@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/blerp.py

@@ -0,0 +1,167 @@
+import json
+
+from .common import InfoExtractor
+from ..utils import strip_or_none, traverse_obj
+
+
+class BlerpIE(InfoExtractor):
+    IE_NAME = 'blerp'
+    _VALID_URL = r'https?://(?:www\.)?blerp\.com/soundbites/(?P<id>[0-9a-zA-Z]+)'
+    _TESTS = [{
+        'url': 'https://blerp.com/soundbites/6320fe8745636cb4dd677a5a',
+        'info_dict': {
+            'id': '6320fe8745636cb4dd677a5a',
+            'title': 'Samsung Galaxy S8 Over the Horizon Ringtone 2016',
+            'uploader': 'luminousaj',
+            'uploader_id': '5fb81e51aa66ae000c395478',
+            'ext': 'mp3',
+            'tags': ['samsung', 'galaxy', 's8', 'over the horizon', '2016', 'ringtone'],
+        }
+    }, {
+        'url': 'https://blerp.com/soundbites/5bc94ef4796001000498429f',
+        'info_dict': {
+            'id': '5bc94ef4796001000498429f',
+            'title': 'Yee',
+            'uploader': '179617322678353920',
+            'uploader_id': '5ba99cf71386730004552c42',
+            'ext': 'mp3',
+            'tags': ['YEE', 'YEET', 'wo ha haah catchy tune yee', 'yee']
+        }
+    }]
+
+    _GRAPHQL_OPERATIONNAME = "webBitePageGetBite"
+    _GRAPHQL_QUERY = (
+        '''query webBitePageGetBite($_id: MongoID!) {
+            web {
+                biteById(_id: $_id) {
+                    ...bitePageFrag
+                    __typename
+                }
+                __typename
+            }
+        }
+
+        fragment bitePageFrag on Bite {
+            _id
+            title
+            userKeywords
+            keywords
+            color
+            visibility
+            isPremium
+            owned
+            price
+            extraReview
+            isAudioExists
+            image {
+                filename
+                original {
+                    url
+                    __typename
+                }
+                __typename
+            }
+            userReactions {
+                _id
+                reactions
+                createdAt
+                __typename
+            }
+            topReactions
+            totalSaveCount
+            saved
+            blerpLibraryType
+            license
+            licenseMetaData
+            playCount
+            totalShareCount
+            totalFavoriteCount
+            totalAddedToBoardCount
+            userCategory
+            userAudioQuality
+            audioCreationState
+            transcription
+            userTranscription
+            description
+            createdAt
+            updatedAt
+            author
+            listingType
+            ownerObject {
+                _id
+                username
+                profileImage {
+                    filename
+                    original {
+                        url
+                        __typename
+                    }
+                    __typename
+                }
+                __typename
+            }
+            transcription
+            favorited
+            visibility
+            isCurated
+            sourceUrl
+            audienceRating
+            strictAudienceRating
+            ownerId
+            reportObject {
+                reportedContentStatus
+                __typename
+            }
+            giphy {
+                mp4
+                gif
+                __typename
+            }
+            audio {
+                filename
+                original {
+                    url
+                    __typename
+                }
+                mp3 {
+                    url
+                    __typename
+                }
+                __typename
+            }
+            __typename
+        }
+
+        ''')
+
+    def _real_extract(self, url):
+        audio_id = self._match_id(url)
+
+        data = {
+            'operationName': self._GRAPHQL_OPERATIONNAME,
+            'query': self._GRAPHQL_QUERY,
+            'variables': {
+                '_id': audio_id
+            }
+        }
+
+        headers = {
+            'Content-Type': 'application/json'
+        }
+
+        json_result = self._download_json('https://api.blerp.com/graphql',
+                                          audio_id, data=json.dumps(data).encode('utf-8'), headers=headers)
+
+        bite_json = json_result['data']['web']['biteById']
+
+        info_dict = {
+            'id': bite_json['_id'],
+            'url': bite_json['audio']['mp3']['url'],
+            'title': bite_json['title'],
+            'uploader': traverse_obj(bite_json, ('ownerObject', 'username'), expected_type=strip_or_none),
+            'uploader_id': traverse_obj(bite_json, ('ownerObject', '_id'), expected_type=strip_or_none),
+            'ext': 'mp3',
+            'tags': list(filter(None, map(strip_or_none, (traverse_obj(bite_json, 'userKeywords', expected_type=list) or []))) or None)
+        }
+
+        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/blogger.py

