@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/vocaroo.py

@@ -0,0 +1,63 @@
+from .common import InfoExtractor
+from ..networking import HEADRequest
+from ..utils import float_or_none
+
+
+class VocarooIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?(?:vocaroo\.com|voca\.ro)/(?:embed/)?(?P<id>\w+)'
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:www\.)?vocaroo\.com/embed/.+?)\1']
+    _TESTS = [
+        {
+            'url': 'https://vocaroo.com/1de8yA3LNe77',
+            'md5': 'c557841d5e50261777a6585648adf439',
+            'info_dict': {
+                'id': '1de8yA3LNe77',
+                'ext': 'mp3',
+                'title': 'Vocaroo video #1de8yA3LNe77',
+                'timestamp': 1675059800.370,
+                'upload_date': '20230130',
+            },
+        },
+        {
+            'url': 'https://vocaroo.com/embed/12WqtjLnpj6g?autoplay=0',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://voca.ro/12D52rgpzkB0',
+            'only_matching': True,
+        },
+    ]
+
+    _WEBPAGE_TESTS = [
+        {
+            'url': 'https://qbnu.github.io/cool.html',
+            'md5': 'f322e529275dd8a47994919eeac404a5',
+            'info_dict': {
+                'id': '19cgWmKO6AmC',
+                'ext': 'mp3',
+                'title': 'Vocaroo video #19cgWmKO6AmC',
+                'timestamp': 1675093841.408,
+                'upload_date': '20230130',
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        audio_id = self._match_id(url)
+        if len(audio_id) == 10 or (len(audio_id) == 12 and audio_id[0] == '1'):
+            media_subdomain = 'media1'
+        else:
+            media_subdomain = 'media'
+
+        url = f'https://{media_subdomain}.vocaroo.com/mp3/{audio_id}'
+        http_headers = {'Referer': 'https://vocaroo.com/'}
+        resp = self._request_webpage(HEADRequest(url), audio_id, headers=http_headers)
+        return {
+            'id': audio_id,
+            'title': '',
+            'url': url,
+            'ext': 'mp3',
+            'timestamp': float_or_none(resp.headers.get('x-bz-upload-timestamp'), scale=1000),
+            'vcodec': 'none',
+            'http_headers': http_headers,
+        }

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

@@ -0,0 +1,29 @@
+from .onet import OnetBaseIE
+
+
+class VODPlIE(OnetBaseIE):
+    _VALID_URL = r'https?://vod\.pl/(?:[^/]+/)+(?P<id>[0-9a-zA-Z]+)'
+
+    _TESTS = [{
+        'url': 'https://vod.pl/filmy/chlopaki-nie-placza/3ep3jns',
+        'md5': 'a7dc3b2f7faa2421aefb0ecaabf7ec74',
+        'info_dict': {
+            'id': '3ep3jns',
+            'ext': 'mp4',
+            'title': 'Chłopaki nie płaczą',
+            'description': 'md5:f5f03b84712e55f5ac9f0a3f94445224',
+            'timestamp': 1463415154,
+            'duration': 5765,
+            'upload_date': '20160516',
+        },
+    }, {
+        'url': 'https://vod.pl/seriale/belfer-na-planie-praca-kamery-online/2c10heh',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        info_dict = self._extract_from_id(self._search_mvp_id(webpage), webpage)
+        info_dict['id'] = video_id
+        return info_dict

