@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/brilliantpala.py

@@ -0,0 +1,127 @@
+import hashlib
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    traverse_obj,
+    urlencode_postdata,
+)
+
+
+class BrilliantpalaBaseIE(InfoExtractor):
+    _NETRC_MACHINE = 'brilliantpala'
+    _DOMAIN = '{subdomain}.brilliantpala.org'
+
+    def _initialize_pre_login(self):
+        self._HOMEPAGE = f'https://{self._DOMAIN}'
+        self._LOGIN_API = f'{self._HOMEPAGE}/login/'
+        self._LOGOUT_DEVICES_API = f'{self._HOMEPAGE}/logout_devices/?next=/'
+        self._CONTENT_API = f'{self._HOMEPAGE}/api/v2.4/contents/{{content_id}}/'
+        self._HLS_AES_URI = f'{self._HOMEPAGE}/api/v2.5/video_contents/{{content_id}}/key/'
+
+    def _get_logged_in_username(self, url, video_id):
+        webpage, urlh = self._download_webpage_handle(url, video_id)
+        if urlh.url.startswith(self._LOGIN_API):
+            self.raise_login_required()
+        return self._html_search_regex(
+            r'"username"\s*:\s*"(?P<username>[^"]+)"', webpage, 'logged-in username')
+
+    def _perform_login(self, username, password):
+        login_form = self._hidden_inputs(self._download_webpage(
+            self._LOGIN_API, None, 'Downloading login page'))
+        login_form.update({
+            'username': username,
+            'password': password,
+        })
+        self._set_cookie(self._DOMAIN, 'csrftoken', login_form['csrfmiddlewaretoken'])
+
+        logged_page = self._download_webpage(
+            self._LOGIN_API, None, note='Logging in', headers={'Referer': self._LOGIN_API},
+            data=urlencode_postdata(login_form))
+
+        if self._html_search_regex(
+                r'(Your username / email and password)', logged_page, 'auth fail', default=None):
+            raise ExtractorError('wrong username or password', expected=True)
+
+        # the maximum number of logins is one
+        if self._html_search_regex(
+                r'(Logout Other Devices)', logged_page, 'logout devices button', default=None):
+            logout_device_form = self._hidden_inputs(logged_page)
+            self._download_webpage(
+                self._LOGOUT_DEVICES_API, None, headers={'Referer': self._LOGIN_API},
+                note='Logging out other devices', data=urlencode_postdata(logout_device_form))
+
+    def _real_extract(self, url):
+        course_id, content_id = self._match_valid_url(url).group('course_id', 'content_id')
+        video_id = f'{course_id}-{content_id}'
+
+        username = self._get_logged_in_username(url, video_id)
+
+        content_json = self._download_json(
+            self._CONTENT_API.format(content_id=content_id), video_id,
+            note='Fetching content info', errnote='Unable to fetch content info')
+
+        entries = []
+        for stream in traverse_obj(content_json, ('video', 'streams', lambda _, v: v['id'] and v['url'])):
+            formats = self._extract_m3u8_formats(stream['url'], video_id, fatal=False)
+            if not formats:
+                continue
+            entries.append({
+                'id': str(stream['id']),
+                'title': content_json.get('title'),
+                'formats': formats,
+                'hls_aes': {'uri': self._HLS_AES_URI.format(content_id=content_id)},
+                'http_headers': {'X-Key': hashlib.sha256(username.encode('ascii')).hexdigest()},
+                'thumbnail': content_json.get('cover_image'),
+            })
+
+        return self.playlist_result(
+            entries, playlist_id=video_id, playlist_title=content_json.get('title'))
+
+
+class BrilliantpalaElearnIE(BrilliantpalaBaseIE):
+    IE_NAME = 'Brilliantpala:Elearn'
+    IE_DESC = 'VoD on elearn.brilliantpala.org'
+    _VALID_URL = r'https?://elearn\.brilliantpala\.org/courses/(?P<course_id>\d+)/contents/(?P<content_id>\d+)/?'
+    _TESTS = [{
+        'url': 'https://elearn.brilliantpala.org/courses/42/contents/12345/',
+        'only_matching': True,
+    }, {
+        'url': 'https://elearn.brilliantpala.org/courses/98/contents/36683/',
+        'info_dict': {
+            'id': '23577',
+            'ext': 'mp4',
+            'title': 'Physical World, Units and Measurements  - 1',
+            'thumbnail': 'https://d1j3vi2u94ebt0.cloudfront.net/institute/brilliantpalalms/chapter_contents/26237/e657f81b90874be19795c7ea081f8d5c.png',
+            'live_status': 'not_live',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    _DOMAIN = BrilliantpalaBaseIE._DOMAIN.format(subdomain='elearn')
+
+
+class BrilliantpalaClassesIE(BrilliantpalaBaseIE):
+    IE_NAME = 'Brilliantpala:Classes'
+    IE_DESC = 'VoD on classes.brilliantpala.org'
+    _VALID_URL = r'https?://classes\.brilliantpala\.org/courses/(?P<course_id>\d+)/contents/(?P<content_id>\d+)/?'
+    _TESTS = [{
+        'url': 'https://classes.brilliantpala.org/courses/42/contents/12345/',
+        'only_matching': True,
+    }, {
+        'url': 'https://classes.brilliantpala.org/courses/416/contents/25445/',
+        'info_dict': {
+            'id': '9128',
+            'ext': 'mp4',
+            'title': 'Motion in a Straight Line - Class 1',
+            'thumbnail': 'https://d3e4y8hquds3ek.cloudfront.net/institute/brilliantpalaelearn/chapter_contents/ff5ba838d0ec43419f67387fe1a01fa8.png',
+            'live_status': 'not_live',
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    _DOMAIN = BrilliantpalaBaseIE._DOMAIN.format(subdomain='classes')