@@ -0,0 +1,45 @@
+from ..utils import (
+    mimetype2ext,
+    parse_duration,
+    parse_qs,
+    str_or_none,
+    traverse_obj,
+)
+from .common import InfoExtractor
+
+
+class BloggerIE(InfoExtractor):
+    IE_NAME = 'blogger.com'
+    _VALID_URL = r'https?://(?:www\.)?blogger\.com/video\.g\?token=(?P<id>.+)'
+    _EMBED_REGEX = [r'''<iframe[^>]+src=["'](?P<url>(?:https?:)?//(?:www\.)?blogger\.com/video\.g\?token=[^"']+)["']''']
+    _TESTS = [{
+        'url': 'https://www.blogger.com/video.g?token=AD6v5dzEe9hfcARr5Hlq1WTkYy6t-fXH3BBahVhGvVHe5szdEUBEloSEDSTA8-b111089KbfWuBvTN7fnbxMtymsHhXAXwVvyzHH4Qch2cfLQdGxKQrrEuFpC1amSl_9GuLWODjPgw',
+        'md5': 'f1bc19b6ea1b0fd1d81e84ca9ec467ac',
+        'info_dict': {
+            'id': 'BLOGGER-video-3c740e3a49197e16-796',
+            'title': 'BLOGGER-video-3c740e3a49197e16-796',
+            'ext': 'mp4',
+            'thumbnail': r're:^https?://.*',
+            'duration': 76.068,
+        }
+    }]
+
+    def _real_extract(self, url):
+        token_id = self._match_id(url)
+        webpage = self._download_webpage(url, token_id)
+        data_json = self._search_regex(r'var\s+VIDEO_CONFIG\s*=\s*(\{.*)', webpage, 'JSON data')
+        data = self._parse_json(data_json.encode('utf-8').decode('unicode_escape'), token_id)
+        streams = data['streams']
+        formats = [{
+            'ext': mimetype2ext(traverse_obj(parse_qs(stream['play_url']), ('mime', 0))),
+            'url': stream['play_url'],
+            'format_id': str_or_none(stream.get('format_id')),
+        } for stream in streams]
+
+        return {
+            'id': data.get('iframe_id', token_id),
+            'title': data.get('iframe_id', token_id),
+            'formats': formats,
+            'thumbnail': data.get('thumbnail'),
+            'duration': parse_duration(traverse_obj(parse_qs(streams[0]['play_url']), ('dur', 0))),
+        }

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

@@ -0,0 +1,77 @@
+import re
+
+from .common import InfoExtractor
+
+
+class BloombergIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bloomberg\.com/(?:[^/]+/)*(?P<id>[^/?#]+)'
+
+    _TESTS = [{
+        'url': 'https://www.bloomberg.com/news/videos/2021-09-14/apple-unveils-the-new-iphone-13-stock-doesn-t-move-much-video',
+        'info_dict': {
+            'id': 'V8cFcYMxTHaMcEiiYVr39A',
+            'ext': 'flv',
+            'title': 'Apple Unveils the New IPhone 13, Stock Doesn\'t Move Much',
+        },
+        'params': {
+            'format': 'best[format_id^=hds]',
+        },
+    }, {
+        # video ID in BPlayer(...)
+        'url': 'http://www.bloomberg.com/features/2016-hello-world-new-zealand/',
+        'info_dict': {
+            'id': '938c7e72-3f25-4ddb-8b85-a9be731baa74',
+            'ext': 'flv',
+            'title': 'Meet the Real-Life Tech Wizards of Middle Earth',
+            'description': 'Hello World, Episode 1: New Zealand’s freaky AI babies, robot exoskeletons, and a virtual you.',
+        },
+        'params': {
+            'format': 'best[format_id^=hds]',
+        },
+    }, {
+        # data-bmmrid=
+        'url': 'https://www.bloomberg.com/politics/articles/2017-02-08/le-pen-aide-briefed-french-central-banker-on-plan-to-print-money',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.bloomberg.com/politics/videos/2015-11-25/karl-rove-on-jeb-bush-s-struggles-stopping-trump',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        name = self._match_id(url)
+        webpage = self._download_webpage(url, name)
+        video_id = self._search_regex(
+            (r'["\']bmmrId["\']\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
+             r'videoId\s*:\s*(["\'])(?P<id>(?:(?!\1).)+)\1',
+             r'data-bmmrid=(["\'])(?P<id>(?:(?!\1).)+)\1'),
+            webpage, 'id', group='id', default=None)
+        if not video_id:
+            bplayer_data = self._parse_json(self._search_regex(
+                r'BPlayer\(null,\s*({[^;]+})\);', webpage, 'id'), name)
+            video_id = bplayer_data['id']
+        title = re.sub(': Video$', '', self._og_search_title(webpage))
+
+        embed_info = self._download_json(
+            'http://www.bloomberg.com/multimedia/api/embed?id=%s' % video_id, video_id)
+        formats = []
+        for stream in embed_info['streams']:
+            stream_url = stream.get('url')
+            if not stream_url:
+                continue
+            if stream['muxing_format'] == 'TS':
+                formats.extend(self._extract_m3u8_formats(
+                    stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+            else:
+                formats.extend(self._extract_f4m_formats(
+                    stream_url, video_id, f4m_id='hds', fatal=False))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+        }

