@tushar-br/desktop 1.0.283 → 1.0.284

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

@@ -1,119 +0,0 @@
-import re
-
-from .common import InfoExtractor
-from ..utils import extract_attributes
-
-
-class BFMTVBaseIE(InfoExtractor):
-    _VALID_URL_BASE = r'https?://(?:www\.|rmc\.)?bfmtv\.com/'
-    _VALID_URL_TMPL = _VALID_URL_BASE + r'(?:[^/]+/)*[^/?&#]+_%s[A-Z]-(?P<id>\d{12})\.html'
-    _VIDEO_BLOCK_REGEX = r'(<div[^>]+class="video_block[^"]*"[^>]*>)'
-    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
-
-    def _brightcove_url_result(self, video_id, video_block):
-        account_id = video_block.get('accountid') or '876450612001'
-        player_id = video_block.get('playerid') or 'I2qBTln4u'
-        return self.url_result(
-            self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, video_id),
-            'BrightcoveNew', video_id)
-
-
-class BFMTVIE(BFMTVBaseIE):
-    IE_NAME = 'bfmtv'
-    _VALID_URL = BFMTVBaseIE._VALID_URL_TMPL % 'V'
-    _TESTS = [{
-        'url': 'https://www.bfmtv.com/politique/emmanuel-macron-l-islam-est-une-religion-qui-vit-une-crise-aujourd-hui-partout-dans-le-monde_VN-202010020146.html',
-        'info_dict': {
-            'id': '6196747868001',
-            'ext': 'mp4',
-            'title': 'Emmanuel Macron: "L\'Islam est une religion qui vit une crise aujourd’hui, partout dans le monde"',
-            'description': 'Le Président s\'exprime sur la question du séparatisme depuis les Mureaux, dans les Yvelines.',
-            'uploader_id': '876450610001',
-            'upload_date': '20201002',
-            'timestamp': 1601629620,
-            'duration': 44.757,
-            'tags': ['bfmactu', 'politique'],
-            'thumbnail': 'https://cf-images.eu-west-1.prod.boltdns.net/v1/static/876450610001/5041f4c1-bc48-4af8-a256-1b8300ad8ef0/cf2f9114-e8e2-4494-82b4-ab794ea4bc7d/1920x1080/match/image.jpg',
-        },
-    }]
-
-    def _real_extract(self, url):
-        bfmtv_id = self._match_id(url)
-        webpage = self._download_webpage(url, bfmtv_id)
-        video_block = extract_attributes(self._search_regex(
-            self._VIDEO_BLOCK_REGEX, webpage, 'video block'))
-        return self._brightcove_url_result(video_block['videoid'], video_block)
-
-
-class BFMTVLiveIE(BFMTVIE):  # XXX: Do not subclass from concrete IE
-    IE_NAME = 'bfmtv:live'
-    _VALID_URL = BFMTVBaseIE._VALID_URL_BASE + '(?P<id>(?:[^/]+/)?en-direct)'
-    _TESTS = [{
-        'url': 'https://www.bfmtv.com/en-direct/',
-        'info_dict': {
-            'id': '5615950982001',
-            'ext': 'mp4',
-            'title': r're:^le direct BFMTV WEB \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
-            'uploader_id': '876450610001',
-            'upload_date': '20220926',
-            'timestamp': 1664207191,
-            'live_status': 'is_live',
-            'thumbnail': r're:https://.+/image\.jpg',
-            'tags': [],
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        'url': 'https://www.bfmtv.com/economie/en-direct/',
-        'only_matching': True,
-    }]
-
-
-class BFMTVArticleIE(BFMTVBaseIE):
-    IE_NAME = 'bfmtv:article'
-    _VALID_URL = BFMTVBaseIE._VALID_URL_TMPL % 'A'
-    _TESTS = [{
-        'url': 'https://www.bfmtv.com/sante/covid-19-un-responsable-de-l-institut-pasteur-se-demande-quand-la-france-va-se-reconfiner_AV-202101060198.html',
-        'info_dict': {
-            'id': '202101060198',
-            'title': 'Covid-19: un responsable de l\'Institut Pasteur se demande "quand la France va se reconfiner"',
-            'description': 'md5:947974089c303d3ac6196670ae262843',
-        },
-        'playlist_count': 2,
-    }, {
-        'url': 'https://www.bfmtv.com/international/pour-bolsonaro-le-bresil-est-en-faillite-mais-il-ne-peut-rien-faire_AD-202101060232.html',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.bfmtv.com/sante/covid-19-oui-le-vaccin-de-pfizer-distribue-en-france-a-bien-ete-teste-sur-des-personnes-agees_AN-202101060275.html',
-        'only_matching': True,
-    }, {
-        'url': 'https://rmc.bfmtv.com/actualites/societe/transports/ce-n-est-plus-tout-rentable-le-bioethanol-e85-depasse-1eu-le-litre-des-automobilistes-regrettent_AV-202301100268.html',
-        'info_dict': {
-            'id': '6318445464112',
-            'ext': 'mp4',
-            'title': 'Le plein de bioéthanol fait de plus en plus mal à la pompe',
-            'uploader_id': '876630703001',
-            'upload_date': '20230110',
-            'timestamp': 1673341692,
-            'duration': 109.269,
-            'tags': ['rmc', 'show', 'apolline de malherbe', 'info', 'talk', 'matinale', 'radio'],
-            'thumbnail': 'https://cf-images.eu-west-1.prod.boltdns.net/v1/static/876630703001/5bef74b8-9d5e-4480-a21f-60c2e2480c46/96c88b74-f9db-45e1-8040-e199c5da216c/1920x1080/match/image.jpg'
-        }
-    }]
-
-    def _real_extract(self, url):
-        bfmtv_id = self._match_id(url)
-        webpage = self._download_webpage(url, bfmtv_id)
-
-        entries = []
-        for video_block_el in re.findall(self._VIDEO_BLOCK_REGEX, webpage):
-            video_block = extract_attributes(video_block_el)
-            video_id = video_block.get('videoid')
-            if not video_id:
-                continue
-            entries.append(self._brightcove_url_result(video_id, video_block))
-
-        return self.playlist_result(
-            entries, bfmtv_id, self._og_search_title(webpage, fatal=False),
-            self._html_search_meta(['og:description', 'description'], webpage))

