@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/truth.py

@@ -0,0 +1,68 @@
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    format_field,
+    int_or_none,
+    strip_or_none,
+    traverse_obj,
+    unified_timestamp,
+)
+
+
+class TruthIE(InfoExtractor):
+    _VALID_URL = r'https?://truthsocial\.com/@[^/]+/posts/(?P<id>\d+)'
+    _TESTS = [
+        {
+            'url': 'https://truthsocial.com/@realDonaldTrump/posts/108779000807761862',
+            'md5': '4a5fb1470c192e493d9efd6f19e514d3',
+            'info_dict': {
+                'id': '108779000807761862',
+                'ext': 'qt',
+                'title': 'Truth video #108779000807761862',
+                'timestamp': 1659835827,
+                'upload_date': '20220807',
+                'uploader': 'Donald J. Trump',
+                'uploader_id': 'realDonaldTrump',
+                'uploader_url': 'https://truthsocial.com/@realDonaldTrump',
+                'repost_count': int,
+                'comment_count': int,
+                'like_count': int,
+            },
+        },
+        {
+            'url': 'https://truthsocial.com/@ProjectVeritasAction/posts/108618228543962049',
+            'md5': 'fd47ba68933f9dce27accc52275be9c3',
+            'info_dict': {
+                'id': '108618228543962049',
+                'ext': 'mp4',
+                'title': 'md5:debde7186cf83f60ff7b44dbb9444e35',
+                'description': 'md5:de2fc49045bf92bb8dc97e56503b150f',
+                'timestamp': 1657382637,
+                'upload_date': '20220709',
+                'uploader': 'Project Veritas Action',
+                'uploader_id': 'ProjectVeritasAction',
+                'uploader_url': 'https://truthsocial.com/@ProjectVeritasAction',
+                'repost_count': int,
+                'comment_count': int,
+                'like_count': int,
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        status = self._download_json(f'https://truthsocial.com/api/v1/statuses/{video_id}', video_id)
+        uploader_id = strip_or_none(traverse_obj(status, ('account', 'username')))
+        return {
+            'id': video_id,
+            'url': status['media_attachments'][0]['url'],
+            'title': '',
+            'description': strip_or_none(clean_html(status.get('content'))) or None,
+            'timestamp': unified_timestamp(status.get('created_at')),
+            'uploader': strip_or_none(traverse_obj(status, ('account', 'display_name'))),
+            'uploader_id': uploader_id,
+            'uploader_url': format_field(uploader_id, None, 'https://truthsocial.com/@%s'),
+            'repost_count': int_or_none(status.get('reblogs_count')),
+            'like_count': int_or_none(status.get('favourites_count')),
+            'comment_count': int_or_none(status.get('replies_count')),
+        }

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

@@ -0,0 +1,70 @@
+from .turner import TurnerBaseIE
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+)
+
+
+class TruTVIE(TurnerBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?trutv\.com/(?:shows|full-episodes)/(?P<series_slug>[0-9A-Za-z-]+)/(?:videos/(?P<clip_slug>[0-9A-Za-z-]+)|(?P<id>\d+))'
+    _TEST = {
+        'url': 'https://www.trutv.com/shows/the-carbonaro-effect/videos/sunlight-activated-flower.html',
+        'info_dict': {
+            'id': 'f16c03beec1e84cd7d1a51f11d8fcc29124cc7f1',
+            'ext': 'mp4',
+            'title': 'Sunlight-Activated Flower',
+            'description': "A customer is stunned when he sees Michael's sunlight-activated flower.",
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        series_slug, clip_slug, video_id = self._match_valid_url(url).groups()
+
+        if video_id:
+            path = 'episode'
+            display_id = video_id
+        else:
+            path = 'series/clip'
+            display_id = clip_slug
+
+        data = self._download_json(
+            'https://api.trutv.com/v2/web/%s/%s/%s' % (path, series_slug, display_id),
+            display_id)
+        video_data = data['episode'] if video_id else data['info']
+        media_id = video_data['mediaId']
+        title = video_data['title'].strip()
+
+        info = self._extract_ngtv_info(
+            media_id, {}, {
+                'url': url,
+                'site_name': 'truTV',
+                'auth_required': video_data.get('isAuthRequired'),
+            })
+
+        thumbnails = []
+        for image in video_data.get('images', []):
+            image_url = image.get('srcUrl')
