@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/servus.py

@@ -0,0 +1,135 @@
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    format_field,
+    int_or_none,
+    join_nonempty,
+    traverse_obj,
+    unescapeHTML,
+    unified_timestamp,
+)
+
+
+class ServusIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?:
+                            servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)|
+                            (?:servustv|pm-wissen)\.com/(?:[^/]+/)?v(?:ideos)?
+                        )
+                        /(?P<id>[aA]{2}-?\w+|\d+-\d+)
+                    '''
+    _TESTS = [{
+        # URL schema v3
+        'url': 'https://www.servustv.com/natur/v/aa-28bycqnh92111/',
+        'info_dict': {
+            'id': 'AA-28BYCQNH92111',
+            'ext': 'mp4',
+            'title': 'Klettersteige in den Alpen',
+            'description': 'md5:25e47ddd83a009a0f9789ba18f2850ce',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 2823,
+            'timestamp': 1655752333,
+            'upload_date': '20220620',
+            'series': 'Bergwelten',
+            'season': 'Season 11',
+            'season_number': 11,
+            'episode': 'Episode 8 - Vie Ferrate – Klettersteige in den Alpen',
+            'episode_number': 8,
+        },
+        'params': {'skip_download': 'm3u8'}
+    }, {
+        'url': 'https://www.servustv.com/natur/v/aa-1xg5xwmgw2112/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.servustv.com/natur/v/aansszcx3yi9jmlmhdc1/',
+        'only_matching': True,
+    }, {
+        # URL schema v2
+        'url': 'https://www.servustv.com/videos/aa-1t6vbu5pw1w12/',
+        'only_matching': True,
+    }, {
+        # URL schema v1
+        'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.servus.com/at/p/Wie-das-Leben-beginnt/1309984137314-381415152/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.servus.com/tv/videos/aa-1t6vbu5pw1w12/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.servus.com/tv/videos/1380889096408-1235196658/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.pm-wissen.com/videos/aa-24mus4g2w2112/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url).upper()
+
+        video = self._download_json(
+            'https://api-player.redbull.com/stv/servus-tv?timeZone=Europe/Berlin',
+            video_id, 'Downloading video JSON', query={'videoId': video_id})
+        if not video.get('videoUrl'):
+            self._report_errors(video)
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            video['videoUrl'], video_id, 'mp4', m3u8_id='hls')
+
+        season = video.get('season')
+        season_number = int_or_none(self._search_regex(
+            r'Season (\d+)', season or '', 'season number', default=None))
+        episode = video.get('chapter')
+        episode_number = int_or_none(self._search_regex(
+            r'Episode (\d+)', episode or '', 'episode number', default=None))
+
+        return {
+            'id': video_id,
+            'title': video.get('title'),
+            'description': self._get_description(video_id) or video.get('description'),
+            'thumbnail': video.get('poster'),
+            'duration': float_or_none(video.get('duration')),
+            'timestamp': unified_timestamp(video.get('currentSunrise')),
+            'series': video.get('label'),
+            'season': season,
+            'season_number': season_number,
+            'episode': episode,
+            'episode_number': episode_number,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+    def _get_description(self, video_id):
+        info = self._download_json(
+            f'https://backend.servustv.com/wp-json/rbmh/v2/media_asset/aa_id/{video_id}?fieldset=page',
+            video_id, fatal=False)
+
+        return join_nonempty(*traverse_obj(info, (
+            ('stv_short_description', 'stv_long_description'),
+            {lambda x: unescapeHTML(x.replace('\n\n', '\n'))})), delim='\n\n')
+
+    def _report_errors(self, video):
+        playability_errors = traverse_obj(video, ('playabilityErrors', ...))
