@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/ruutu.py

@@ -0,0 +1,262 @@
+import json
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_urllib_parse_urlparse
+from ..utils import (
+    determine_ext,
+    ExtractorError,
+    find_xpath_attr,
+    int_or_none,
+    traverse_obj,
+    try_call,
+    unified_strdate,
+    url_or_none,
+    xpath_attr,
+    xpath_text,
+)
+
+
+class RuutuIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            (?:www\.)?(?:ruutu|supla)\.fi/(?:video|supla|audio)/|
+                            static\.nelonenmedia\.fi/player/misc/embed_player\.html\?.*?\bnid=
+                        )
+                        (?P<id>\d+)
+                    '''
+    _TESTS = [
+        {
+            'url': 'http://www.ruutu.fi/video/2058907',
+            'md5': 'ab2093f39be1ca8581963451b3c0234f',
+            'info_dict': {
+                'id': '2058907',
+                'ext': 'mp4',
+                'title': 'Oletko aina halunnut tietää mitä tapahtuu vain hetki ennen lähetystä? - Nyt se selvisi!',
+                'description': 'md5:cfc6ccf0e57a814360df464a91ff67d6',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'duration': 114,
+                'age_limit': 0,
+                'upload_date': '20150508',
+            },
+        },
+        {
+            'url': 'http://www.ruutu.fi/video/2057306',
+            'md5': '065a10ae4d5b8cfd9d0c3d332465e3d9',
+            'info_dict': {
+                'id': '2057306',
+                'ext': 'mp4',
+                'title': 'Superpesis: katso koko kausi Ruudussa',
+                'description': 'md5:bfb7336df2a12dc21d18fa696c9f8f23',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'duration': 40,
+                'age_limit': 0,
+                'upload_date': '20150507',
+                'series': 'Superpesis',
+                'categories': ['Urheilu'],
+            },
+        },
+        {
+            'url': 'http://www.supla.fi/supla/2231370',
+            'md5': 'df14e782d49a2c0df03d3be2a54ef949',
+            'info_dict': {
+                'id': '2231370',
+                'ext': 'mp4',
+                'title': 'Osa 1: Mikael Jungner',
+                'description': 'md5:7d90f358c47542e3072ff65d7b1bcffe',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'age_limit': 0,
+                'upload_date': '20151012',
+                'series': 'Läpivalaisu',
+            },
+        },
+        # Episode where <SourceFile> is "NOT-USED", but has other
+        # downloadable sources available.
+        {
+            'url': 'http://www.ruutu.fi/video/3193728',
+            'only_matching': True,
+        },
+        {
+            # audio podcast
+            'url': 'https://www.supla.fi/supla/3382410',
+            'md5': 'b9d7155fed37b2ebf6021d74c4b8e908',
+            'info_dict': {
+                'id': '3382410',
+                'ext': 'mp3',
+                'title': 'Mikä ihmeen poltergeist?',
+                'description': 'md5:bbb6963df17dfd0ecd9eb9a61bf14b52',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'age_limit': 0,
+                'upload_date': '20190320',
+                'series': 'Mysteeritarinat',
+                'duration': 1324,
+            },
+            'expected_warnings': [
+                'HTTP Error 502: Bad Gateway',
+                'Failed to download m3u8 information',
+            ],
+        },
+        {
+            'url': 'http://www.supla.fi/audio/2231370',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://static.nelonenmedia.fi/player/misc/embed_player.html?nid=3618790',
+            'only_matching': True,
+        },
+        {
+            # episode
+            'url': 'https://www.ruutu.fi/video/3401964',
+            'info_dict': {
+                'id': '3401964',
+                'ext': 'mp4',
+                'title': 'Temptation Island Suomi - Kausi 5 - Jakso 17',
+                'description': 'md5:87cf01d5e1e88adf0c8a2937d2bd42ba',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'duration': 2582,
+                'age_limit': 12,
+                'upload_date': '20190508',
+                'series': 'Temptation Island Suomi',
+                'season_number': 5,
+                'episode_number': 17,
+                'categories': ['Reality ja tositapahtumat', 'Kotimaiset suosikit', 'Romantiikka ja parisuhde'],
+            },