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

@@ -1,197 +0,0 @@
-from functools import partial
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    clean_html,
-    determine_ext,
-    format_field,
-    int_or_none,
-    js_to_json,
-    orderedSet,
-    parse_iso8601,
-    traverse_obj,
-    url_or_none,
-)
-
-
-class BibelTVBaseIE(InfoExtractor):
-    _GEO_COUNTRIES = ['AT', 'CH', 'DE']
-    _GEO_BYPASS = False
-
-    API_URL = 'https://www.bibeltv.de/mediathek/api'
-    AUTH_TOKEN = 'j88bRXY8DsEqJ9xmTdWhrByVi5Hm'
-
-    def _extract_formats_and_subtitles(self, data, crn_id, *, is_live=False):
-        formats = []
-        subtitles = {}
-        for media_url in traverse_obj(data, (..., 'src', {url_or_none})):
-            media_ext = determine_ext(media_url)
-            if media_ext == 'm3u8':
-                m3u8_formats, m3u8_subs = self._extract_m3u8_formats_and_subtitles(
-                    media_url, crn_id, live=is_live)
-                formats.extend(m3u8_formats)
-                subtitles.update(m3u8_subs)
-            elif media_ext == 'mpd':
-                mpd_formats, mpd_subs = self._extract_mpd_formats_and_subtitles(media_url, crn_id)
-                formats.extend(mpd_formats)
-                subtitles.update(mpd_subs)
-            elif media_ext == 'mp4':
-                formats.append({'url': media_url})
-            else:
-                self.report_warning(f'Unknown format {media_ext!r}')
-
-        return formats, subtitles
-
-    @staticmethod
-    def _extract_base_info(data):
-        return {
-            'id': data['crn'],
-            **traverse_obj(data, {
-                'title': 'title',
-                'description': 'description',
-                'duration': ('duration', {partial(int_or_none, scale=1000)}),
-                'timestamp': ('schedulingStart', {parse_iso8601}),
-                'season_number': 'seasonNumber',
-                'episode_number': 'episodeNumber',
-                'view_count': 'viewCount',
-                'like_count': 'likeCount',
-            }),
-            'thumbnails': orderedSet(traverse_obj(data, ('images', ..., {
-                'url': ('url', {url_or_none}),
-            }))),
-        }
-
-    def _extract_url_info(self, data):
-        return {
-            '_type': 'url',
-            'url': format_field(data, 'slug', 'https://www.bibeltv.de/mediathek/videos/%s'),
-            **self._extract_base_info(data),
-        }
-
-    def _extract_video_info(self, data):
-        crn_id = data['crn']
-
-        if data.get('drm'):
-            self.report_drm(crn_id)
-
-        json_data = self._download_json(
-            format_field(data, 'id', f'{self.API_URL}/video/%s'), crn_id,
-            headers={'Authorization': self.AUTH_TOKEN}, fatal=False,
-            errnote='No formats available') or {}
-
-        formats, subtitles = self._extract_formats_and_subtitles(
-            traverse_obj(json_data, ('video', 'videoUrls', ...)), crn_id)
-
-        return {
-            '_type': 'video',
-            **self._extract_base_info(data),
-            'formats': formats,
-            'subtitles': subtitles,
-        }
-
-
-class BibelTVVideoIE(BibelTVBaseIE):
-    IE_DESC = 'BibelTV single video'
-    _VALID_URL = r'https?://(?:www\.)?bibeltv\.de/mediathek/videos/(?P<id>\d+)[\w-]+'
-    IE_NAME = 'bibeltv:video'
-
-    _TESTS = [{
-        'url': 'https://www.bibeltv.de/mediathek/videos/344436-alte-wege',
-        'md5': 'ec1c07efe54353780512e8a4103b612e',