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

@@ -0,0 +1,37 @@
+from .common import InfoExtractor
+from ..utils import unescapeHTML
+
+
+class VODPlatformIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/(?P<id>[^/?#]+)'
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:(?:www\.)?vod-platform\.net|embed\.kwikmotion\.com)/[eE]mbed/.+?)\1']
+    _TESTS = [{
+        # from http://www.lbcgroup.tv/watch/chapter/29143/52844/%D8%A7%D9%84%D9%86%D8%B5%D8%B1%D8%A9-%D9%81%D9%8A-%D8%B6%D9%8A%D8%A7%D9%81%D8%A9-%D8%A7%D9%84%D9%80-cnn/ar
+        'url': 'http://vod-platform.net/embed/RufMcytHDolTH1MuKHY9Fw',
+        'md5': '1db2b7249ce383d6be96499006e951fc',
+        'info_dict': {
+            'id': 'RufMcytHDolTH1MuKHY9Fw',
+            'ext': 'mp4',
+            'title': 'LBCi News_ النصرة في ضيافة الـ "سي.أن.أن"',
+        }
+    }, {
+        'url': 'http://embed.kwikmotion.com/embed/RufMcytHDolTH1MuKHY9Fw',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        title = unescapeHTML(self._og_search_title(webpage))
+        hidden_inputs = self._hidden_inputs(webpage)
+
+        formats = self._extract_wowza_formats(
+            hidden_inputs.get('HiddenmyhHlsLink') or hidden_inputs['HiddenmyDashLink'], video_id, skip_protocols=['f4m', 'smil'])
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': hidden_inputs.get('HiddenThumbnail') or self._og_search_thumbnail(webpage),
+            'formats': formats,
+        }

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

@@ -0,0 +1,146 @@
+import itertools
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    ExtractorError,
+    smuggle_url,
+    str_or_none,
+    traverse_obj,
+    unified_strdate,
+    unsmuggle_url,
+)
+
+
+class VoicyBaseIE(InfoExtractor):
+    def _extract_from_playlist_data(self, value):
+        voice_id = compat_str(value.get('PlaylistId'))
+        upload_date = unified_strdate(value.get('Published'), False)
+        items = [self._extract_single_article(voice_data) for voice_data in value['VoiceData']]
+        return {
+            '_type': 'multi_video',
+            'entries': items,
+            'id': voice_id,
+            'title': compat_str(value.get('PlaylistName')),
+            'uploader': value.get('SpeakerName'),
+            'uploader_id': str_or_none(value.get('SpeakerId')),
+            'channel': value.get('ChannelName'),
+            'channel_id': str_or_none(value.get('ChannelId')),
+            'upload_date': upload_date,
+        }
+
+    def _extract_single_article(self, entry):
+        formats = [{
+            'url': entry['VoiceHlsFile'],
+            'format_id': 'hls',
+            'ext': 'm4a',
+            'acodec': 'aac',
+            'vcodec': 'none',
+            'protocol': 'm3u8_native',
+        }, {
+            'url': entry['VoiceFile'],
+            'format_id': 'mp3',
+            'ext': 'mp3',
+            'acodec': 'mp3',
+            'vcodec': 'none',
+        }]
+        return {
+            'id': compat_str(entry.get('ArticleId')),
+            'title': entry.get('ArticleTitle'),
+            'description': entry.get('MediaName'),
+            'formats': formats,
+        }
+
+    def _call_api(self, url, video_id, **kwargs):
+        response = self._download_json(url, video_id, **kwargs)
+        if response.get('Status') != 0:
+            message = traverse_obj(response, ('Value', 'Error', 'Message'), expected_type=compat_str)
+            if not message:
+                message = 'There was a error in the response: %d' % response.get('Status')
+            raise ExtractorError(message, expected=False)
+        return response.get('Value')
+
+
+class VoicyIE(VoicyBaseIE):
+    _WORKING = False
+    IE_NAME = 'voicy'
+    _VALID_URL = r'https?://voicy\.jp/channel/(?P<channel_id>\d+)/(?P<id>\d+)'
+    ARTICLE_LIST_API_URL = 'https://vmw.api.voicy.jp/articles_list?channel_id=%s&pid=%s'
+    _TESTS = [{
+        'url': 'https://voicy.jp/channel/1253/122754',
+        'info_dict': {
+            'id': '122754',
+            'title': '1/21(木)声日記：ついに原稿終わった！！',
+            'uploader': 'ちょまど@ ITエンジニアなオタク',
+            'uploader_id': '7339',
+        },
+        'playlist_mincount': 9,
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        assert mobj
+        voice_id = mobj.group('id')
+        channel_id = mobj.group('channel_id')
+        url, article_list = unsmuggle_url(url)
+        if not article_list:
+            article_list = self._call_api(self.ARTICLE_LIST_API_URL % (channel_id, voice_id), voice_id)
+        return self._extract_from_playlist_data(article_list)
+
+
+class VoicyChannelIE(VoicyBaseIE):
+    _WORKING = False
+    IE_NAME = 'voicy:channel'
+    _VALID_URL = r'https?://voicy\.jp/channel/(?P<id>\d+)'
+    PROGRAM_LIST_API_URL = 'https://vmw.api.voicy.jp/program_list/all?channel_id=%s&limit=20&public_type=3%s'
+    _TESTS = [{
+        'url': 'https://voicy.jp/channel/1253/',
+        'info_dict': {
+            'id': '7339',
+            'title': 'ゆるふわ日常ラジオ #ちょまラジ',
+            'uploader': 'ちょまど@ ITエンジニアなオタク',
+            'uploader_id': '7339',
+        },
+        'playlist_mincount': 54,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return not VoicyIE.suitable(url) and super().suitable(url)
+
+    def _entries(self, channel_id):
+        pager = ''
+        for count in itertools.count(1):
+            article_list = self._call_api(self.PROGRAM_LIST_API_URL % (channel_id, pager), channel_id, note='Paging #%d' % count)
+            playlist_data = article_list.get('PlaylistData')
+            if not playlist_data:
+                break
+            yield from playlist_data
+            last = playlist_data[-1]
+            pager = '&pid=%d&p_date=%s&play_count=%s' % (last['PlaylistId'], last['Published'], last['PlayCount'])
+
+    def _real_extract(self, url):
+        channel_id = self._match_id(url)
+        articles = self._entries(channel_id)
+
+        first_article = next(articles, None)
+        title = traverse_obj(first_article, ('ChannelName', ), expected_type=compat_str)
+        speaker_name = traverse_obj(first_article, ('SpeakerName', ), expected_type=compat_str)
+        if not title and speaker_name:
+            title = 'Uploads from %s' % speaker_name
+        if not title:
+            title = 'Uploads from channel ID %s' % channel_id
+
+        articles = itertools.chain([first_article], articles) if first_article else articles
+
+        playlist = (
+            self.url_result(smuggle_url('https://voicy.jp/channel/%s/%d' % (channel_id, value['PlaylistId']), value), VoicyIE.ie_key())
+            for value in articles)
+        return {
+            '_type': 'playlist',
+            'entries': playlist,
+            'id': channel_id,
+            'title': title,
+            'channel': speaker_name,
+            'channel_id': channel_id,
+        }

