@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/commonmistakes.py

@@ -0,0 +1,42 @@
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class CommonMistakesIE(InfoExtractor):
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'(?:url|URL|yt-dlp)$'
+
+    _TESTS = [{
+        'url': 'url',
+        'only_matching': True,
+    }, {
+        'url': 'URL',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        msg = (
+            'You\'ve asked yt-dlp to download the URL "%s". '
+            'That doesn\'t make any sense. '
+            'Simply remove the parameter in your command or configuration.'
+        ) % url
+        if not self.get_param('verbose'):
+            msg += ' Add -v to the command line to see what arguments and configuration yt-dlp has'
+        raise ExtractorError(msg, expected=True)
+
+
+class UnicodeBOMIE(InfoExtractor):
+    IE_DESC = False
+    _VALID_URL = r'(?P<bom>\ufeff)(?P<id>.*)$'
+
+    _TESTS = [{
+        'url': '\ufeffhttp://www.youtube.com/watch?v=BaW_jenozKc',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        real_url = self._match_id(url)
+        self.report_warning(
+            'Your URL starts with a Byte Order Mark (BOM). '
+            'Removing the BOM and looking for "%s" ...' % real_url)
+        return self.url_result(real_url)

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

@@ -0,0 +1,70 @@
+import urllib.parse
+
+from .common import InfoExtractor
+
+
+class RtmpIE(InfoExtractor):
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'(?i)rtmp[est]?://.+'
+
+    _TESTS = [{
+        'url': 'rtmp://cp44293.edgefcs.net/ondemand?auth=daEcTdydfdqcsb8cZcDbAaCbhamacbbawaS-bw7dBb-bWG-GqpGFqCpNCnGoyL&aifp=v001&slist=public/unsecure/audio/2c97899446428e4301471a8cb72b4b97--audio--pmg-20110908-0900a_flv_aac_med_int.mp4',
+        'only_matching': True,
+    }, {
+        'url': 'rtmp://edge.live.hitbox.tv/live/dimak',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._generic_id(url)
+        title = self._generic_title(url)
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': [{
+                'url': url,
+                'ext': 'flv',
+                'format_id': urllib.parse.urlparse(url).scheme,
+            }],
+        }
+
+
+class MmsIE(InfoExtractor):
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'(?i)mms://.+'
+
+    _TEST = {
+        # Direct MMS link
+        'url': 'mms://kentro.kaist.ac.kr/200907/MilesReid(0709).wmv',
+        'info_dict': {
+            'id': 'MilesReid(0709)',
+            'ext': 'wmv',
+            'title': 'MilesReid(0709)',
+        },
+        'params': {
+            'skip_download': True,  # rtsp downloads, requiring mplayer or mpv
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._generic_id(url)
+        title = self._generic_title(url)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': url,
+        }
+
+
+class ViewSourceIE(InfoExtractor):
+    IE_DESC = False
+    _VALID_URL = r'view-source:(?P<url>.+)'
+
+    _TEST = {
+        'url': 'view-source:https://www.youtube.com/watch?v=BaW_jenozKc',
+        'only_matching': True
+    }
+
+    def _real_extract(self, url):
+        return self.url_result(self._match_valid_url(url).group('url'))