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

@@ -0,0 +1,34 @@
+from .common import InfoExtractor
+from .jwplatform import JWPlatformIE
+
+
+class BundesligaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bundesliga\.com/[a-z]{2}/bundesliga/videos(?:/[^?]+)?\?vid=(?P<id>[a-zA-Z0-9]{8})'
+    _TESTS = [
+        {
+            'url': 'https://www.bundesliga.com/en/bundesliga/videos?vid=bhhHkKyN',
+            'md5': '8fc3b25cd12440e3a8cdc51f1493849c',
+            'info_dict': {
+                'id': 'bhhHkKyN',
+                'ext': 'mp4',
+                'title': 'Watch: Alphonso Davies and Jeremie Frimpong head-to-head',
+                'thumbnail': 'https://cdn.jwplayer.com/v2/media/bhhHkKyN/poster.jpg?width=720',
+                'upload_date': '20220928',
+                'duration': 146,
+                'timestamp': 1664366511,
+                'description': 'md5:803d4411bd134140c774021dd4b7598b'
+            }
+        },
+        {
+            'url': 'https://www.bundesliga.com/en/bundesliga/videos/latest-features/T8IKc8TX?vid=ROHjs06G',
+            'only_matching': True
+        },
+        {
+            'url': 'https://www.bundesliga.com/en/bundesliga/videos/goals?vid=mOG56vWA',
+            'only_matching': True
+        }
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self.url_result(f'jwplatform:{video_id}', JWPlatformIE, video_id)