-        'info_dict': {
-            'id': '344436',
-            'ext': 'mp4',
-            'title': 'Alte Wege',
-            'description': 'md5:2f4eb7294c9797a47b8fd13cccca22e9',
-            'timestamp': 1677877071,
-            'duration': 150.0,
-            'upload_date': '20230303',
-            'thumbnail': r're:https://bibeltv\.imgix\.net/[\w-]+\.jpg',
-            'episode': 'Episode 1',
-            'episode_number': 1,
-            'view_count': int,
-            'like_count': int,
-        },
-        'params': {
-            'format': '6',
-        },
-    }]
-
-    def _real_extract(self, url):
-        crn_id = self._match_id(url)
-        video_data = traverse_obj(
-            self._search_nextjs_data(self._download_webpage(url, crn_id), crn_id),
-            ('props', 'pageProps', 'videoPageData', 'videos', 0, {dict}))
-        if not video_data:
-            raise ExtractorError('Missing video data.')
-
-        return self._extract_video_info(video_data)
-
-
-class BibelTVSeriesIE(BibelTVBaseIE):
-    IE_DESC = 'BibelTV series playlist'
-    _VALID_URL = r'https?://(?:www\.)?bibeltv\.de/mediathek/serien/(?P<id>\d+)[\w-]+'
-    IE_NAME = 'bibeltv:series'
-
-    _TESTS = [{
-        'url': 'https://www.bibeltv.de/mediathek/serien/333485-ein-wunder-fuer-jeden-tag',
-        'playlist_mincount': 400,
-        'info_dict': {
-            'id': '333485',
-            'title': 'Ein Wunder für jeden Tag',
-            'description': 'Tägliche Kurzandacht mit Déborah Rosenkranz.',
-        },
-    }]
-
-    def _real_extract(self, url):
-        crn_id = self._match_id(url)
-        webpage = self._download_webpage(url, crn_id)
-        nextjs_data = self._search_nextjs_data(webpage, crn_id)
-        series_data = traverse_obj(nextjs_data, ('props', 'pageProps', 'seriePageData', {dict}))
-        if not series_data:
-            raise ExtractorError('Missing series data.')
-
-        return self.playlist_result(
-            traverse_obj(series_data, ('videos', ..., {dict}, {self._extract_url_info})),
-            crn_id, series_data.get('title'), clean_html(series_data.get('description')))
-
-
-class BibelTVLiveIE(BibelTVBaseIE):
-    IE_DESC = 'BibelTV live program'
-    _VALID_URL = r'https?://(?:www\.)?bibeltv\.de/livestreams/(?P<id>[\w-]+)'
-    IE_NAME = 'bibeltv:live'
-
-    _TESTS = [{
-        'url': 'https://www.bibeltv.de/livestreams/bibeltv/',
-        'info_dict': {
-            'id': 'bibeltv',
-            'ext': 'mp4',
-            'title': 're:Bibel TV',
-            'live_status': 'is_live',
-            'thumbnail': 'https://streampreview.bibeltv.de/bibeltv.webp',
-        },
-        'params': {'skip_download': 'm3u8'},
-    }, {
-        'url': 'https://www.bibeltv.de/livestreams/impuls/',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        stream_id = self._match_id(url)
-        webpage = self._download_webpage(url, stream_id)
-        stream_data = self._search_json(
-            r'\\"video\\":', webpage, 'bibeltvData', stream_id,
-            transform_source=lambda jstring: js_to_json(jstring.replace('\\"', '"')))
-
-        formats, subtitles = self._extract_formats_and_subtitles(
-            traverse_obj(stream_data, ('src', ...)), stream_id, is_live=True)
-
-        return {
-            'id': stream_id,
-            'title': stream_data.get('title'),
-            'thumbnail': stream_data.get('poster'),
-            'is_live': True,
-            '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/bigflix.py