+        if not playability_errors:
+            raise ExtractorError('No videoUrl and no information about errors')
+
+        elif 'FSK_BLOCKED' in playability_errors:
+            details = traverse_obj(video, ('playabilityErrorDetails', 'FSK_BLOCKED'), expected_type=dict)
+            message = format_field(''.join((
+                format_field(details, 'minEveningHour', ' from %02d:00'),
+                format_field(details, 'maxMorningHour', ' to %02d:00'),
+                format_field(details, 'minAge', ' (Minimum age %d)'),
+            )), None, 'Only available%s') or 'Blocked by FSK with unknown availability'
+
+        elif 'NOT_YET_AVAILABLE' in playability_errors:
+            message = format_field(
+                video, (('playabilityErrorDetails', 'NOT_YET_AVAILABLE', 'availableFrom'), 'currentSunrise'),
+                'Only available from %s') or 'Video not yet available with unknown availability'
+
+        else:
+            message = f'Video unavailable: {", ".join(playability_errors)}'
+
+        raise ExtractorError(message, expected=True)

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

@@ -0,0 +1,132 @@
+import json
+import re
+
+from .brightcove import BrightcoveNewBaseIE
+from ..compat import compat_str
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    try_get,
+    update_url_query,
+)
+
+
+class SevenPlusIE(BrightcoveNewBaseIE):
+    IE_NAME = '7plus'
+    _VALID_URL = r'https?://(?:www\.)?7plus\.com\.au/(?P<path>[^?]+\?.*?\bepisode-id=(?P<id>[^&#]+))'
+    _TESTS = [{
+        'url': 'https://7plus.com.au/MTYS?episode-id=MTYS7-003',
+        'info_dict': {
+            'id': 'MTYS7-003',
+            'ext': 'mp4',
+            'title': 'S7 E3 - Wind Surf',
+            'description': 'md5:29c6a69f21accda7601278f81b46483d',
+            'uploader_id': '5303576322001',
+            'upload_date': '20171201',
+            'timestamp': 1512106377,
+            'series': 'Mighty Ships',
+            'season_number': 7,
+            'episode_number': 3,
+            'episode': 'Wind Surf',
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://7plus.com.au/UUUU?episode-id=AUMS43-001',
+        'only_matching': True,
+    }]
+
+    def _real_initialize(self):
+        self.token = None
+
+        cookies = self._get_cookies('https://7plus.com.au')
+        api_key = next((x for x in cookies if x.startswith('glt_')), '')[4:]
+        if not api_key:  # Cookies are signed out, skip login
+            return
+
+        login_resp = self._download_json(
+            'https://login.7plus.com.au/accounts.getJWT', None, 'Logging in', fatal=False,
+            query={
+                'APIKey': api_key,
+                'sdk': 'js_latest',
+                'login_token': cookies[f'glt_{api_key}'].value,
+                'authMode': 'cookie',
+                'pageURL': 'https://7plus.com.au/',
+                'sdkBuild': '12471',
+                'format': 'json',
+            }) or {}
+
+        if 'errorMessage' in login_resp:
+            self.report_warning(f'Unable to login: 7plus said: {login_resp["errorMessage"]}')
+            return
+        id_token = login_resp.get('id_token')
+        if not id_token:
+            self.report_warning('Unable to login: Could not extract id token')
+            return
+
+        token_resp = self._download_json(
+            'https://7plus.com.au/auth/token', None, 'Getting auth token', fatal=False,
+            headers={'Content-Type': 'application/json'}, data=json.dumps({
+                'idToken': id_token,
+                'platformId': 'web',
+                'regSource': '7plus',
+            }).encode('utf-8')) or {}
+        self.token = token_resp.get('token')
+        if not self.token:
+            self.report_warning('Unable to log in: Could not extract auth token')
+
+    def _real_extract(self, url):