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

@@ -0,0 +1,123 @@
+import re
+from functools import partial
+
+from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    bug_reports_message,
+    clean_html,
+    format_field,
+    get_element_text_and_html_by_tag,
+    int_or_none,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class BundestagIE(InfoExtractor):
+    _VALID_URL = [
+        r'https?://dbtg\.tv/[cf]vid/(?P<id>\d+)',
+        r'https?://www\.bundestag\.de/mediathek/?\?(?:[^#]+&)?videoid=(?P<id>\d+)',
+    ]
+    _TESTS = [{
+        'url': 'https://dbtg.tv/cvid/7605304',
+        'info_dict': {
+            'id': '7605304',
+            'ext': 'mp4',
+            'title': '145. Sitzung vom 15.12.2023, TOP 24 Barrierefreiheit',
+            'description': 'md5:321a9dc6bdad201264c0045efc371561',
+        },
+    }, {
+        'url': 'https://www.bundestag.de/mediathek?videoid=7602120&url=L21lZGlhdGhla292ZXJsYXk=&mod=mediathek',
+        'info_dict': {
+            'id': '7602120',
+            'ext': 'mp4',
+            'title': '130. Sitzung vom 18.10.2023, TOP 1 Befragung der Bundesregierung',
+            'description': 'Befragung der Bundesregierung',
+        },
+    }, {
+        'url': 'https://www.bundestag.de/mediathek?videoid=7604941#url=L21lZGlhdGhla292ZXJsYXk/dmlkZW9pZD03NjA0OTQx&mod=mediathek',
+        'only_matching': True,
+    }, {
+        'url': 'http://dbtg.tv/fvid/3594346',
+        'only_matching': True,
+    }]
+
+    _OVERLAY_URL = 'https://www.bundestag.de/mediathekoverlay'
+    _INSTANCE_FORMAT = 'https://cldf-wzw-od.r53.cdn.tv1.eu/13014bundestagod/_definst_/13014bundestag/ondemand/3777parlamentsfernsehen/archiv/app144277506/145293313/{0}/{0}_playlist.smil/playlist.m3u8'
+
+    _SHARE_URL = 'https://webtv.bundestag.de/player/macros/_x_s-144277506/shareData.json?contentId='
+    _SHARE_AUDIO_REGEX = r'/\d+_(?P<codec>\w+)_(?P<bitrate>\d+)kb_(?P<channels>\w+)_\w+_\d+\.(?P<ext>\w+)'
+    _SHARE_VIDEO_REGEX = r'/\d+_(?P<codec>\w+)_(?P<width>\w+)_(?P<height>\w+)_(?P<bitrate>\d+)kb_\w+_\w+_\d+\.(?P<ext>\w+)'
+
+    def _bt_extract_share_formats(self, video_id):
+        share_data = self._download_json(
+            f'{self._SHARE_URL}{video_id}', video_id, note='Downloading share format JSON')
+        if traverse_obj(share_data, ('status', 'code', {int})) != 1:
+            self.report_warning(format_field(
+                share_data, [('status', 'message', {str})],
+                'Share API response: %s', default='Unknown Share API Error')
+                + bug_reports_message())
+            return
+
+        for name, url in share_data.items():
+            if not isinstance(name, str) or not url_or_none(url):
+                continue
+
+            elif name.startswith('audio'):
+                match = re.search(self._SHARE_AUDIO_REGEX, url)
+                yield {
+                    'format_id': name,
+                    'url': url,
+                    'vcodec': 'none',
+                    **traverse_obj(match, {
+                        'acodec': 'codec',
+                        'audio_channels': ('channels', {{'mono': 1, 'stereo': 2}.get}),
+                        'abr': ('bitrate', {int_or_none}),
+                        'ext': 'ext',
+                    }),
+                }
+
+            elif name.startswith('download'):
+                match = re.search(self._SHARE_VIDEO_REGEX, url)
+                yield {
+                    'format_id': name,
+                    'url': url,
+                    **traverse_obj(match, {
+                        'vcodec': 'codec',
+                        'tbr': ('bitrate', {int_or_none}),
+                        'width': ('width', {int_or_none}),
+                        'height': ('height', {int_or_none}),
+                        'ext': 'ext',
+                    }),
+                }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        formats = []
+        result = {'id': video_id, 'formats': formats}
+
+        try:
+            formats.extend(self._extract_m3u8_formats(
+                self._INSTANCE_FORMAT.format(video_id), video_id, m3u8_id='instance'))
+        except ExtractorError as error:
+            if isinstance(error.cause, HTTPError) and error.cause.status == 404:
+                raise ExtractorError('Could not find video id', expected=True)
+            self.report_warning(f'Error extracting hls formats: {error}', video_id)
+        formats.extend(self._bt_extract_share_formats(video_id))
+        if not formats:
+            self.raise_no_formats('Could not find suitable formats', video_id=video_id)
+
+        result.update(traverse_obj(self._download_webpage(
+            self._OVERLAY_URL, video_id,
+            query={'videoid': video_id, 'view': 'main'},
+            note='Downloading metadata overlay', fatal=False,
+        ), {
+            'title': (
+                {partial(get_element_text_and_html_by_tag, 'h3')}, 0,
+                {partial(re.sub, r'<span[^>]*>[^<]+</span>', '')}, {clean_html}),
+            'description': ({partial(get_element_text_and_html_by_tag, 'p')}, 0, {clean_html}),
+        }))
+
+        return result