+            if not image_url:
+                continue
+            thumbnails.append({
+                'url': image_url,
+                'width': int_or_none(image.get('width')),
+                'height': int_or_none(image.get('height')),
+            })
+
+        info.update({
+            'id': media_id,
+            'display_id': display_id,
+            'title': title,
+            'description': video_data.get('description'),
+            'thumbnails': thumbnails,
+            'timestamp': parse_iso8601(video_data.get('publicationDate')),
+            'series': video_data.get('showTitle'),
+            'season_number': int_or_none(video_data.get('seasonNum')),
+            'episode_number': int_or_none(video_data.get('episodeNum')),
+        })
+        return info

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/tube8.py

@@ -0,0 +1,170 @@
+import re
+
+from .common import InfoExtractor
+from ..aes import aes_decrypt_text
+from ..compat import compat_urllib_parse_unquote
+from ..utils import (
+    determine_ext,
+    format_field,
+    int_or_none,
+    str_to_int,
+    strip_or_none,
+    url_or_none,
+)
+
+
+class Tube8IE(InfoExtractor):
+    _WORKING = False
+    _VALID_URL = r'https?://(?:www\.)?tube8\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/(?P<id>\d+)'
+    _EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?tube8\.com/embed/(?:[^/]+/)+\d+)']
+    _TESTS = [{
+        'url': 'http://www.tube8.com/teen/kasia-music-video/229795/',
+        'md5': '65e20c48e6abff62ed0c3965fff13a39',
+        'info_dict': {
+            'id': '229795',
+            'display_id': 'kasia-music-video',
+            'ext': 'mp4',
+            'description': 'hot teen Kasia grinding',
+            'uploader': 'unknown',
+            'title': 'Kasia music video',
+            'age_limit': 18,
+            'duration': 230,
+            'categories': ['Teen'],
+            'tags': ['dancing'],
+        },
+    }, {
+        'url': 'http://www.tube8.com/shemale/teen/blonde-cd-gets-kidnapped-by-two-blacks-and-punished-for-being-a-slutty-girl/19569151/',
+        'only_matching': True,
+    }]
+
+    def _extract_info(self, url, fatal=True):
+        mobj = self._match_valid_url(url)
+        video_id = mobj.group('id')
+        display_id = (mobj.group('display_id')
+                      if 'display_id' in mobj.groupdict()
+                      else None) or mobj.group('id')
+
+        webpage = self._download_webpage(
+            url, display_id, headers={'Cookie': 'age_verified=1'})
+
+        formats = []
+        format_urls = set()
+
+        title = None
+        thumbnail = None
+        duration = None
+        encrypted = False
+
+        def extract_format(format_url, height=None):
+            format_url = url_or_none(format_url)
+            if not format_url or not format_url.startswith(('http', '//')):
+                return
+            if format_url in format_urls:
+                return
+            format_urls.add(format_url)
+            tbr = int_or_none(self._search_regex(
+                r'[/_](\d+)[kK][/_]', format_url, 'tbr', default=None))
+            if not height:
+                height = int_or_none(self._search_regex(
+                    r'[/_](\d+)[pP][/_]', format_url, 'height', default=None))
+            if encrypted:
+                format_url = aes_decrypt_text(
+                    video_url, title, 32).decode('utf-8')
+            formats.append({
+                'url': format_url,
+                'format_id': format_field(height, None, '%dp'),
+                'height': height,
+                'tbr': tbr,
+            })
+
+        flashvars = self._parse_json(
+            self._search_regex(
+                r'flashvars\s*=\s*({.+?});', webpage,
+                'flashvars', default='{}'),
+            display_id, fatal=False)
+
+        if flashvars:
+            title = flashvars.get('video_title')
+            thumbnail = flashvars.get('image_url')
+            duration = int_or_none(flashvars.get('video_duration'))
+            encrypted = flashvars.get('encrypted') is True
+            for key, value in flashvars.items():
+                mobj = re.search(r'quality_(\d+)[pP]', key)
+                if mobj:
+                    extract_format(value, int(mobj.group(1)))
+            video_url = flashvars.get('video_url')
+            if video_url and determine_ext(video_url, None):
+                extract_format(video_url)
+
+        video_url = self._html_search_regex(