+            'params': {
+                'skip_download': True,
+            },
+        },
+        {
+            # premium
+            'url': 'https://www.ruutu.fi/video/3618715',
+            'only_matching': True,
+        },
+    ]
+    _API_BASE = 'https://gatling.nelonenmedia.fi'
+
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        # nelonen.fi
+        settings = try_call(
+            lambda: json.loads(re.search(
+                r'jQuery\.extend\(Drupal\.settings, ({.+?})\);', webpage).group(1), strict=False))
+        if settings:
+            video_id = traverse_obj(settings, (
+                'mediaCrossbowSettings', 'file', 'field_crossbow_video_id', 'und', 0, 'value'))
+            if video_id:
+                return [f'http://www.ruutu.fi/video/{video_id}']
+        # hs.fi and is.fi
+        settings = try_call(
+            lambda: json.loads(re.search(
+                '(?s)<script[^>]+id=[\'"]__NEXT_DATA__[\'"][^>]*>([^<]+)</script>',
+                webpage).group(1), strict=False))
+        if settings:
+            video_ids = set(traverse_obj(settings, (
+                'props', 'pageProps', 'page', 'assetData', 'splitBody', ..., 'video', 'sourceId')) or [])
+            if video_ids:
+                return [f'http://www.ruutu.fi/video/{v}' for v in video_ids]
+            video_id = traverse_obj(settings, (
+                'props', 'pageProps', 'page', 'assetData', 'mainVideo', 'sourceId'))
+            if video_id:
+                return [f'http://www.ruutu.fi/video/{video_id}']
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video_xml = self._download_xml(
+            '%s/media-xml-cache' % self._API_BASE, video_id,
+            query={'id': video_id})
+
+        formats = []
+        processed_urls = []
+
+        def extract_formats(node):
+            for child in node:
+                if child.tag.endswith('Files'):
+                    extract_formats(child)
+                elif child.tag.endswith('File'):
+                    video_url = child.text
+                    if (not video_url or video_url in processed_urls
+                            or any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
+                        continue
+                    processed_urls.append(video_url)
+                    ext = determine_ext(video_url)
+                    auth_video_url = url_or_none(self._download_webpage(
+                        '%s/auth/access/v2' % self._API_BASE, video_id,
+                        note='Downloading authenticated %s stream URL' % ext,
+                        fatal=False, query={'stream': video_url}))
+                    if auth_video_url:
+                        processed_urls.append(auth_video_url)
+                        video_url = auth_video_url
+                    if ext == 'm3u8':
+                        formats.extend(self._extract_m3u8_formats(
+                            video_url, video_id, 'mp4',
+                            entry_protocol='m3u8_native', m3u8_id='hls',
+                            fatal=False))
+                    elif ext == 'f4m':
+                        formats.extend(self._extract_f4m_formats(
+                            video_url, video_id, f4m_id='hds', fatal=False))
+                    elif ext == 'mpd':
+                        # video-only and audio-only streams are of different
+                        # duration resulting in out of sync issue
+                        continue
+                        formats.extend(self._extract_mpd_formats(
+                            video_url, video_id, mpd_id='dash', fatal=False))
+                    elif ext == 'mp3' or child.tag == 'AudioMediaFile':
+                        formats.append({
+                            'format_id': 'audio',
+                            'url': video_url,
+                            'vcodec': 'none',
+                        })
+                    else:
+                        proto = compat_urllib_parse_urlparse(video_url).scheme
+                        if not child.tag.startswith('HTTP') and proto != 'rtmp':
+                            continue
+                        preference = -1 if proto == 'rtmp' else 1
+                        label = child.get('label')
+                        tbr = int_or_none(child.get('bitrate'))
+                        format_id = '%s-%s' % (proto, label if label else tbr) if label or tbr else proto