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

@@ -0,0 +1,40 @@
+from .common import InfoExtractor
+
+
+class VolejTVIE(InfoExtractor):
+    _VALID_URL = r'https?://volej\.tv/video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://volej.tv/video/725742/',
+        'info_dict': {
+            'id': '725742',
+            'ext': 'mp4',
+            'description': 'Zápas VK Královo Pole vs VK Prostějov 10.12.2022 v 19:00 na Volej.TV',
+            'thumbnail': 'https://volej.tv/images/og/16/17186/og.png',
+            'title': 'VK Královo Pole vs VK Prostějov',
+        }
+    }, {
+        'url': 'https://volej.tv/video/725605/',
+        'info_dict': {
+            'id': '725605',
+            'ext': 'mp4',
+            'thumbnail': 'https://volej.tv/images/og/15/17185/og.png',
+            'title': 'VK Lvi Praha vs VK Euro Sitex Příbram',
+            'description': 'Zápas VK Lvi Praha vs VK Euro Sitex Příbram 11.12.2022 v 19:00 na Volej.TV',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        json_data = self._search_json(
+            r'<\s*!\[CDATA[^=]+=', webpage, 'CDATA', video_id)
+        formats, subtitle = self._extract_m3u8_formats_and_subtitles(
+            json_data['urls']['hls'], video_id)
+        return {
+            'id': video_id,
+            'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
+            'thumbnail': self._html_search_meta(['og:image', 'twitter:image'], webpage),
+            'description': self._html_search_meta(['description', 'og:description', 'twitter:description'], webpage),
+            'formats': formats,
+            'subtitles': subtitle,
+        }