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

@@ -0,0 +1,250 @@
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_urllib_parse_urlparse,
+    compat_urlparse,
+)
+from ..utils import (
+    determine_ext,
+    extract_attributes,
+    int_or_none,
+    js_to_json,
+    mimetype2ext,
+    orderedSet,
+    parse_iso8601,
+    strip_or_none,
+    try_get,
+)
+
+
+class CondeNastIE(InfoExtractor):
+    """
+    Condé Nast is a media group, some of its sites use a custom HTML5 player
+    that works the same in all of them.
+    """
+
+    # The keys are the supported sites and the values are the name to be shown
+    # to the user and in the extractor description.
+    _SITES = {
+        'allure': 'Allure',
+        'architecturaldigest': 'Architectural Digest',
+        'arstechnica': 'Ars Technica',
+        'bonappetit': 'Bon Appétit',
+        'brides': 'Brides',
+        'cnevids': 'Condé Nast',
+        'cntraveler': 'Condé Nast Traveler',
+        'details': 'Details',
+        'epicurious': 'Epicurious',
+        'glamour': 'Glamour',
+        'golfdigest': 'Golf Digest',
+        'gq': 'GQ',
+        'newyorker': 'The New Yorker',
+        'self': 'SELF',
+        'teenvogue': 'Teen Vogue',
+        'vanityfair': 'Vanity Fair',
+        'vogue': 'Vogue',
+        'wired': 'WIRED',
+        'wmagazine': 'W Magazine',
+    }
+
+    _VALID_URL = r'''(?x)https?://(?:video|www|player(?:-backend)?)\.(?:%s)\.com/
+        (?:
+            (?:
+                embed(?:js)?|
+                (?:script|inline)/video
+            )/(?P<id>[0-9a-f]{24})(?:/(?P<player_id>[0-9a-f]{24}))?(?:.+?\btarget=(?P<target>[^&]+))?|
+            (?P<type>watch|series|video)/(?P<display_id>[^/?#]+)
+        )''' % '|'.join(_SITES.keys())
+    IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))
+
+    _EMBED_REGEX = [r'''(?x)
+        <(?:iframe|script)[^>]+?src=(["\'])(?P<url>
+            (?:https?:)?//player(?:-backend)?\.(?:%s)\.com/(?:embed(?:js)?|(?:script|inline)/video)/.+?
+        )\1''' % '|'.join(_SITES.keys())]
+
+    _TESTS = [{
+        'url': 'http://video.wired.com/watch/3d-printed-speakers-lit-with-led',
+        'md5': '1921f713ed48aabd715691f774c451f7',
+        'info_dict': {
+            'id': '5171b343c2b4c00dd0c1ccb3',
+            'ext': 'mp4',
+            'title': '3D Printed Speakers Lit With LED',
+            'description': 'Check out these beautiful 3D printed LED speakers.  You can\'t actually buy them, but LumiGeek is working on a board that will let you make you\'re own.',
+            'uploader': 'wired',
+            'upload_date': '20130314',
+            'timestamp': 1363219200,
+        }
+    }, {
+        'url': 'http://video.gq.com/watch/the-closer-with-keith-olbermann-the-only-true-surprise-trump-s-an-idiot?c=series',
+        'info_dict': {
+            'id': '58d1865bfd2e6126e2000015',
+            'ext': 'mp4',
+            'title': 'The Only True Surprise? Trump’s an Idiot',
+            'uploader': 'gq',
+            'upload_date': '20170321',
+            'timestamp': 1490126427,
+            'description': 'How much grimmer would things be if these people were competent?',
+        },
+    }, {
+        # JS embed
+        'url': 'http://player.cnevids.com/embedjs/55f9cf8b61646d1acf00000c/5511d76261646d5566020000.js',
+        'md5': 'f1a6f9cafb7083bab74a710f65d08999',
+        'info_dict': {
+            'id': '55f9cf8b61646d1acf00000c',
+            'ext': 'mp4',
+            'title': '3D printed TSA Travel Sentry keys really do open TSA locks',
+            'uploader': 'arstechnica',
+            'upload_date': '20150916',
+            'timestamp': 1442434920,
+        }
+    }, {
+        'url': 'https://player.cnevids.com/inline/video/59138decb57ac36b83000005.js?target=js-cne-player',
+        'only_matching': True,
+    }, {
+        'url': 'http://player-backend.cnevids.com/script/video/59138decb57ac36b83000005.js',
+        'only_matching': True,
+    }]
+
+    def _extract_series(self, url, webpage):
+        title = self._html_search_regex(
+            r'(?s)<div class="cne-series-info">.*?<h1>(.+?)</h1>',
+            webpage, 'series title')
+        url_object = compat_urllib_parse_urlparse(url)
+        base_url = '%s://%s' % (url_object.scheme, url_object.netloc)
+        m_paths = re.finditer(
+            r'(?s)<p class="cne-thumb-title">.*?<a href="(/watch/.+?)["\?]', webpage)
+        paths = orderedSet(m.group(1) for m in m_paths)
+        build_url = lambda path: compat_urlparse.urljoin(base_url, path)
+        entries = [self.url_result(build_url(path), 'CondeNast') for path in paths]
+        return self.playlist_result(entries, playlist_title=title)
+
+    def _extract_video_params(self, webpage, display_id):
+        query = self._parse_json(
+            self._search_regex(
+                r'(?s)var\s+params\s*=\s*({.+?})[;,]', webpage, 'player params',