@@ -1,73 +0,0 @@
-import re
-
-from .common import InfoExtractor
-from ..compat import (
-    compat_b64decode,
-    compat_urllib_parse_unquote,
-)
-
-
-class BigflixIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?bigflix\.com/.+/(?P<id>[0-9]+)'
-    _TESTS = [{
-        # 2 formats
-        'url': 'http://www.bigflix.com/Tamil-movies/Drama-movies/Madarasapatinam/16070',
-        'info_dict': {
-            'id': '16070',
-            'ext': 'mp4',
-            'title': 'Madarasapatinam',
-            'description': 'md5:9f0470b26a4ba8e824c823b5d95c2f6b',
-            'formats': 'mincount:2',
-        },
-        'params': {
-            'skip_download': True,
-        }
-    }, {
-        # multiple formats
-        'url': 'http://www.bigflix.com/Malayalam-movies/Drama-movies/Indian-Rupee/15967',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        title = self._html_search_regex(
-            r'<div[^>]+class=["\']pagetitle["\'][^>]*>(.+?)</div>',
-            webpage, 'title')
-
-        def decode_url(quoted_b64_url):
-            return compat_b64decode(compat_urllib_parse_unquote(
-                quoted_b64_url)).decode('utf-8')
-
-        formats = []
-        for height, encoded_url in re.findall(
-                r'ContentURL_(\d{3,4})[pP][^=]+=([^&]+)', webpage):
-            video_url = decode_url(encoded_url)
-            f = {
-                'url': video_url,
-                'format_id': '%sp' % height,
-                'height': int(height),
-            }
-            if video_url.startswith('rtmp'):
-                f['ext'] = 'flv'
-            formats.append(f)
-
-        file_url = self._search_regex(
-            r'file=([^&]+)', webpage, 'video url', default=None)
-        if file_url:
-            video_url = decode_url(file_url)
-            if all(f['url'] != video_url for f in formats):
-                formats.append({
-                    'url': decode_url(file_url),
-                })
-
-        description = self._html_search_meta('description', webpage)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'formats': formats
-        }