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

@@ -0,0 +1,53 @@
+from .common import InfoExtractor
+from ..compat import compat_parse_qs
+from ..utils import ExtractorError
+
+
+class BokeCCBaseIE(InfoExtractor):
+    def _extract_bokecc_formats(self, webpage, video_id, format_id=None):
+        player_params_str = self._html_search_regex(
+            r'<(?:script|embed)[^>]+src=(?P<q>["\'])(?:https?:)?//p\.bokecc\.com/(?:player|flash/player\.swf)\?(?P<query>.+?)(?P=q)',
+            webpage, 'player params', group='query')
+
+        player_params = compat_parse_qs(player_params_str)
+
+        info_xml = self._download_xml(
+            'http://p.bokecc.com/servlet/playinfo?uid=%s&vid=%s&m=1' % (
+                player_params['siteid'][0], player_params['vid'][0]), video_id)
+
+        formats = [{
+            'format_id': format_id,
+            'url': quality.find('./copy').attrib['playurl'],
+            'quality': int(quality.attrib['value']),
+        } for quality in info_xml.findall('./video/quality')]
+
+        return formats
+
+
+class BokeCCIE(BokeCCBaseIE):
+    _IE_DESC = 'CC视频'
+    _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
+
+    _TESTS = [{
+        'url': 'http://union.bokecc.com/playvideo.bo?vid=E0ABAE9D4F509B189C33DC5901307461&uid=FE644790DE9D154A',
+        'info_dict': {
+            'id': 'FE644790DE9D154A_E0ABAE9D4F509B189C33DC5901307461',
+            'ext': 'flv',
+            'title': 'BokeCC Video',
+        },
+    }]
+
+    def _real_extract(self, url):
+        qs = compat_parse_qs(self._match_valid_url(url).group('query'))
+        if not qs.get('vid') or not qs.get('uid'):
+            raise ExtractorError('Invalid URL', expected=True)
+
+        video_id = '%s_%s' % (qs['uid'][0], qs['vid'][0])
+
+        webpage = self._download_webpage(url, video_id)
+
+        return {
+            'id': video_id,
+            'title': 'BokeCC Video',  # no title provided in the webpage
+            'formats': self._extract_bokecc_formats(webpage, video_id),
+        }

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

@@ -0,0 +1,70 @@
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    try_get,
+    urlencode_postdata,
+)
+
+
+class BongaCamsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?P<host>(?:[^/]+\.)?bongacams\d*\.(?:com|net))/(?P<id>[^/?&#]+)'
+    _TESTS = [{
+        'url': 'https://de.bongacams.com/azumi-8',
+        'only_matching': True,
+    }, {
+        'url': 'https://cn.bongacams.com/azumi-8',
+        'only_matching': True,
+    }, {
+        'url': 'https://de.bongacams.net/claireashton',
+        'info_dict': {
+            'id': 'claireashton',
+            'ext': 'mp4',
+            'title': r're:ClaireAshton \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
+            'age_limit': 18,
+            'uploader_id': 'ClaireAshton',
+            'uploader': 'ClaireAshton',
+            'like_count': int,
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        host = mobj.group('host')
+        channel_id = mobj.group('id')
+
+        amf = self._download_json(
+            'https://%s/tools/amf.php' % host, channel_id,
+            data=urlencode_postdata((
+                ('method', 'getRoomData'),
+                ('args[]', channel_id),
+                ('args[]', 'false'),
+            )), headers={'X-Requested-With': 'XMLHttpRequest'})
+
+        server_url = amf['localData']['videoServerUrl']
+
+        uploader_id = try_get(
+            amf, lambda x: x['performerData']['username'], compat_str) or channel_id
+        uploader = try_get(
+            amf, lambda x: x['performerData']['displayName'], compat_str)
+        like_count = int_or_none(try_get(
+            amf, lambda x: x['performerData']['loversCount']))
+
+        formats = self._extract_m3u8_formats(
+            '%s/hls/stream_%s/playlist.m3u8' % (server_url, uploader_id),
+            channel_id, 'mp4', m3u8_id='hls', live=True)
+
+        return {
+            'id': channel_id,
+            'title': uploader or uploader_id,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'like_count': like_count,
+            'age_limit': 18,
+            'is_live': True,
+            'formats': formats,
+        }