+        path, episode_id = self._match_valid_url(url).groups()
+
+        headers = {}
+        if self.token:
+            headers['Authorization'] = f'Bearer {self.token}'
+
+        try:
+            media = self._download_json(
+                'https://videoservice.swm.digital/playback', episode_id, query={
+                    'appId': '7plus',
+                    'deviceType': 'web',
+                    'platformType': 'web',
+                    'accountId': 5303576322001,
+                    'referenceId': 'ref:' + episode_id,
+                    'deliveryId': 'csai',
+                    'videoType': 'vod',
+                }, headers=headers)['media']
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 403:
+                raise ExtractorError(self._parse_json(
+                    e.cause.response.read().decode(), episode_id)[0]['error_code'], expected=True)
+            raise
+
+        for source in media.get('sources', {}):
+            src = source.get('src')
+            if not src:
+                continue
+            source['src'] = update_url_query(src, {'rule': ''})
+
+        info = self._parse_brightcove_metadata(media, episode_id)
+
+        content = self._download_json(
+            'https://component-cdn.swm.digital/content/' + path,
+            episode_id, headers={
+                'market-id': 4,
+            }, fatal=False) or {}
+        for item in content.get('items', {}):
+            if item.get('componentData', {}).get('componentType') == 'infoPanel':
+                for src_key, dst_key in [('title', 'title'), ('shortSynopsis', 'description')]:
+                    value = item.get(src_key)
+                    if value:
+                        info[dst_key] = value
+                info['series'] = try_get(
+                    item, lambda x: x['seriesLogo']['name'], compat_str)
+                mobj = re.search(r'^S(\d+)\s+E(\d+)\s+-\s+(.+)$', info['title'])
+                if mobj:
+                    info.update({
+                        'season_number': int(mobj.group(1)),
+                        'episode_number': int(mobj.group(2)),
+                        'episode': mobj.group(3),
+                    })
+
+        return info

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

@@ -0,0 +1,61 @@
+from .common import InfoExtractor
+
+
+class SexuIE(InfoExtractor):
+    _WORKING = False
+    _VALID_URL = r'https?://(?:www\.)?sexu\.com/(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://sexu.com/961791/',
+        'md5': 'ff615aca9691053c94f8f10d96cd7884',
+        'info_dict': {
+            'id': '961791',
+            'ext': 'mp4',
+            'title': 'md5:4d05a19a5fc049a63dbbaf05fb71d91b',
+            'description': 'md5:2b75327061310a3afb3fbd7d09e2e403',
+            'categories': list,  # NSFW
+            'thumbnail': r're:https?://.*\.jpg$',
+            'age_limit': 18,
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        jwvideo = self._parse_json(
+            self._search_regex(r'\.setup\(\s*({.+?})\s*\);', webpage, 'jwvideo'),
+            video_id)
+
+        sources = jwvideo['sources']
+
+        formats = [{
+            'url': source['file'].replace('\\', ''),
+            'format_id': source.get('label'),
+            'height': int(self._search_regex(
+                r'^(\d+)[pP]', source.get('label', ''), 'height',
+                default=None)),
+        } for source in sources if source.get('file')]
+
+        title = self._html_search_regex(
+            r'<title>([^<]+)\s*-\s*Sexu\.Com</title>', webpage, 'title')
+
+        description = self._html_search_meta(
+            'description', webpage, 'description')
+
+        thumbnail = jwvideo.get('image')
+
+        categories_str = self._html_search_meta(
+            'keywords', webpage, 'categories')
+        categories = (
+            None if categories_str is None