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

@@ -0,0 +1,212 @@
+import json
+import time
+import uuid
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    int_or_none,
+    jwt_decode_hs256,
+    parse_age_limit,
+    traverse_obj,
+    try_call,
+    try_get,
+    unified_strdate,
+)
+
+
+class VootBaseIE(InfoExtractor):
+    _NETRC_MACHINE = 'voot'
+    _GEO_BYPASS = False
+    _LOGIN_HINT = 'Log in with "-u <email_address> -p <password>", or use "-u token -p <auth_token>" to login with auth token.'
+    _TOKEN = None
+    _EXPIRY = 0
+    _API_HEADERS = {'Origin': 'https://www.voot.com', 'Referer': 'https://www.voot.com/'}
+
+    def _perform_login(self, username, password):
+        if self._TOKEN and self._EXPIRY:
+            return
+
+        if username.lower() == 'token' and try_call(lambda: jwt_decode_hs256(password)):
+            VootBaseIE._TOKEN = password
+            VootBaseIE._EXPIRY = jwt_decode_hs256(password)['exp']
+            self.report_login()
+
+        # Mobile number as username is not supported
+        elif not username.isdigit():
+            check_username = self._download_json(
+                'https://userauth.voot.com/usersV3/v3/checkUser', None, data=json.dumps({
+                    'type': 'email',
+                    'email': username
+                }, separators=(',', ':')).encode(), headers={
+                    **self._API_HEADERS,
+                    'Content-Type': 'application/json;charset=utf-8',
+                }, note='Checking username', expected_status=403)
+            if not traverse_obj(check_username, ('isExist', {bool})):
+                if traverse_obj(check_username, ('status', 'code', {int})) == 9999:
+                    self.raise_geo_restricted(countries=['IN'])
+                raise ExtractorError('Incorrect username', expected=True)
+            auth_token = traverse_obj(self._download_json(
+                'https://userauth.voot.com/usersV3/v3/login', None, data=json.dumps({
+                    'type': 'traditional',
+                    'deviceId': str(uuid.uuid4()),
+                    'deviceBrand': 'PC/MAC',
+                    'data': {
+                        'email': username,
+                        'password': password
+                    }
+                }, separators=(',', ':')).encode(), headers={
+                    **self._API_HEADERS,
+                    'Content-Type': 'application/json;charset=utf-8',
+                }, note='Logging in', expected_status=400), ('data', 'authToken', {dict}))
+            if not auth_token:
+                raise ExtractorError('Incorrect password', expected=True)
+            VootBaseIE._TOKEN = auth_token['accessToken']
+            VootBaseIE._EXPIRY = auth_token['expirationTime']
+
+        else:
+            raise ExtractorError(self._LOGIN_HINT, expected=True)
+
+    def _check_token_expiry(self):
+        if int(time.time()) >= self._EXPIRY:
+            raise ExtractorError('Access token has expired', expected=True)
+
+    def _real_initialize(self):
+        if not self._TOKEN:
+            self.raise_login_required(self._LOGIN_HINT, method=None)
+        self._check_token_expiry()
+
+
+class VootIE(VootBaseIE):
+    _WORKING = False
+    _VALID_URL = r'''(?x)
+                    (?:
+                        voot:|
+                        https?://(?:www\.)?voot\.com/?
+                        (?:
+                            movies?/[^/]+/|
+                            (?:shows|kids)/(?:[^/]+/){4}
+                        )
+                     )
+                    (?P<id>\d{3,})
+                    '''
+    _TESTS = [{
+        'url': 'https://www.voot.com/shows/ishq-ka-rang-safed/1/360558/is-this-the-end-of-kamini-/441353',
+        'info_dict': {
+            'id': '441353',
+            'ext': 'mp4',
+            'title': 'Is this the end of Kamini?',
+            'description': 'md5:06291fbbbc4dcbe21235c40c262507c1',
+            'timestamp': 1472103000,
+            'upload_date': '20160825',
+            'series': 'Ishq Ka Rang Safed',
+            'season_number': 1,
+            'episode': 'Is this the end of Kamini?',
+            'episode_number': 340,
+            'release_date': '20160825',
+            'season': 'Season 1',
+            'age_limit': 13,
+            'duration': 1146.0,