+                        if not self._is_valid_url(video_url, video_id, format_id):
+                            continue
+                        width, height = [int_or_none(x) for x in child.get('resolution', 'x').split('x')[:2]]
+                        formats.append({
+                            'format_id': format_id,
+                            'url': video_url,
+                            'width': width,
+                            'height': height,
+                            'tbr': tbr,
+                            'preference': preference,
+                        })
+
+        extract_formats(video_xml.find('./Clip'))
+
+        def pv(name):
+            value = try_call(lambda: find_xpath_attr(
+                video_xml, './Clip/PassthroughVariables/variable', 'name', name).get('value'))
+            if value != 'NA':
+                return value or None
+
+        if not formats:
+            if (not self.get_param('allow_unplayable_formats')
+                    and xpath_text(video_xml, './Clip/DRM', default=None)):
+                self.report_drm(video_id)
+            ns_st_cds = pv('ns_st_cds')
+            if ns_st_cds != 'free':
+                raise ExtractorError('This video is %s.' % ns_st_cds, expected=True)
+
+        themes = pv('themes')
+
+        return {
+            'id': video_id,
+            'title': xpath_attr(video_xml, './/Behavior/Program', 'program_name', 'title', fatal=True),
+            'description': xpath_attr(video_xml, './/Behavior/Program', 'description', 'description'),
+            'thumbnail': xpath_attr(video_xml, './/Behavior/Startpicture', 'href', 'thumbnail'),
+            'duration': int_or_none(xpath_text(video_xml, './/Runtime', 'duration')) or int_or_none(pv('runtime')),
+            'age_limit': int_or_none(xpath_text(video_xml, './/AgeLimit', 'age limit')),
+            'upload_date': unified_strdate(pv('date_start')),
+            'series': pv('series_name'),
+            'season_number': int_or_none(pv('season_number')),
+            'episode_number': int_or_none(pv('episode_number')),
+            'categories': themes.split(',') if themes else None,
+            'formats': formats,
+        }

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

@@ -0,0 +1,186 @@
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    parse_duration,
+    traverse_obj,
+    unified_timestamp,
+)
+
+
+class RuvIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?ruv\.is/(?:sarpurinn/[^/]+|node)/(?P<id>[^/]+(?:/\d+)?)'
+    _TESTS = [{
+        # m3u8
+        'url': 'http://ruv.is/sarpurinn/ruv-aukaras/fh-valur/20170516',
+        'md5': '66347652f4e13e71936817102acc1724',
+        'info_dict': {
+            'id': '1144499',
+            'display_id': 'fh-valur/20170516',
+            'ext': 'mp4',
+            'title': 'FH - Valur',
+            'description': 'Bein útsending frá 3. leik FH og Vals í úrslitum Olísdeildar karla í handbolta.',
+            'timestamp': 1494963600,
+            'upload_date': '20170516',
+        },
+    }, {
+        # mp3
+        'url': 'http://ruv.is/sarpurinn/ras-2/morgunutvarpid/20170619',
+        'md5': '395ea250c8a13e5fdb39d4670ef85378',
+        'info_dict': {
+            'id': '1153630',
+            'display_id': 'morgunutvarpid/20170619',
+            'ext': 'mp3',
+            'title': 'Morgunútvarpið',
+            'description': 'md5:a4cf1202c0a1645ca096b06525915418',
+            'timestamp': 1497855000,
+            'upload_date': '20170619',
+        },
+    }, {
+        'url': 'http://ruv.is/sarpurinn/ruv/frettir/20170614',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.ruv.is/node/1151854',
+        'only_matching': True,
+    }, {
+        'url': 'http://ruv.is/sarpurinn/klippa/secret-soltice-hefst-a-morgun',
+        'only_matching': True,
+    }, {
+        'url': 'http://ruv.is/sarpurinn/ras-1/morgunvaktin/20170619',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, display_id)
+
+        title = self._og_search_title(webpage)
+
+        FIELD_RE = r'video\.%s\s*=\s*(["\'])(?P<url>(?:(?!\1).)+)\1'
+
+        media_url = self._html_search_regex(
+            FIELD_RE % 'src', webpage, 'video URL', group='url')
+
+        video_id = self._search_regex(
+            r'<link\b[^>]+\bhref=["\']https?://www\.ruv\.is/node/(\d+)',
