(
+                        format_url, media_id, 'mp4', 'm3u8_native',
+                        m3u8_id=format_id, fatal=False)
+                    formats.extend(m3u8_fmts)
+                    subtitles = self._merge_subtitles(subtitles, m3u8_subs)
+            elif protocol in ('HTTP', 'HTTPS'):
+                formats.append({
+                    'format_id': format_id,
+                    'url': format_url,
+                    'quality': q(quality),
+                })
+
+        # This is needed because for audio medias the podcast url is usually
+        # always included, even if is only an audio segment and not the
+        # whole episode.
+        if int_or_none(media_data.get('position')) == 0:
+            for p in ('S', 'H'):
+                podcast_url = media_data.get('podcast%sdUrl' % p)
+                if not podcast_url:
+                    continue
+                quality = p + 'D'
+                formats.append({
+                    'format_id': 'PODCAST-' + quality,
+                    'url': podcast_url,
+                    'quality': q(quality),
+                })
+
+        if media_type == 'video':
+            for sub in (media_data.get('subtitleList') or []):
+                sub_url = sub.get('url')
+                if not sub_url:
+                    continue
+                lang = sub.get('locale') or self._DEFAULT_LANGUAGE_CODES[bu]
+                subtitles.setdefault(lang, []).append({
+                    'url': sub_url,
+                })
+
+        return {
+            'id': media_id,
+            'title': title,
+            'description': media_data.get('description'),
+            'timestamp': parse_iso8601(media_data.get('date')),
+            'thumbnail': media_data.get('imageUrl'),
+            'duration': float_or_none(media_data.get('duration'), 1000),
+            'subtitles': subtitles,
+            'formats': formats,
+        }
+
+
+class SRGSSRPlayIE(InfoExtractor):
+    IE_DESC = 'srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:(?:www|play)\.)?
+                        (?P<bu>srf|rts|rsi|rtr|swissinfo)\.ch/play/(?:tv|radio)/
+                        (?:
+                            [^/]+/(?P<type>video|audio)/[^?]+|
+                            popup(?P<type_2>video|audio)player
+                        )
+                        \?.*?\b(?:id=|urn=urn:[^:]+:video:)(?P<id>[0-9a-f\-]{36}|\d+)
+                    '''
+
+    _TESTS = [{
+        'url': 'http://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?id=28e1a57d-5b76-4399-8ab3-9097f071e6c5',
+        'md5': '6db2226ba97f62ad42ce09783680046c',
+        'info_dict': {
+            'id': '28e1a57d-5b76-4399-8ab3-9097f071e6c5',
+            'ext': 'mp4',
+            'upload_date': '20130701',
+            'title': 'Snowden beantragt Asyl in Russland',
+            'timestamp': 1372708215,
+            'duration': 113.827,
+            'thumbnail': r're:^https?://.*1383719781\.png$',
+        },
+        'expected_warnings': ['Unable to download f4m manifest'],
+    }, {
+        'url': 'http://www.rtr.ch/play/radio/actualitad/audio/saira-tujetsch-tuttina-cuntinuar-cun-sedrun-muster-turissem?id=63cb0778-27f8-49af-9284-8c7a8c6d15fc',
+        'info_dict': {
+            'id': '63cb0778-27f8-49af-9284-8c7a8c6d15fc',
+            'ext': 'mp3',
+            'upload_date': '20151013',
+            'title': 'Saira: Tujetsch - tuttina cuntinuar cun Sedrun Mustér Turissem',
+            'timestamp': 1444709160,
+            'duration': 336.816,
+        },
+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://www.rts.ch/play/tv/-/video/le-19h30?id=6348260',
+        'md5': '67a2a9ae4e8e62a68d0e9820cc9782df',
+        'info_dict': {
+            'id': '6348260',
+            'display_id': '6348260',
+            'ext': 'mp4',
+            'duration': 1796.76,
+            'title': 'Le 19h30',
+            'upload_date': '20141201',
+            'timestamp': 1417458600,
+            'thumbnail': r're:^https?://.*\.image',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }, {
+        'url': 'http://play.swissinfo.ch/play/tv/business/video/why-people-were-against-tax-reforms?id=42960270',
+        'info_dict': {
+            'id': '42960270',
+            'ext': 'mp4',
+            'title': 'Why people were against tax reforms',
+            'description': 'md5:7ac442c558e9630e947427469c4b824d',
+            'duration': 94.0,
+            'upload_date': '20170215',
+            'timestamp': 1487173560,
+            'thumbnail': r're:https?://www\.swissinfo\.ch/srgscalableimage/42961964',
+            'subtitles': 'count:9',
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://www.srf.ch/play/tv/popupvideoplayer?id=c4dba0ca-e75b-43b2-a34f-f708a4932e01',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.srf.ch/play/tv/10vor10/video/snowden-beantragt-asyl-in-russland?urn=urn:srf:video:28e1a57d-5b76-4399-8ab3-9097f071e6c5',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.rts.ch/play/tv/19h30/video/le-19h30?urn=urn:rts:video:6348260',
+        'only_matching': True,
+    }, {
+        # audio segment, has podcastSdUrl of the full episode
+        'url': 'https://www.srf.ch/play/radio/popupaudioplayer?id=50b20dc8-f05b-4972-bf03-e438ff2833eb',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        bu = mobj.group('bu')
+        media_type = mobj.group('type') or mobj.group('type_2')
+        media_id = mobj.group('id')
+        return self.url_result('srgssr:%s:%s:%s' % (bu[:3], media_type, media_id), 'SRGSSR')

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

@@ -0,0 +1,57 @@
+from .ard import ARDMediathekBaseIE
+from ..utils import (
+    ExtractorError,
+    get_element_by_attribute,
+)
+
+
+class SRMediathekIE(ARDMediathekBaseIE):
+    _WORKING = False
+    IE_NAME = 'sr:mediathek'
+    IE_DESC = 'Saarländischer Rundfunk'
+    _VALID_URL = r'https?://sr-mediathek(?:\.sr-online)?\.de/index\.php\?.*?&id=(?P<id>[0-9]+)'
+
+    _TESTS = [{
+        'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=28455',
+        'info_dict': {
+            'id': '28455',
+            'ext': 'mp4',
+            'title': 'sportarena (26.10.2014)',
+            'description': 'Ringen: KSV Köllerbach gegen Aachen-Walheim; Frauen-Fußball: 1. FC Saarbrücken gegen Sindelfingen; Motorsport: Rallye in Losheim; dazu: Interview mit Timo Bernhard; Turnen: TG Saar; Reitsport: Deutscher Voltigier-Pokal; Badminton: Interview mit Michael Fuchs ',
+            'thumbnail': r're:^https?://.*\.jpg$',
+        },
+        'skip': 'no longer available',
+    }, {
+        'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=37682',
+        'info_dict': {
+            'id': '37682',
+            'ext': 'mp4',
+            'title': 'Love, Cakes and Rock\'n\'Roll',
+            'description': 'md5:18bf9763631c7d326c22603681e1123d',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'http://sr-mediathek.de/index.php?seite=7&id=7480',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        if '>Der gew&uuml;nschte Beitrag ist leider nicht mehr verf&uuml;gbar.<' in webpage:
+            raise ExtractorError('Video %s is no longer available' % video_id, expected=True)
+
+        media_collection_url = self._search_regex(
+            r'data-mediacollection-ardplayer="([^"]+)"', webpage, 'media collection url')
+        info = self._extract_media_info(media_collection_url, webpage, video_id)
+        info.update({
+            'id': video_id,
+            'title': get_element_by_attribute('class', 'ardplayer-title', webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        })
+        return info