+            else categories_str.split(','))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'categories': categories,
+            'formats': formats,
+            'age_limit': 18,
+        }

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

@@ -0,0 +1,157 @@
+from .common import InfoExtractor
+from ..compat import (
+    compat_str,
+    compat_urllib_parse_urlparse,
+)
+from ..utils import (
+    urljoin,
+    int_or_none,
+    parse_codecs,
+    parse_qs,
+    try_get,
+)
+
+
+def _raw_id(src_url):
+    return compat_urllib_parse_urlparse(src_url).path.split('/')[-1]
+
+
+class SeznamZpravyIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?seznamzpravy\.cz/iframe/player\?.*\bsrc='
+    _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//(?:www\.)?seznamzpravy\.cz/iframe/player\?.*?)\1']
+    _TESTS = [{
+        'url': 'https://www.seznamzpravy.cz/iframe/player?duration=241&serviceSlug=zpravy&src=https%3A%2F%2Fv39-a.sdn.szn.cz%2Fv_39%2Fvmd%2F5999c902ea707c67d8e267a9%3Ffl%3Dmdk%2C432f65a0%7C&itemType=video&autoPlay=false&title=Sv%C4%9Bt%20bez%20obalu%3A%20%C4%8Ce%C5%A1t%C3%AD%20voj%C3%A1ci%20na%20mis%C3%ADch%20(kr%C3%A1tk%C3%A1%20verze)&series=Sv%C4%9Bt%20bez%20obalu&serviceName=Seznam%20Zpr%C3%A1vy&poster=%2F%2Fd39-a.sdn.szn.cz%2Fd_39%2Fc_img_F_I%2FR5puJ.jpeg%3Ffl%3Dcro%2C0%2C0%2C1920%2C1080%7Cres%2C1200%2C%2C1%7Cjpg%2C80%2C%2C1&width=1920&height=1080&cutFrom=0&cutTo=0&splVersion=VOD&contentId=170889&contextId=35990&showAdvert=true&collocation=&autoplayPossible=true&embed=&isVideoTooShortForPreroll=false&isVideoTooLongForPostroll=true&videoCommentOpKey=&videoCommentId=&version=4.0.76&dotService=zpravy&gemiusPrismIdentifier=bVc1ZIb_Qax4W2v5xOPGpMeCP31kFfrTzj0SqPTLh_b.Z7&zoneIdPreroll=seznam.pack.videospot&skipOffsetPreroll=5&sectionPrefixPreroll=%2Fzpravy',
+        'info_dict': {
+            'id': '170889',
+            'ext': 'mp4',
+            'title': 'Svět bez obalu: Čeští vojáci na misích (krátká verze)',
+            'thumbnail': r're:^https?://.*\.jpe?g',
+            'duration': 241,
+            'series': 'Svět bez obalu',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # with Location key
+        'url': 'https://www.seznamzpravy.cz/iframe/player?duration=null&serviceSlug=zpravy&src=https%3A%2F%2Flive-a.sdn.szn.cz%2Fv_39%2F59e468fe454f8472a96af9fa%3Ffl%3Dmdk%2C5c1e2840%7C&itemType=livevod&autoPlay=false&title=P%C5%99edseda%20KDU-%C4%8CSL%20Pavel%20B%C4%9Blobr%C3%A1dek%20ve%20volebn%C3%AD%20V%C3%BDzv%C4%9B%20Seznamu&series=V%C3%BDzva&serviceName=Seznam%20Zpr%C3%A1vy&poster=%2F%2Fd39-a.sdn.szn.cz%2Fd_39%2Fc_img_G_J%2FjTBCs.jpeg%3Ffl%3Dcro%2C0%2C0%2C1280%2C720%7Cres%2C1200%2C%2C1%7Cjpg%2C80%2C%2C1&width=16&height=9&cutFrom=0&cutTo=0&splVersion=VOD&contentId=185688&contextId=38489&showAdvert=true&collocation=&hideFullScreen=false&hideSubtitles=false&embed=&isVideoTooShortForPreroll=false&isVideoTooShortForPreroll2=false&isVideoTooLongForPostroll=false&fakePostrollZoneID=seznam.clanky.zpravy.preroll&fakePrerollZoneID=seznam.clanky.zpravy.preroll&videoCommentId=&trim=default_16x9&noPrerollVideoLength=30&noPreroll2VideoLength=undefined&noMidrollVideoLength=0&noPostrollVideoLength=999999&autoplayPossible=true&version=5.0.41&dotService=zpravy&gemiusPrismIdentifier=zD3g7byfW5ekpXmxTVLaq5Srjw5i4hsYo0HY1aBwIe..27&zoneIdPreroll=seznam.pack.videospot&skipOffsetPreroll=5&sectionPrefixPreroll=%2Fzpravy%2Fvyzva&zoneIdPostroll=seznam.pack.videospot&skipOffsetPostroll=5&sectionPrefixPostroll=%2Fzpravy%2Fvyzva&regression=false',
+        'info_dict': {
+            'id': '185688',
+            'ext': 'mp4',
+            'title': 'Předseda KDU-ČSL Pavel Bělobrádek ve volební Výzvě Seznamu',
+            'thumbnail': r're:^https?://.*\.jpe?g',
+            'series': 'Výzva',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _extract_sdn_formats(self, sdn_url, video_id):
+        sdn_data = self._download_json(sdn_url, video_id)