+                default='{}'),
+            display_id, transform_source=js_to_json, fatal=False)
+        if query:
+            query['videoId'] = self._search_regex(
+                r'(?:data-video-id=|currentVideoId\s*=\s*)["\']([\da-f]+)',
+                webpage, 'video id', default=None)
+        else:
+            params = extract_attributes(self._search_regex(
+                r'(<[^>]+data-js="video-player"[^>]+>)',
+                webpage, 'player params element'))
+            query.update({
+                'videoId': params['data-video'],
+                'playerId': params['data-player'],
+                'target': params['id'],
+            })
+        return query
+
+    def _extract_video(self, params):
+        video_id = params['videoId']
+
+        video_info = None
+
+        # New API path
+        query = params.copy()
+        query['embedType'] = 'inline'
+        info_page = self._download_json(
+            'http://player.cnevids.com/embed-api.json', video_id,
+            'Downloading embed info', fatal=False, query=query)
+
+        # Old fallbacks
+        if not info_page:
+            if params.get('playerId'):
+                info_page = self._download_json(
+                    'http://player.cnevids.com/player/video.js', video_id,
+                    'Downloading video info', fatal=False, query=params)
+        if info_page:
+            video_info = info_page.get('video')
+        if not video_info:
+            info_page = self._download_webpage(
+                'http://player.cnevids.com/player/loader.js',
+                video_id, 'Downloading loader info', query=params)
+        if not video_info:
+            info_page = self._download_webpage(
+                'https://player.cnevids.com/inline/video/%s.js' % video_id,
+                video_id, 'Downloading inline info', query={
+                    'target': params.get('target', 'embedplayer')
+                })
+
+        if not video_info:
+            video_info = self._parse_json(
+                self._search_regex(
+                    r'(?s)var\s+config\s*=\s*({.+?});', info_page, 'config'),
+                video_id, transform_source=js_to_json)['video']
+
+        title = video_info['title']
+
+        formats = []
+        for fdata in video_info['sources']:
+            src = fdata.get('src')
+            if not src:
+                continue
+            ext = mimetype2ext(fdata.get('type')) or determine_ext(src)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    src, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+                continue
+            quality = fdata.get('quality')
+            formats.append({
+                'format_id': ext + ('-%s' % quality if quality else ''),
+                'url': src,
+                'ext': ext,
+                'quality': 1 if quality == 'high' else 0,
+            })
+
+        subtitles = {}
+        for t, caption in video_info.get('captions', {}).items():
+            caption_url = caption.get('src')
+            if not (t in ('vtt', 'srt', 'tml') and caption_url):
+                continue
+            subtitles.setdefault('en', []).append({'url': caption_url})
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+            'thumbnail': video_info.get('poster_frame'),
+            'uploader': video_info.get('brand'),
+            'duration': int_or_none(video_info.get('duration')),
+            'tags': video_info.get('tags'),
+            'series': video_info.get('series_title'),
+            'season': video_info.get('season_title'),
+            'timestamp': parse_iso8601(video_info.get('premiere_date')),
+            'categories': video_info.get('categories'),
+            'subtitles': subtitles,
+        }
+
+    def _real_extract(self, url):
+        video_id, player_id, target, url_type, display_id = self._match_valid_url(url).groups()
+
+        if video_id:
+            return self._extract_video({
+                'videoId': video_id,
+                'playerId': player_id,
+                'target': target,
+            })
+
+        webpage = self._download_webpage(url, display_id)
+
+        if url_type == 'series':
+            return self._extract_series(url, webpage)
+        else:
+            video = try_get(self._parse_json(self._search_regex(
+                r'__PRELOADED_STATE__\s*=\s*({.+?});', webpage,
+                'preload state', '{}'), display_id),
+                lambda x: x['transformed']['video'])
+            if video:
+                params = {'videoId': video['id']}
+                info = {'description': strip_or_none(video.get('description'))}
+            else:
+                params = self._extract_video_params(webpage, display_id)
+                info = self._search_json_ld(
+                    webpage, display_id, fatal=False)
+            info.update(self._extract_video(params))
+            return info