+            webpage, 'video id', default=display_id)
+
+        ext = determine_ext(media_url)
+
+        if ext == 'm3u8':
+            formats = self._extract_m3u8_formats(
+                media_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls')
+        elif ext == 'mp3':
+            formats = [{
+                'format_id': 'mp3',
+                'url': media_url,
+                'vcodec': 'none',
+            }]
+        else:
+            formats = [{
+                'url': media_url,
+            }]
+
+        description = self._og_search_description(webpage, default=None)
+        thumbnail = self._og_search_thumbnail(
+            webpage, default=None) or self._search_regex(
+            FIELD_RE % 'poster', webpage, 'thumbnail', fatal=False)
+        timestamp = unified_timestamp(self._html_search_meta(
+            'article:published_time', webpage, 'timestamp', fatal=False))
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'timestamp': timestamp,
+            'formats': formats,
+        }
+
+
+class RuvSpilaIE(InfoExtractor):
+    IE_NAME = 'ruv.is:spila'
+    _VALID_URL = r'https?://(?:www\.)?ruv\.is/(?:(?:sjon|ut)varp|(?:krakka|ung)ruv)/spila/.+/(?P<series_id>[0-9]+)/(?P<id>[a-z0-9]+)'
+    _TESTS = [{
+        'url': 'https://www.ruv.is/sjonvarp/spila/ithrottir/30657/9jcnd4',
+        'info_dict': {
+            'id': '9jcnd4',
+            'ext': 'mp4',
+            'title': '01.02.2022',
+            'chapters': 'count:4',
+            'timestamp': 1643743500,
+            'upload_date': '20220201',
+            'thumbnail': 'https://d38kdhuogyllre.cloudfront.net/fit-in/1960x/filters:quality(65)/hd_posters/94boog-iti3jg.jpg',
+            'description': 'Íþróttafréttir.',
+            'age_limit': 0,
+        },
+    }, {
+        'url': 'https://www.ruv.is/utvarp/spila/i-ljosi-sogunnar/23795/7hqkre',
+        'info_dict': {
+            'id': '7hqkre',
+            'ext': 'mp3',
+            'thumbnail': 'https://d38kdhuogyllre.cloudfront.net/fit-in/1960x/filters:quality(65)/hd_posters/7hqkre-7uepao.jpg',
+            'description': 'md5:8d7046549daff35e9a3190dc9901a120',
+            'chapters': [],
+            'upload_date': '20220204',
+            'timestamp': 1643965500,
+            'title': 'Nellie Bly II',
+            'age_limit': 0,
+        },
+    }, {
+        'url': 'https://www.ruv.is/ungruv/spila/ungruv/28046/8beuph',
+        'only_matching': True
+    }, {
+        'url': 'https://www.ruv.is/krakkaruv/spila/krakkafrettir/30712/9jbgb0',
+        'only_matching': True
+    }]
+
+    def _real_extract(self, url):
+        display_id, series_id = self._match_valid_url(url).group('id', 'series_id')
+        program = self._download_json(
+            'https://www.ruv.is/gql/', display_id, query={'query': '''{
+                Program(id: %s){
+                    title image description short_description
+                    episodes(id: {value: "%s"}) {
+                        rating title duration file image firstrun description
+                        clips {
+                            time text
+                        }
+                        subtitles {
+                            name value
+                        }
+                    }
+                }
+            }''' % (series_id, display_id)})['data']['Program']
+        episode = program['episodes'][0]
+
+        subs = {}
+        for trk in episode.get('subtitles'):
+            if trk.get('name') and trk.get('value'):
+                subs.setdefault(trk['name'], []).append({'url': trk['value'], 'ext': 'vtt'})
+
+        media_url = episode['file']
+        if determine_ext(media_url) == 'm3u8':
+            formats = self._extract_m3u8_formats(media_url, display_id)
+        else:
+            formats = [{'url': media_url}]
+
+        clips = [
+            {'start_time': parse_duration(c.get('time')), 'title': c.get('text')}
+            for c in episode.get('clips') or []]
+
+        return {
+            'id': display_id,
+            'title': traverse_obj(program, ('episodes', 0, 'title'), 'title'),
+            'description': traverse_obj(
+                program, ('episodes', 0, 'description'), 'description', 'short_description',
+                expected_type=lambda x: x or None),
+            'subtitles': subs,
+            'thumbnail': episode.get('image', '').replace('$$IMAGESIZE$$', '1960') or None,