+
+        if sdn_data.get('Location'):
+            sdn_url = sdn_data['Location']
+            sdn_data = self._download_json(sdn_url, video_id)
+
+        formats = []
+        mp4_formats = try_get(sdn_data, lambda x: x['data']['mp4'], dict) or {}
+        for format_id, format_data in mp4_formats.items():
+            relative_url = format_data.get('url')
+            if not relative_url:
+                continue
+
+            try:
+                width, height = format_data.get('resolution')
+            except (TypeError, ValueError):
+                width, height = None, None
+
+            f = {
+                'url': urljoin(sdn_url, relative_url),
+                'format_id': 'http-%s' % format_id,
+                'tbr': int_or_none(format_data.get('bandwidth'), scale=1000),
+                'width': int_or_none(width),
+                'height': int_or_none(height),
+            }
+            f.update(parse_codecs(format_data.get('codec')))
+            formats.append(f)
+
+        pls = sdn_data.get('pls', {})
+
+        def get_url(format_id):
+            return try_get(pls, lambda x: x[format_id]['url'], compat_str)
+
+        dash_rel_url = get_url('dash')
+        if dash_rel_url:
+            formats.extend(self._extract_mpd_formats(
+                urljoin(sdn_url, dash_rel_url), video_id, mpd_id='dash',
+                fatal=False))
+
+        hls_rel_url = get_url('hls')
+        if hls_rel_url:
+            formats.extend(self._extract_m3u8_formats(
+                urljoin(sdn_url, hls_rel_url), video_id, ext='mp4',
+                m3u8_id='hls', fatal=False))
+
+        return formats
+
+    def _real_extract(self, url):
+        params = parse_qs(url)
+
+        src = params['src'][0]
+        title = params['title'][0]
+        video_id = params.get('contentId', [_raw_id(src)])[0]
+        formats = self._extract_sdn_formats(src + 'spl2,2,VOD', video_id)
+
+        duration = int_or_none(params.get('duration', [None])[0])
+        series = params.get('series', [None])[0]
+        thumbnail = params.get('poster', [None])[0]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'series': series,
+            'formats': formats,
+        }
+
+
+class SeznamZpravyArticleIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?(?:seznam\.cz/zpravy|seznamzpravy\.cz)/clanek/(?:[^/?#&]+)-(?P<id>\d+)'
+    _API_URL = 'https://apizpravy.seznam.cz/'
+
+    _TESTS = [{
+        # two videos on one page, with SDN URL
+        'url': 'https://www.seznamzpravy.cz/clanek/jejich-svet-na-nas-utoci-je-lepsi-branit-se-na-jejich-pisecku-rika-reziser-a-major-v-zaloze-marhoul-35990',
+        'info_dict': {
+            'id': '35990',
+            'title': 'md5:6011c877a36905f28f271fcd8dcdb0f2',
+            'description': 'md5:933f7b06fa337a814ba199d3596d27ba',
+        },
+        'playlist_count': 2,
+    }, {
+        # video with live stream URL
+        'url': 'https://www.seznam.cz/zpravy/clanek/znovu-do-vlady-s-ano-pavel-belobradek-ve-volebnim-specialu-seznamu-38489',
+        'info_dict': {
+            'id': '38489',
+            'title': 'md5:8fa1afdc36fd378cf0eba2b74c5aca60',
+            'description': 'md5:428e7926a1a81986ec7eb23078004fb4',
+        },
+        'playlist_count': 1,
+    }]
+
+    def _real_extract(self, url):
+        article_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, article_id)
+
+        info = self._search_json_ld(webpage, article_id, default={})
+
+        title = info.get('title') or self._og_search_title(webpage, fatal=False)
+        description = info.get('description') or self._og_search_description(webpage)
+
+        return self.playlist_result([
+            self.url_result(entry_url, ie=SeznamZpravyIE.ie_key())
+            for entry_url in SeznamZpravyIE._extract_embed_urls(url, webpage)],
+            article_id, title, description)