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

@@ -0,0 +1,113 @@
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    int_or_none,
+)
+
+
+class CONtvIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?contv\.com/details-movie/(?P<id>[^/]+)'
+    _TESTS = [{
+        'url': 'https://www.contv.com/details-movie/CEG10022949/days-of-thrills-&-laughter',
+        'info_dict': {
+            'id': 'CEG10022949',
+            'ext': 'mp4',
+            'title': 'Days Of Thrills & Laughter',
+            'description': 'md5:5d6b3d0b1829bb93eb72898c734802eb',
+            'upload_date': '20180703',
+            'timestamp': 1530634789.61,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.contv.com/details-movie/CLIP-show_fotld_bts/fight-of-the-living-dead:-behind-the-scenes-bites',
+        'info_dict': {
+            'id': 'CLIP-show_fotld_bts',
+            'title': 'Fight of the Living Dead: Behind the Scenes Bites',
+        },
+        'playlist_mincount': 7,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        details = self._download_json(
+            'http://metax.contv.live.junctiontv.net/metax/2.5/details/' + video_id,
+            video_id, query={'device': 'web'})
+
+        if details.get('type') == 'episodic':
+            seasons = self._download_json(
+                'http://metax.contv.live.junctiontv.net/metax/2.5/seriesfeed/json/' + video_id,
+                video_id)
+            entries = []
+            for season in seasons:
+                for episode in season.get('episodes', []):
+                    episode_id = episode.get('id')
+                    if not episode_id:
+                        continue
+                    entries.append(self.url_result(
+                        'https://www.contv.com/details-movie/' + episode_id,
+                        CONtvIE.ie_key(), episode_id))
+            return self.playlist_result(entries, video_id, details.get('title'))
+
+        m_details = details['details']
+        title = details['title']
+
+        formats = []
+
+        media_hls_url = m_details.get('media_hls_url')
+        if media_hls_url:
+            formats.extend(self._extract_m3u8_formats(
+                media_hls_url, video_id, 'mp4',
+                m3u8_id='hls', fatal=False))
+
+        media_mp4_url = m_details.get('media_mp4_url')
+        if media_mp4_url:
+            formats.append({
+                'format_id': 'http',
+                'url': media_mp4_url,
+            })
+
+        subtitles = {}
+        captions = m_details.get('captions') or {}
+        for caption_url in captions.values():
+            subtitles.setdefault('en', []).append({
+                'url': caption_url
+            })
+
+        thumbnails = []
+        for image in m_details.get('images', []):
+            image_url = image.get('url')
+            if not image_url:
+                continue
+            thumbnails.append({
+                'url': image_url,
+                'width': int_or_none(image.get('width')),
+                'height': int_or_none(image.get('height')),
+            })
+
+        description = None
+        for p in ('large_', 'medium_', 'small_', ''):
+            d = m_details.get(p + 'description')
+            if d:
+                description = d
+                break
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'description': description,
+            'timestamp': float_or_none(details.get('metax_added_on'), 1000),
+            'subtitles': subtitles,
+            'duration': float_or_none(m_details.get('duration'), 1000),
+            'view_count': int_or_none(details.get('num_watched')),
+            'like_count': int_or_none(details.get('num_fav')),
+            'categories': details.get('category'),
+            'tags': details.get('tags'),
+            'season_number': int_or_none(details.get('season')),
+            'episode_number': int_or_none(details.get('episode')),
+            'release_year': int_or_none(details.get('pub_year')),
+        }