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

@@ -0,0 +1,45 @@
+from .common import InfoExtractor
+from .jwplatform import JWPlatformIE
+
+
+class BusinessInsiderIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:[^/]+\.)?businessinsider\.(?:com|nl)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'http://uk.businessinsider.com/how-much-radiation-youre-exposed-to-in-everyday-life-2016-6',
+        'md5': 'ffed3e1e12a6f950aa2f7d83851b497a',
+        'info_dict': {
+            'id': 'cjGDb0X9',
+            'ext': 'mp4',
+            'title': "Bananas give you more radiation exposure than living next to a nuclear power plant",
+            'description': 'md5:0175a3baf200dd8fa658f94cade841b3',
+            'upload_date': '20160611',
+            'timestamp': 1465675620,
+        },
+    }, {
+        'url': 'https://www.businessinsider.nl/5-scientifically-proven-things-make-you-less-attractive-2017-7/',
+        'md5': '43f438dbc6da0b89f5ac42f68529d84a',
+        'info_dict': {
+            'id': '5zJwd4FK',
+            'ext': 'mp4',
+            'title': 'Deze dingen zorgen ervoor dat je minder snel een date scoort',
+            'description': 'md5:2af8975825d38a4fed24717bbe51db49',
+            'upload_date': '20170705',
+            'timestamp': 1499270528,
+        },
+    }, {
+        'url': 'http://www.businessinsider.com/excel-index-match-vlookup-video-how-to-2015-2?IR=T',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        jwplatform_id = self._search_regex(
+            (r'data-media-id=["\']([a-zA-Z0-9]{8})',
+             r'id=["\']jwplayer_([a-zA-Z0-9]{8})',
+             r'id["\']?\s*:\s*["\']?([a-zA-Z0-9]{8})',
+             r'(?:jwplatform\.com/players/|jwplayer_)([a-zA-Z0-9]{8})'),
+            webpage, 'jwplatform id')
+        return self.url_result(
+            'jwplatform:%s' % jwplatform_id, ie=JWPlatformIE.ie_key(),
+            video_id=video_id)

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

@@ -0,0 +1,95 @@
+import json
+import re
+
+from .common import InfoExtractor
+from .facebook import FacebookIE
+
+
+class BuzzFeedIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?buzzfeed\.com/[^?#]*?/(?P<id>[^?#]+)'
+    _TESTS = [{
+        'url': 'http://www.buzzfeed.com/abagg/this-angry-ram-destroys-a-punching-bag-like-a-boss?utm_term=4ldqpia',
+        'info_dict': {
+            'id': 'this-angry-ram-destroys-a-punching-bag-like-a-boss',
+            'title': 'This Angry Ram Destroys A Punching Bag Like A Boss',
+            'description': 'Rambro!',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'aVCR29aE_OQ',
+                'ext': 'mp4',
+                'title': 'Angry Ram destroys a punching bag..',
+                'description': 'md5:c59533190ef23fd4458a5e8c8c872345',
+                'upload_date': '20141024',
+                'uploader_id': 'Buddhanz1',
+                'uploader': 'Angry Ram',
+            }
+        }]
+    }, {
+        'url': 'http://www.buzzfeed.com/sheridanwatson/look-at-this-cute-dog-omg?utm_term=4ldqpia',
+        'params': {
+            'skip_download': True,  # Got enough YouTube download tests
+        },
+        'info_dict': {
+            'id': 'look-at-this-cute-dog-omg',
+            'description': 're:Munchkin the Teddy Bear is back ?!',
+            'title': 'You Need To Stop What You\'re Doing And Watching This Dog Walk On A Treadmill',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'mVmBL8B-In0',
+                'ext': 'mp4',
+                'title': 're:Munchkin the Teddy Bear gets her exercise',
+                'description': 'md5:28faab95cda6e361bcff06ec12fc21d8',
+                'upload_date': '20141124',
+                'uploader_id': 'CindysMunchkin',
+                'uploader': 're:^Munchkin the',
+            },
+        }]
+    }, {
+        'url': 'http://www.buzzfeed.com/craigsilverman/the-most-adorable-crash-landing-ever#.eq7pX0BAmK',
+        'info_dict': {
+            'id': 'the-most-adorable-crash-landing-ever',
+            'title': 'Watch This Baby Goose Make The Most Adorable Crash Landing',
+            'description': 'This gosling knows how to stick a landing.',
+        },
+        'playlist': [{
+            'md5': '763ca415512f91ca62e4621086900a23',
+            'info_dict': {
+                'id': '971793786185728',
+                'ext': 'mp4',
+                'title': 'We set up crash pads so that the goslings on our roof would have a safe landi...',
+                'uploader': 'Calgary Outdoor Centre-University of Calgary',
+            },
+        }],
+        'add_ie': ['Facebook'],
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        all_buckets = re.findall(
+            r'(?s)<div class="video-embed[^"]*"..*?rel:bf_bucket_data=\'([^\']+)\'',
+            webpage)
+
+        entries = []
+        for bd_json in all_buckets:
+            bd = json.loads(bd_json)
+            video = bd.get('video') or bd.get('progload_video')
+            if not video:
+                continue
+            entries.append(self.url_result(video['url']))
+
+        facebook_urls = FacebookIE._extract_embed_urls(url, webpage)
+        entries.extend([
+            self.url_result(facebook_url)
+            for facebook_url in facebook_urls])
+
+        return {
+            '_type': 'playlist',
+            'id': playlist_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'entries': entries,
+        }