+            'timestamp': unified_timestamp(episode.get('firstrun')),
+            'formats': formats,
+            'age_limit': episode.get('rating'),
+            'chapters': clips
+        }

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/s4c.py

@@ -0,0 +1,103 @@
+from .common import InfoExtractor
+from ..utils import traverse_obj, url_or_none
+
+
+class S4CIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?s4c\.cymru/clic/programme/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.s4c.cymru/clic/programme/861362209',
+        'info_dict': {
+            'id': '861362209',
+            'ext': 'mp4',
+            'title': 'Y Swn',
+            'description': 'md5:f7681a30e4955b250b3224aa9fe70cf0',
+            'duration': 5340,
+            'thumbnail': 'https://www.s4c.cymru/amg/1920x1080/Y_Swn_2023S4C_099_ii.jpg'
+        },
+    }, {
+        'url': 'https://www.s4c.cymru/clic/programme/856636948',
+        'info_dict': {
+            'id': '856636948',
+            'ext': 'mp4',
+            'title': 'Am Dro',
+            'duration': 2880,
+            'description': 'md5:100d8686fc9a632a0cb2db52a3433ffe',
+            'thumbnail': 'https://www.s4c.cymru/amg/1920x1080/Am_Dro_2022-23S4C_P6_4005.jpg'
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        details = self._download_json(
+            f'https://www.s4c.cymru/df/full_prog_details?lang=e&programme_id={video_id}',
+            video_id, fatal=False)
+
+        player_config = self._download_json(
+            'https://player-api.s4c-cdn.co.uk/player-configuration/prod', video_id, query={
+                'programme_id': video_id,
+                'signed': '0',
+                'lang': 'en',
+                'mode': 'od',
+                'appId': 'clic',
+                'streamName': '',
+            }, note='Downloading player config JSON')
+        subtitles = {}
+        for sub in traverse_obj(player_config, ('subtitles', lambda _, v: url_or_none(v['0']))):
+            subtitles.setdefault(sub.get('3', 'en'), []).append({
+                'url': sub['0'],
+                'name': sub.get('1'),
+            })
+        m3u8_url = self._download_json(
+            'https://player-api.s4c-cdn.co.uk/streaming-urls/prod', video_id, query={
+                'mode': 'od',
+                'application': 'clic',
+                'region': 'WW',
+                'extra': 'false',
+                'thirdParty': 'false',
+                'filename': player_config['filename'],
+            }, note='Downloading streaming urls JSON')['hls']
+
+        return {
+            'id': video_id,
+            'formats': self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls'),
+            'subtitles': subtitles,
+            'thumbnail': url_or_none(player_config.get('poster')),
+            **traverse_obj(details, ('full_prog_details', 0, {
+                'title': (('programme_title', 'series_title'), {str}),
+                'description': ('full_billing', {str.strip}),
+                'duration': ('duration', {lambda x: int(x) * 60}),
+            }), get_all=False),
+        }
+
+
+class S4CSeriesIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?s4c\.cymru/clic/series/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.s4c.cymru/clic/series/864982911',
+        'playlist_mincount': 6,
+        'info_dict': {
+            'id': '864982911',
+            'title': 'Iaith ar Daith',
+        },
+    }, {
+        'url': 'https://www.s4c.cymru/clic/series/866852587',
+        'playlist_mincount': 8,
+        'info_dict': {
+            'id': '866852587',
+            'title': 'FFIT Cymru',
+        },
+    }]
+
+    def _real_extract(self, url):
+        series_id = self._match_id(url)
+        series_details = self._download_json(
+            'https://www.s4c.cymru/df/series_details', series_id, query={
+                'lang': 'e',
+                'series_id': series_id,
+                'show_prog_in_series': 'Y'
+            }, note='Downloading series details JSON')
+
+        return self.playlist_result(
+            [self.url_result(f'https://www.s4c.cymru/clic/programme/{episode_id}', S4CIE, episode_id)
+             for episode_id in traverse_obj(series_details, ('other_progs_in_series', ..., 'id'))],
+            series_id, traverse_obj(series_details, ('full_prog_details', 0, 'series_title', {str})))