+            r'flashvars\.video_url\s*=\s*(["\'])(?P<url>http.+?)\1',
+            webpage, 'video url', default=None, group='url')
+        if video_url:
+            extract_format(compat_urllib_parse_unquote(video_url))
+
+        if not formats:
+            if 'title="This video is no longer available"' in webpage:
+                self.raise_no_formats(
+                    'Video %s is no longer available' % video_id, expected=True)
+
+        if not title:
+            title = self._html_search_regex(
+                r'<h1[^>]*>([^<]+)', webpage, 'title')
+
+        return webpage, {
+            'id': video_id,
+            'display_id': display_id,
+            'title': strip_or_none(title),
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'age_limit': 18,
+            'formats': formats,
+        }
+
+    def _real_extract(self, url):
+        webpage, info = self._extract_info(url)
+
+        if not info['title']:
+            info['title'] = self._html_search_regex(
+                r'videoTitle\s*=\s*"([^"]+)', webpage, 'title')
+
+        description = self._html_search_regex(
+            r'(?s)Description:</dt>\s*<dd>(.+?)</dd>', webpage, 'description', fatal=False)
+        uploader = self._html_search_regex(
+            r'<span class="username">\s*(.+?)\s*<',
+            webpage, 'uploader', fatal=False)
+
+        like_count = int_or_none(self._search_regex(
+            r'rupVar\s*=\s*"(\d+)"', webpage, 'like count', fatal=False))
+        dislike_count = int_or_none(self._search_regex(
+            r'rdownVar\s*=\s*"(\d+)"', webpage, 'dislike count', fatal=False))
+        view_count = str_to_int(self._search_regex(
+            r'Views:\s*</dt>\s*<dd>([\d,\.]+)',
+            webpage, 'view count', fatal=False))
+        comment_count = str_to_int(self._search_regex(
+            r'<span id="allCommentsCount">(\d+)</span>',
+            webpage, 'comment count', fatal=False))
+
+        category = self._search_regex(
+            r'Category:\s*</dt>\s*<dd>\s*<a[^>]+href=[^>]+>([^<]+)',
+            webpage, 'category', fatal=False)
+        categories = [category] if category else None
+
+        tags_str = self._search_regex(
+            r'(?s)Tags:\s*</dt>\s*<dd>(.+?)</(?!a)',
+            webpage, 'tags', fatal=False)
+        tags = [t for t in re.findall(
+            r'<a[^>]+href=[^>]+>([^<]+)', tags_str)] if tags_str else None
+
+        info.update({
+            'description': description,
+            'uploader': uploader,
+            'view_count': view_count,
+            'like_count': like_count,
+            'dislike_count': dislike_count,
+            'comment_count': comment_count,
+            'categories': categories,
+            'tags': tags,
+        })
+
+        return info

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

@@ -0,0 +1,252 @@
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    parse_resolution,
+    traverse_obj,
+    urlencode_postdata,
+    variadic,
+)
+
+
+class TubeTuGrazBaseIE(InfoExtractor):
+    _NETRC_MACHINE = 'tubetugraz'
+
+    _API_EPISODE = 'https://tube.tugraz.at/search/episode.json'
+    _FORMAT_TYPES = ('presentation', 'presenter')
+
+    def _perform_login(self, username, password):
+        urlh = self._request_webpage(
+            'https://tube.tugraz.at/Shibboleth.sso/Login?target=/paella/ui/index.html',
+            None, fatal=False, note='downloading login page', errnote='unable to fetch login page')
+        if not urlh:
+            return
+
+        content, urlh = self._download_webpage_handle(
+            urlh.url, None, fatal=False, headers={'referer': urlh.url},
+            note='logging in', errnote='unable to log in',
+            data=urlencode_postdata({
+                'lang': 'de',
+                '_eventId_proceed': '',
+                'j_username': username,
+                'j_password': password
+            }))
+        if not urlh or urlh.url == 'https://tube.tugraz.at/paella/ui/index.html':
+            return
+
+        if not self._html_search_regex(
+                r'<p\b[^>]*>(Bitte geben Sie einen OTP-Wert ein:)</p>',
+                content, 'TFA prompt', default=None):
+            self.report_warning('unable to login: incorrect password')
+            return
+
+        content, urlh = self._download_webpage_handle(
+            urlh.url, None, fatal=False, headers={'referer': urlh.url},
+            note='logging in with TFA', errnote='unable to log in with TFA',
+            data=urlencode_postdata({
+                'lang': 'de',
+                '_eventId_proceed': '',