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

@@ -0,0 +1,154 @@
+from .theplatform import ThePlatformFeedIE
+from ..utils import (
+    dict_get,
+    ExtractorError,
+    float_or_none,
+    int_or_none,
+)
+
+
+class CorusIE(ThePlatformFeedIE):  # XXX: Do not subclass from concrete IE
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?P<domain>
+                            (?:
+                                globaltv|
+                                etcanada|
+                                seriesplus|
+                                wnetwork|
+                                ytv
+                            )\.com|
+                            (?:
+                                hgtv|
+                                foodnetwork|
+                                slice|
+                                history|
+                                showcase|
+                                bigbrothercanada|
+                                abcspark|
+                                disney(?:channel|lachaine)
+                            )\.ca
+                        )
+                        /(?:[^/]+/)*
+                        (?:
+                            video\.html\?.*?\bv=|
+                            videos?/(?:[^/]+/)*(?:[a-z0-9-]+-)?
+                        )
+                        (?P<id>
+                            [\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}|
+                            (?:[A-Z]{4})?\d{12,20}
+                        )
+                    '''
+    _TESTS = [{
+        'url': 'https://www.hgtv.ca/video/bryan-inc/movie-night-popcorn-with-bryan/870923331648/',
+        'info_dict': {
+            'id': '870923331648',
+            'ext': 'mp4',
+            'title': 'Movie Night Popcorn with Bryan',
+            'description': 'Bryan whips up homemade popcorn, the old fashion way for Jojo and Lincoln.',
+            'upload_date': '20170206',
+            'timestamp': 1486392197,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'expected_warnings': ['Failed to parse JSON'],
+        # FIXME: yt-dlp wrongly raises for geo restriction
+    }, {
+        'url': 'http://www.foodnetwork.ca/shows/chopped/video/episode/chocolate-obsession/video.html?v=872683587753',
+        'only_matching': True,
+    }, {
+        'url': 'http://etcanada.com/video/873675331955/meet-the-survivor-game-changers-castaways-part-2/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.history.ca/the-world-without-canada/video/full-episodes/natural-resources/video.html?v=955054659646#video',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.showcase.ca/eyewitness/video/eyewitness++106/video.html?v=955070531919&p=1&s=da#video',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.bigbrothercanada.ca/video/1457812035894/',
+        'only_matching': True
+    }, {
+        'url': 'https://www.bigbrothercanada.ca/video/big-brother-canada-704/1457812035894/',
+        'only_matching': True
+    }, {
+        'url': 'https://www.seriesplus.com/emissions/dre-mary-mort-sur-ordonnance/videos/deux-coeurs-battant/SERP0055626330000200/',
+        'only_matching': True
+    }, {
+        'url': 'https://www.disneychannel.ca/shows/gabby-duran-the-unsittables/video/crybaby-duran-clip/2f557eec-0588-11ea-ae2b-e2c6776b770e/',
+        'only_matching': True
+    }]
+    _GEO_BYPASS = False
+    _SITE_MAP = {
+        'globaltv': 'series',
+        'etcanada': 'series',
+        'foodnetwork': 'food',
+        'bigbrothercanada': 'series',
+        'disneychannel': 'disneyen',
+        'disneylachaine': 'disneyfr',
+    }
+
+    def _real_extract(self, url):
+        domain, video_id = self._match_valid_url(url).groups()
+        site = domain.split('.')[0]
+        path = self._SITE_MAP.get(site, site)
+        if path != 'series':
+            path = 'migration/' + path
+        video = self._download_json(
+            'https://globalcontent.corusappservices.com/templates/%s/playlist/' % path,
+            video_id, query={'byId': video_id},
+            headers={'Accept': 'application/json'})[0]
+        title = video['title']
+
+        formats = []
+        for source in video.get('sources', []):
+            smil_url = source.get('file')
+            if not smil_url:
+                continue
+            source_type = source.get('type')
+            note = 'Downloading%s smil file' % (' ' + source_type if source_type else '')
+            resp = self._download_webpage(
+                smil_url, video_id, note, fatal=False,
+                headers=self.geo_verification_headers())
+            if not resp:
+                continue
+            error = self._parse_json(resp, video_id, fatal=False)
+            if error:
+                if error.get('exception') == 'GeoLocationBlocked':
+                    self.raise_geo_restricted(countries=['CA'])
+                raise ExtractorError(error['description'])
+            smil = self._parse_xml(resp, video_id, fatal=False)
+            if smil is None:
+                continue
+            namespace = self._parse_smil_namespace(smil)
+            formats.extend(self._parse_smil_formats(
+                smil, smil_url, video_id, namespace))
+        if not formats and video.get('drm'):
+            self.report_drm(video_id)
+
+        subtitles = {}
+        for track in video.get('tracks', []):
+            track_url = track.get('file')
+            if not track_url:
+                continue
+            lang = 'fr' if site in ('disneylachaine', 'seriesplus') else 'en'
+            subtitles.setdefault(lang, []).append({'url': track_url})
+
+        metadata = video.get('metadata') or {}
+        get_number = lambda x: int_or_none(video.get('pl1$' + x) or metadata.get(x + 'Number'))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': dict_get(video, ('defaultThumbnailUrl', 'thumbnail', 'image')),
+            'description': video.get('description'),
+            'timestamp': int_or_none(video.get('availableDate'), 1000),
+            'subtitles': subtitles,
+            'duration': float_or_none(metadata.get('duration')),
+            'series': dict_get(video, ('show', 'pl1$show')),
+            'season_number': get_number('season'),
+            'episode_number': get_number('episode'),
+        }