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

@@ -0,0 +1,104 @@
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    merge_dicts,
+    parse_duration,
+    url_or_none,
+)
+
+
+class BYUtvIE(InfoExtractor):
+    _WORKING = False
+    _VALID_URL = r'https?://(?:www\.)?byutv\.org/(?:watch|player)/(?!event/)(?P<id>[0-9a-f-]+)(?:/(?P<display_id>[^/?#&]+))?'
+    _TESTS = [{
+        'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
+        'info_dict': {
+            'id': 'ZvanRocTpW-G5_yZFeltTAMv6jxOU9KH',
+            'display_id': 'studio-c-season-5-episode-5',
+            'ext': 'mp4',
+            'title': 'Season 5 Episode 5',
+            'description': 'md5:1d31dc18ef4f075b28f6a65937d22c65',
+            'thumbnail': r're:^https?://.*',
+            'duration': 1486.486,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # dvr
+        'url': 'https://www.byutv.org/player/8f1dab9b-b243-47c8-b525-3e2d021a3451/byu-softball-pacific-vs-byu-41219---game-2',
+        'info_dict': {
+            'id': '8f1dab9b-b243-47c8-b525-3e2d021a3451',
+            'display_id': 'byu-softball-pacific-vs-byu-41219---game-2',
+            'ext': 'mp4',
+            'title': 'Pacific vs. BYU (4/12/19)',
+            'description': 'md5:1ac7b57cb9a78015910a4834790ce1f3',
+            'duration': 11645,
+        },
+        'params': {
+            'skip_download': True
+        },
+    }, {
+        'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.byutv.org/player/27741493-dc83-40b0-8420-e7ae38a2ae98/byu-football-toledo-vs-byu-93016?listid=4fe0fee5-0d3c-4a29-b725-e4948627f472&listindex=0&q=toledo',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id') or video_id
+
+        video = self._download_json(
+            'https://api.byutv.org/api3/catalog/getvideosforcontent',
+            display_id, query={
+                'contentid': video_id,
+                'channel': 'byutv',
+                'x-byutv-context': 'web$US',
+            }, headers={
+                'x-byutv-context': 'web$US',
+                'x-byutv-platformkey': 'xsaaw9c7y5',
+            })
+
+        info = {}
+        formats = []
+        subtitles = {}
+        for format_id, ep in video.items():
+            if not isinstance(ep, dict):
+                continue
+            video_url = url_or_none(ep.get('videoUrl'))
+            if not video_url:
+                continue
+            ext = determine_ext(video_url)
+            if ext == 'm3u8':
+                m3u8_fmts, m3u8_subs = self._extract_m3u8_formats_and_subtitles(
+                    video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False)
+                formats.extend(m3u8_fmts)
+                subtitles = self._merge_subtitles(subtitles, m3u8_subs)
+            elif ext == 'mpd':
+                mpd_fmts, mpd_subs = self._extract_mpd_formats_and_subtitles(
+                    video_url, video_id, mpd_id='dash', fatal=False)
+                formats.extend(mpd_fmts)
+                subtitles = self._merge_subtitles(subtitles, mpd_subs)
+            else:
+                formats.append({
+                    'url': video_url,
+                    'format_id': format_id,
+                })
+            merge_dicts(info, {
+                'title': ep.get('title'),
+                'description': ep.get('description'),
+                'thumbnail': ep.get('imageThumbnail'),
+                'duration': parse_duration(ep.get('length')),
+            })
+
+        return merge_dicts(info, {
+            'id': video_id,
+            'display_id': display_id,
+            'title': display_id,
+            'formats': formats,
+            'subtitles': subtitles,
+        })