+                'j_tokenNumber': self._get_tfa_info(),
+            }))
+        if not urlh or urlh.url == 'https://tube.tugraz.at/paella/ui/index.html':
+            return
+
+        self.report_warning('unable to login: incorrect TFA code')
+
+    def _extract_episode(self, episode_info):
+        id = episode_info.get('id')
+        formats = list(self._extract_formats(
+            traverse_obj(episode_info, ('mediapackage', 'media', 'track')), id))
+
+        title = traverse_obj(episode_info, ('mediapackage', 'title'), 'dcTitle')
+        series_title = traverse_obj(episode_info, ('mediapackage', 'seriestitle'))
+        creator = ', '.join(variadic(traverse_obj(
+            episode_info, ('mediapackage', 'creators', 'creator'), 'dcCreator', default='')))
+        return {
+            'id': id,
+            'title': title,
+            'creator': creator or None,
+            'duration': traverse_obj(episode_info, ('mediapackage', 'duration'), 'dcExtent'),
+            'series': series_title,
+            'series_id': traverse_obj(episode_info, ('mediapackage', 'series'), 'dcIsPartOf'),
+            'episode': series_title and title,
+            'formats': formats
+        }
+
+    def _set_format_type(self, formats, type):
+        for f in formats:
+            f['format_note'] = type
+            if not type.startswith(self._FORMAT_TYPES[0]):
+                f['preference'] = -2
+        return formats
+
+    def _extract_formats(self, format_list, id):
+        has_hls, has_dash = False, False
+
+        for format_info in format_list or []:
+            url = traverse_obj(format_info, ('tags', 'url'), 'url')
+            if url is None:
+                continue
+
+            type = format_info.get('type') or 'unknown'
+            transport = (format_info.get('transport') or 'https').lower()
+
+            if transport == 'https':
+                formats = [{
+                    'url': url,
+                    'abr': float_or_none(traverse_obj(format_info, ('audio', 'bitrate')), 1000),
+                    'vbr': float_or_none(traverse_obj(format_info, ('video', 'bitrate')), 1000),
+                    'fps': traverse_obj(format_info, ('video', 'framerate')),
+                    **parse_resolution(traverse_obj(format_info, ('video', 'resolution'))),
+                }]
+            elif transport == 'hls':
+                has_hls, formats = True, self._extract_m3u8_formats(
+                    url, id, 'mp4', fatal=False, note=f'downloading {type} HLS manifest')
+            elif transport == 'dash':
+                has_dash, formats = True, self._extract_mpd_formats(
+                    url, id, fatal=False, note=f'downloading {type} DASH manifest')
+            else:
+                # RTMP, HDS, SMOOTH, and unknown formats
+                # - RTMP url fails on every tested entry until now
+                # - HDS url 404's on every tested entry until now
+                # - SMOOTH url 404's on every tested entry until now
+                continue
+
+            yield from self._set_format_type(formats, type)
+
+        # TODO: Add test for these
+        for type in self._FORMAT_TYPES:
+            if not has_hls:
+                hls_formats = self._extract_m3u8_formats(
+                    f'https://wowza.tugraz.at/matterhorn_engage/smil:engage-player_{id}_{type}.smil/playlist.m3u8',
+                    id, 'mp4', fatal=False, note=f'Downloading {type} HLS manifest', errnote=False) or []
+                yield from self._set_format_type(hls_formats, type)
+
+            if not has_dash:
+                dash_formats = self._extract_mpd_formats(
+                    f'https://wowza.tugraz.at/matterhorn_engage/smil:engage-player_{id}_{type}.smil/manifest_mpm4sav_mvlist.mpd',
+                    id, fatal=False, note=f'Downloading {type} DASH manifest', errnote=False)
+                yield from self._set_format_type(dash_formats, type)
+
+
+class TubeTuGrazIE(TubeTuGrazBaseIE):
+    IE_DESC = 'tube.tugraz.at'
+
+    _VALID_URL = r'''(?x)
+        https?://tube\.tugraz\.at/paella/ui/watch.html\?id=
+        (?P<id>[0-9a-fA-F]{8}-(?:[0-9a-fA-F]{4}-){3}[0-9a-fA-F]{12})
+    '''
+    _TESTS = [
+        {
+            'url': 'https://tube.tugraz.at/paella/ui/watch.html?id=f2634392-e40e-4ac7-9ddc-47764aa23d40',
+            'md5': 'a23a3d5c9aaca2b84932fdba66e17145',
+            'info_dict': {
+                'id': 'f2634392-e40e-4ac7-9ddc-47764aa23d40',
+                'ext': 'mp4',
+                'title': '#6 (23.11.2017)',