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

@@ -0,0 +1,209 @@
+from .common import InfoExtractor
+from .youtube import YoutubeIE
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    qualities,
+    str_or_none,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class BoostyIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?boosty\.to/(?P<user>[^/#?]+)/posts/(?P<post_id>[^/#?]+)'
+    _TESTS = [{
+        # single ok_video
+        'url': 'https://boosty.to/kuplinov/posts/e55d050c-e3bb-4873-a7db-ac7a49b40c38',
+        'info_dict': {
+            'id': 'd7473824-352e-48e2-ae53-d4aa39459968',
+            'title': 'phasma_3',
+            'channel': 'Kuplinov',
+            'channel_id': '7958701',
+            'timestamp': 1655031975,
+            'upload_date': '20220612',
+            'release_timestamp': 1655049000,
+            'release_date': '20220612',
+            'modified_timestamp': 1668680993,
+            'modified_date': '20221117',
+            'tags': ['куплинов', 'phasmophobia'],
+            'like_count': int,
+            'ext': 'mp4',
+            'duration': 105,
+            'view_count': int,
+            'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
+        },
+    }, {
+        # multiple ok_video
+        'url': 'https://boosty.to/maddyson/posts/0c652798-3b35-471f-8b48-a76a0b28736f',
+        'info_dict': {
+            'id': '0c652798-3b35-471f-8b48-a76a0b28736f',
+            'title': 'то что не пропустил юта6',
+            'channel': 'Илья Давыдов',
+            'channel_id': '6808257',
+            'timestamp': 1694017040,
+            'upload_date': '20230906',
+            'release_timestamp': 1694017040,
+            'release_date': '20230906',
+            'modified_timestamp': 1694071178,
+            'modified_date': '20230907',
+            'like_count': int,
+        },
+        'playlist_count': 3,
+        'playlist': [{
+            'info_dict': {
+                'id': 'cc325a9f-a563-41c6-bf47-516c1b506c9a',
+                'title': 'то что не пропустил юта6',
+                'channel': 'Илья Давыдов',
+                'channel_id': '6808257',
+                'timestamp': 1694017040,
+                'upload_date': '20230906',
+                'release_timestamp': 1694017040,
+                'release_date': '20230906',
+                'modified_timestamp': 1694071178,
+                'modified_date': '20230907',
+                'like_count': int,
+                'ext': 'mp4',
+                'duration': 31204,
+                'view_count': int,
+                'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
+            },
+        }, {
+            'info_dict': {
+                'id': 'd07b0a72-9493-4512-b54e-55ce468fd4b7',
+                'title': 'то что не пропустил юта6',
+                'channel': 'Илья Давыдов',
+                'channel_id': '6808257',
+                'timestamp': 1694017040,
+                'upload_date': '20230906',
+                'release_timestamp': 1694017040,
+                'release_date': '20230906',
+                'modified_timestamp': 1694071178,
+                'modified_date': '20230907',
+                'like_count': int,
+                'ext': 'mp4',
+                'duration': 25704,
+                'view_count': int,
+                'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
+            },
+        }, {
+            'info_dict': {
+                'id': '4a3bba32-78c8-422a-9432-2791aff60b42',
+                'title': 'то что не пропустил юта6',
+                'channel': 'Илья Давыдов',
+                'channel_id': '6808257',
+                'timestamp': 1694017040,
+                'upload_date': '20230906',
+                'release_timestamp': 1694017040,
+                'release_date': '20230906',
+                'modified_timestamp': 1694071178,
+                'modified_date': '20230907',
+                'like_count': int,
+                'ext': 'mp4',
+                'duration': 31867,
+                'view_count': int,
+                'thumbnail': r're:^https://i\.mycdn\.me/videoPreview\?',
+            },
+        }],
+    }, {
+        # single external video (youtube)
+        'url': 'https://boosty.to/denischuzhoy/posts/6094a487-bcec-4cf8-a453-43313b463c38',
+        'info_dict': {
+            'id': 'EXelTnve5lY',
+            'title': 'Послание Президента Федеральному Собранию | Класс народа',