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://www.voot.com/kids/characters/mighty-cat-masked-niyander-e-/400478/school-bag-disappears/440925',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.voot.com/movies/pandavas-5/424627',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.voot.com/movie/fight-club/621842',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        media_info = self._download_json(
+            'https://psapi.voot.com/jio/voot/v1/voot-web/content/query/asset-details', video_id,
+            query={'ids': f'include:{video_id}', 'responseType': 'common'}, headers={'accesstoken': self._TOKEN})
+
+        try:
+            m3u8_url = self._download_json(
+                'https://vootapi.media.jio.com/playback/v1/playbackrights', video_id,
+                'Downloading playback JSON', data=b'{}', headers={
+                    **self.geo_verification_headers(),
+                    **self._API_HEADERS,
+                    'Content-Type': 'application/json;charset=utf-8',
+                    'platform': 'androidwebdesktop',
+                    'vootid': video_id,
+                    'voottoken': self._TOKEN,
+                })['m3u8']
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 400:
+                self._check_token_expiry()
+            raise
+
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls')
+        self._remove_duplicate_formats(formats)
+
+        return {
+            'id': video_id,
+            # '/_definst_/smil:vod/' m3u8 manifests claim to have 720p+ formats but max out at 480p
+            'formats': traverse_obj(formats, (
+                lambda _, v: '/_definst_/smil:vod/' not in v['url'] or v['height'] <= 480)),
+            'http_headers': self._API_HEADERS,
+            **traverse_obj(media_info, ('result', 0, {
+                'title': ('fullTitle', {str}),
+                'description': ('fullSynopsis', {str}),
+                'series': ('showName', {str}),
+                'season_number': ('season', {int_or_none}),
+                'episode': ('fullTitle', {str}),
+                'episode_number': ('episode', {int_or_none}),
+                'timestamp': ('uploadTime', {int_or_none}),
+                'release_date': ('telecastDate', {unified_strdate}),
+                'age_limit': ('ageNemonic', {parse_age_limit}),
+                'duration': ('duration', {float_or_none}),
+            })),
+        }
+
+
+class VootSeriesIE(VootBaseIE):
+    _WORKING = False
+    _VALID_URL = r'https?://(?:www\.)?voot\.com/shows/[^/]+/(?P<id>\d{3,})'
+    _TESTS = [{
+        'url': 'https://www.voot.com/shows/chakravartin-ashoka-samrat/100002',
+        'playlist_mincount': 442,
+        'info_dict': {
+            'id': '100002',
+        },
+    }, {
+        'url': 'https://www.voot.com/shows/ishq-ka-rang-safed/100003',
+        'playlist_mincount': 341,
+        'info_dict': {
+            'id': '100003',
+        },
+    }]
+    _SHOW_API = 'https://psapi.voot.com/media/voot/v1/voot-web/content/generic/season-by-show?sort=season%3Aasc&id={}&responseType=common'
+    _SEASON_API = 'https://psapi.voot.com/media/voot/v1/voot-web/content/generic/series-wise-episode?sort=episode%3Aasc&id={}&responseType=common&page={:d}'
+
+    def _entries(self, show_id):
+        show_json = self._download_json(self._SHOW_API.format(show_id), video_id=show_id)
+        for season in show_json.get('result', []):
+            page_num = 1
+            season_id = try_get(season, lambda x: x['id'], compat_str)
+            season_json = self._download_json(self._SEASON_API.format(season_id, page_num),
+                                              video_id=season_id,
+                                              note='Downloading JSON metadata page %d' % page_num)
+            episodes_json = season_json.get('result', [])
+            while episodes_json:
+                page_num += 1
+                for episode in episodes_json:
+                    video_id = episode.get('id')
+                    yield self.url_result(
+                        'voot:%s' % video_id, ie=VootIE.ie_key(), video_id=video_id)
+                episodes_json = self._download_json(self._SEASON_API.format(season_id, page_num),
+                                                    video_id=season_id,
+                                                    note='Downloading JSON metadata page %d' % page_num)['result']
+
+    def _real_extract(self, url):
+        show_id = self._match_id(url)
+        return self.playlist_result(self._entries(show_id), playlist_id=show_id)