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/c56.py

@@ -0,0 +1,59 @@
+from .common import InfoExtractor
+from ..utils import js_to_json
+
+
+class C56IE(InfoExtractor):
+    _VALID_URL = r'https?://(?:(?:www|player)\.)?56\.com/(?:.+?/)?(?:v_|(?:play_album.+-))(?P<textid>.+?)\.(?:html|swf)'
+    IE_NAME = '56.com'
+    _TESTS = [{
+        'url': 'http://www.56.com/u39/v_OTM0NDA3MTY.html',
+        'md5': 'e59995ac63d0457783ea05f93f12a866',
+        'info_dict': {
+            'id': '93440716',
+            'ext': 'flv',
+            'title': '网事知多少 第32期：车怒',
+            'duration': 283.813,
+        },
+    }, {
+        'url': 'http://www.56.com/u47/v_MTM5NjQ5ODc2.html',
+        'md5': '',
+        'info_dict': {
+            'id': '82247482',
+            'title': '爱的诅咒之杜鹃花开',
+        },
+        'playlist_count': 7,
+        'add_ie': ['Sohu'],
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        text_id = mobj.group('textid')
+
+        webpage = self._download_webpage(url, text_id)
+        sohu_video_info_str = self._search_regex(
+            r'var\s+sohuVideoInfo\s*=\s*({[^}]+});', webpage, 'Sohu video info', default=None)
+        if sohu_video_info_str:
+            sohu_video_info = self._parse_json(
+                sohu_video_info_str, text_id, transform_source=js_to_json)
+            return self.url_result(sohu_video_info['url'], 'Sohu')
+
+        page = self._download_json(
+            'http://vxml.56.com/json/%s/' % text_id, text_id, 'Downloading video info')
+
+        info = page['info']
+
+        formats = [
+            {
+                'format_id': f['type'],
+                'filesize': int(f['filesize']),
+                'url': f['url']
+            } for f in info['rfiles']
+        ]
+
+        return {
+            'id': info['vid'],
+            'title': info['Subject'],
+            'duration': int(info['duration']) / 1000.0,
+            'formats': formats,
+            'thumbnail': info.get('bimg') or info.get('img'),
+        }

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

@@ -0,0 +1,32 @@
+from .common import InfoExtractor
+
+
+class CableAVIE(InfoExtractor):
+    _VALID_URL = r'https?://cableav\.tv/(?P<id>[a-zA-Z0-9]+)'
+    _TESTS = [{
+        'url': 'https://cableav.tv/lS4iR9lWjN8/',
+        'md5': '7e3fe5e49d61c4233b7f5b0f69b15e18',
+        'info_dict': {
+            'id': 'lS4iR9lWjN8',
+            'ext': 'mp4',
+            'title': '國產麻豆AV 叮叮映畫 DDF001 情欲小說家 - CableAV',
+            'description': '國產AV 480p, 720p 国产麻豆AV 叮叮映画 DDF001 情欲小说家',
+            'thumbnail': r're:^https?://.*\.jpg$',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._og_search_video_url(webpage, secure=False)
+
+        formats = self._extract_m3u8_formats(video_url, video_id, 'mp4')
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'formats': formats,
+        }