+                'episode': '#6 (23.11.2017)',
+                'series': '[INB03001UF] Einführung in die strukturierte Programmierung',
+                'creator': 'Safran C',
+                'duration': 3295818,
+                'series_id': 'b1192fff-2aa7-4bf0-a5cf-7b15c3bd3b34',
+            }
+        }, {
+            'url': 'https://tube.tugraz.at/paella/ui/watch.html?id=2df6d787-e56a-428d-8ef4-d57f07eef238',
+            'md5': 'de0d854a56bf7318d2b693fe1adb89a5',
+            'info_dict': {
+                'id': '2df6d787-e56a-428d-8ef4-d57f07eef238',
+                'title': 'TubeTuGraz video #2df6d787-e56a-428d-8ef4-d57f07eef238',
+                'ext': 'mp4',
+            },
+            'expected_warnings': ['Extractor failed to obtain "title"'],
+        }
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        episode_data = self._download_json(
+            self._API_EPISODE, video_id, query={'id': video_id, 'limit': 1}, note='Downloading episode metadata')
+
+        episode_info = traverse_obj(episode_data, ('search-results', 'result'), default={'id': video_id})
+        return self._extract_episode(episode_info)
+
+
+class TubeTuGrazSeriesIE(TubeTuGrazBaseIE):
+    _VALID_URL = r'''(?x)
+        https?://tube\.tugraz\.at/paella/ui/browse\.html\?series=
+        (?P<id>[0-9a-fA-F]{8}-(?:[0-9a-fA-F]{4}-){3}[0-9a-fA-F]{12})
+    '''
+    _TESTS = [{
+        'url': 'https://tube.tugraz.at/paella/ui/browse.html?series=0e6351b7-c372-491e-8a49-2c9b7e21c5a6',
+        'id': '0e6351b7-c372-491e-8a49-2c9b7e21c5a6',
+        'info_dict': {
+            'id': '0e6351b7-c372-491e-8a49-2c9b7e21c5a6',
+            'title': '[209351] Strassenwesen',
+        },
+        'playlist': [
+            {
+                'info_dict': {
+                    'id': 'ee17ce5d-34e2-48b7-a76a-fed148614e11',
+                    'series_id': '0e6351b7-c372-491e-8a49-2c9b7e21c5a6',
+                    'ext': 'mp4',
+                    'title': '#4 Detailprojekt',
+                    'episode': '#4 Detailprojekt',
+                    'series': '[209351] Strassenwesen',
+                    'creator': 'Neuhold R',
+                    'duration': 6127024,
+                }
+            },
+            {
+                'info_dict': {
+                    'id': '87350498-799a-44d3-863f-d1518a98b114',
+                    'series_id': '0e6351b7-c372-491e-8a49-2c9b7e21c5a6',
+                    'ext': 'mp4',
+                    'title': '#3 Generelles Projekt',
+                    'episode': '#3 Generelles Projekt',
+                    'series': '[209351] Strassenwesen',
+                    'creator': 'Neuhold R',
+                    'duration': 5374422,
+                }
+            },
+            {
+                'info_dict': {
+                    'id': '778599ea-489e-4189-9e05-3b4888e19bcd',
+                    'series_id': '0e6351b7-c372-491e-8a49-2c9b7e21c5a6',
+                    'ext': 'mp4',
+                    'title': '#2 Vorprojekt',
+                    'episode': '#2 Vorprojekt',
+                    'series': '[209351] Strassenwesen',
+                    'creator': 'Neuhold R',
+                    'duration': 5566404,
+                }
+            },
+            {
+                'info_dict': {
+                    'id': '75e4c71c-d99d-4e56-b0e6-4f2bcdf11f29',
+                    'series_id': '0e6351b7-c372-491e-8a49-2c9b7e21c5a6',
+                    'ext': 'mp4',
+                    'title': '#1 Variantenstudium',
+                    'episode': '#1 Variantenstudium',
+                    'series': '[209351] Strassenwesen',
+                    'creator': 'Neuhold R',
+                    'duration': 5420200,
+                }
+            }
+        ],
+        'min_playlist_count': 4
+    }]
+
+    def _real_extract(self, url):
+        id = self._match_id(url)
+        episodes_data = self._download_json(self._API_EPISODE, id, query={'sid': id}, note='Downloading episode list')
+        series_data = self._download_json(
+            'https://tube.tugraz.at/series/series.json', id, fatal=False,
+            note='downloading series metadata', errnote='failed to download series metadata',
+            query={
+                'seriesId': id,
+                'count': 1,
+                'sort': 'TITLE'
+            })
+
+        return self.playlist_result(
+            map(self._extract_episode, episodes_data['search-results']['result']), id,
+            traverse_obj(series_data, ('catalogs', 0, 'http://purl.org/dc/terms/', 'title', 0, 'value')))