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

@@ -1,57 +0,0 @@
-from .common import InfoExtractor
-from ..utils import ExtractorError, urlencode_postdata
-
-
-class BigoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?bigo\.tv/(?:[a-z]{2,}/)?(?P<id>[^/]+)'
-
-    _TESTS = [{
-        'url': 'https://www.bigo.tv/ja/221338632',
-        'info_dict': {
-            'id': '6576287577575737440',
-            'title': '土よ〜💁‍♂️ 休憩室/REST room',
-            'thumbnail': r're:https?://.+',
-            'uploader': '✨Shin💫',
-            'uploader_id': '221338632',
-            'is_live': True,
-        },
-        'skip': 'livestream',
-    }, {
-        'url': 'https://www.bigo.tv/th/Tarlerm1304',
-        'only_matching': True,
-    }, {
-        'url': 'https://bigo.tv/115976881',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        user_id = self._match_id(url)
-
-        info_raw = self._download_json(
-            'https://ta.bigo.tv/official_website/studio/getInternalStudioInfo',
-            user_id, data=urlencode_postdata({'siteId': user_id}),
-            headers={'Accept': 'application/json'})
-
-        if not isinstance(info_raw, dict):
-            raise ExtractorError('Received invalid JSON data')
-        if info_raw.get('code'):
-            raise ExtractorError(
-                'Bigo says: %s (code %s)' % (info_raw.get('msg'), info_raw.get('code')), expected=True)
-        info = info_raw.get('data') or {}
-
-        if not info.get('alive'):
-            raise ExtractorError('This user is offline.', expected=True)
-
-        formats, subs = self._extract_m3u8_formats_and_subtitles(
-            info.get('hls_src'), user_id, 'mp4', 'm3u8')
-
-        return {
-            'id': info.get('roomId') or user_id,
-            'title': info.get('roomTopic') or info.get('nick_name') or user_id,
-            'formats': formats,
-            'subtitles': subs,
-            'thumbnail': info.get('snapshot'),
-            'uploader': info.get('nick_name'),
-            'uploader_id': user_id,
-            'is_live': True,
-        }

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

@@ -1,63 +0,0 @@
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    traverse_obj,
-    unescapeHTML,
-)
-
-
-class BildIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?bild\.de/(?:[^/]+/)+(?P<display_id>[^/]+)-(?P<id>\d+)(?:,auto=true)?\.bild\.html'
-    IE_DESC = 'Bild.de'
-    _TESTS = [{
-        'note': 'static MP4 only',
-        'url': 'http://www.bild.de/video/clip/apple-ipad-air/das-koennen-die-neuen-ipads-38184146.bild.html',
-        'md5': 'dd495cbd99f2413502a1713a1156ac8a',
-        'info_dict': {
-            'id': '38184146',
-            'ext': 'mp4',
-            'title': 'Das können die  neuen iPads',
-            'description': 'md5:a4058c4fa2a804ab59c00d7244bbf62f',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'duration': 196,
-        }
-    }, {
-        'note': 'static MP4 and HLS',
-        'url': 'https://www.bild.de/video/clip/news-ausland/deftiger-abgang-vom-10m-turm-bademeister-sorgt-fuer-skandal-85158620.bild.html',
-        'md5': 'fb0ed4f09c495d4ba7ce2eee0bb90de1',
-        'info_dict': {
-            'id': '85158620',
-            'ext': 'mp4',
-            'title': 'Der Sprungturm-Skandal',
-            'description': 'md5:709b543c24dc31bbbffee73bccda34ad',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'duration': 69,
-        }
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        video_data = self._download_json(
-            url.split('.bild.html')[0] + ',view=json.bild.html', video_id)
-
-        formats = []
-        for src in traverse_obj(video_data, ('clipList', 0, 'srces', lambda _, v: v['src'])):
-            src_type = src.get('type')
-            if src_type == 'application/x-mpegURL':
-                formats.extend(
-                    self._extract_m3u8_formats(
-                        src['src'], video_id, 'mp4', m3u8_id='hls', fatal=False))
-            elif src_type == 'video/mp4':
-                formats.append({'url': src['src'], 'format_id': 'http-mp4'})
-            else:
-                self.report_warning(f'Skipping unsupported format type: "{src_type}"')
-
-        return {
-            'id': video_id,
-            'title': unescapeHTML(video_data['title']).strip(),
-            'description': unescapeHTML(video_data.get('description')),
-            'formats': formats,
-            'thumbnail': video_data.get('poster'),
-            'duration': int_or_none(video_data.get('durationSec')),
-        }