+            'upload_date': '20210425',
+            'channel': 'Денис Чужой',
+            'tags': 'count:10',
+            'like_count': int,
+            'ext': 'mp4',
+            'duration': 816,
+            'view_count': int,
+            'thumbnail': r're:^https://i\.ytimg\.com/',
+            'age_limit': 0,
+            'availability': 'public',
+            'categories': list,
+            'channel_follower_count': int,
+            'channel_id': 'UCCzVNbWZfYpBfyofCCUD_0w',
+            'channel_is_verified': bool,
+            'channel_url': r're:^https://www\.youtube\.com/',
+            'comment_count': int,
+            'description': str,
+            'heatmap': 'count:100',
+            'live_status': str,
+            'playable_in_embed': bool,
+            'uploader': str,
+            'uploader_id': str,
+            'uploader_url': r're:^https://www\.youtube\.com/',
+        },
+    }]
+
+    _MP4_TYPES = ('tiny', 'lowest', 'low', 'medium', 'high', 'full_hd', 'quad_hd', 'ultra_hd')
+
+    def _extract_formats(self, player_urls, video_id):
+        formats = []
+        quality = qualities(self._MP4_TYPES)
+        for player_url in traverse_obj(player_urls, lambda _, v: url_or_none(v['url'])):
+            url = player_url['url']
+            format_type = player_url.get('type')
+            if format_type in ('hls', 'hls_live', 'live_ondemand_hls', 'live_playback_hls'):
+                formats.extend(self._extract_m3u8_formats(url, video_id, m3u8_id='hls', fatal=False))
+            elif format_type in ('dash', 'dash_live', 'live_playback_dash'):
+                formats.extend(self._extract_mpd_formats(url, video_id, mpd_id='dash', fatal=False))
+            elif format_type in self._MP4_TYPES:
+                formats.append({
+                    'url': url,
+                    'ext': 'mp4',
+                    'format_id': format_type,
+                    'quality': quality(format_type),
+                })
+            else:
+                self.report_warning(f'Unknown format type: {format_type!r}')
+        return formats
+
+    def _real_extract(self, url):
+        user, post_id = self._match_valid_url(url).group('user', 'post_id')
+        post = self._download_json(
+            f'https://api.boosty.to/v1/blog/{user}/post/{post_id}', post_id,
+            note='Downloading post data', errnote='Unable to download post data')
+
+        post_title = post.get('title')
+        if not post_title:
+            self.report_warning('Unable to extract post title. Falling back to parsing html page')
+            webpage = self._download_webpage(url, video_id=post_id)
+            post_title = self._og_search_title(webpage, default=None) or self._html_extract_title(webpage)
+
+        common_metadata = {
+            'title': post_title,
+            **traverse_obj(post, {
+                'channel': ('user', 'name', {str}),
+                'channel_id': ('user', 'id', {str_or_none}),
+                'timestamp': ('createdAt', {int_or_none}),
+                'release_timestamp': ('publishTime', {int_or_none}),
+                'modified_timestamp': ('updatedAt', {int_or_none}),
+                'tags': ('tags', ..., 'title', {str}),
+                'like_count': ('count', 'likes', {int_or_none}),
+            }),
+        }
+        entries = []
+        for item in traverse_obj(post, ('data', ..., {dict})):
+            item_type = item.get('type')
+            if item_type == 'video' and url_or_none(item.get('url')):
+                entries.append(self.url_result(item['url'], YoutubeIE))
+            elif item_type == 'ok_video':
+                video_id = item.get('id') or post_id
+                entries.append({
+                    'id': video_id,
+                    'formats': self._extract_formats(item.get('playerUrls'), video_id),
+                    **common_metadata,
+                    **traverse_obj(item, {
+                        'title': ('title', {str}),
+                        'duration': ('duration', {int_or_none}),
+                        'view_count': ('viewsCounter', {int_or_none}),
+                        'thumbnail': (('previewUrl', 'defaultPreview'), {url_or_none}),
+                    }, get_all=False)})
+
+        if not entries:
+            raise ExtractorError('No videos found', expected=True)
+        if len(entries) == 1:
+            return entries[0]
+        return self.playlist_result(entries, post_id, post_title, **common_metadata)