@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/dw.py

@@ -1,110 +0,0 @@
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    unified_strdate,
-    url_or_none,
-)
-from ..compat import compat_urlparse
-
-
-class DWIE(InfoExtractor):
-    _WORKING = False
-    _ENABLED = None  # XXX: pass through to GenericIE
-    IE_NAME = 'dw'
-    _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+(?:av|e)-(?P<id>\d+)'
-    _TESTS = [{
-        # video
-        'url': 'http://www.dw.com/en/intelligent-light/av-19112290',
-        'md5': 'fb9dfd9520811d3ece80f04befd73428',
-        'info_dict': {
-            'id': '19112290',
-            'ext': 'mp4',
-            'title': 'Intelligent light',
-            'description': 'md5:90e00d5881719f2a6a5827cb74985af1',
-            'upload_date': '20160605',
-        }
-    }, {
-        # audio
-        'url': 'http://www.dw.com/en/worldlink-my-business/av-19111941',
-        'md5': '2814c9a1321c3a51f8a7aeb067a360dd',
-        'info_dict': {
-            'id': '19111941',
-            'ext': 'mp3',
-            'title': 'WorldLink: My business',
-            'description': 'md5:bc9ca6e4e063361e21c920c53af12405',
-            'upload_date': '20160311',
-        }
-    }, {
-        # DW documentaries, only last for one or two weeks
-        'url': 'http://www.dw.com/en/documentaries-welcome-to-the-90s-2016-05-21/e-19220158-9798',
-        'md5': '56b6214ef463bfb9a3b71aeb886f3cf1',
-        'info_dict': {
-            'id': '19274438',
-            'ext': 'mp4',
-            'title': 'Welcome to the 90s – Hip Hop',
-            'description': 'Welcome to the 90s - The Golden Decade of Hip Hop',
-            'upload_date': '20160521',
-        },
-        'skip': 'Video removed',
-    }]
-
-    def _real_extract(self, url):
-        media_id = self._match_id(url)
-        webpage = self._download_webpage(url, media_id)
-        hidden_inputs = self._hidden_inputs(webpage)
-        title = hidden_inputs['media_title']
-        media_id = hidden_inputs.get('media_id') or media_id
-
-        direct_url = url_or_none(hidden_inputs.get('file_name'))
-        if direct_url:
-            formats = [{'url': hidden_inputs['file_name']}]
-        else:
-            formats = self._extract_smil_formats(
-                'http://www.dw.com/smil/v-%s' % media_id, media_id,
-                transform_source=lambda s: s.replace(
-                    'rtmp://tv-od.dw.de/flash/',
-                    'http://tv-download.dw.de/dwtv_video/flv/'))
-
-        upload_date = hidden_inputs.get('display_date')
-        if not upload_date:
-            upload_date = self._html_search_regex(
-                r'<span[^>]+class="date">([0-9.]+)\s*\|', webpage,
-                'upload date', default=None)
-            upload_date = unified_strdate(upload_date)
-
-        return {
-            'id': media_id,
-            'title': title,
-            'description': self._og_search_description(webpage),
-            'thumbnail': hidden_inputs.get('preview_image'),
-            'duration': int_or_none(hidden_inputs.get('file_duration')),
-            'upload_date': upload_date,
-            'formats': formats,
-        }
-
-
-class DWArticleIE(InfoExtractor):
-    _WORKING = False
-    _ENABLED = None  # XXX: pass through to GenericIE
-    IE_NAME = 'dw:article'
-    _VALID_URL = r'https?://(?:www\.)?dw\.com/(?:[^/]+/)+a-(?P<id>\d+)'
-    _TEST = {
-        'url': 'http://www.dw.com/en/no-hope-limited-options-for-refugees-in-idomeni/a-19111009',
-        'md5': '8ca657f9d068bbef74d6fc38b97fc869',
-        'info_dict': {
-            'id': '19105868',
-            'ext': 'mp4',
-            'title': 'The harsh life of refugees in Idomeni',
-            'description': 'md5:196015cc7e48ebf474db9399420043c7',
-            'upload_date': '20160310',
-        }
-    }
-
-    def _real_extract(self, url):
-        article_id = self._match_id(url)
-        webpage = self._download_webpage(url, article_id)
-        hidden_inputs = self._hidden_inputs(webpage)
-        media_id = hidden_inputs['media_id']
-        media_path = self._search_regex(r'href="([^"]+av-%s)"\s+class="overlayLink"' % media_id, webpage, 'media url')
-        media_url = compat_urlparse.urljoin(url, media_path)
-        return self.url_result(media_url, 'DW', media_id)

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

@@ -1,215 +0,0 @@
-import functools
-import re
-
-from .common import InfoExtractor
-from ..networking.exceptions import HTTPError
-from ..utils import (
-    ExtractorError,
-    int_or_none,
-    smuggle_url,
-    unsmuggle_url,
-    url_or_none,
-)
-
-
-class EaglePlatformIE(InfoExtractor):
-    _VALID_URL = r'''(?x)
-                    (?:
-                        eagleplatform:(?P<custom_host>[^/]+):|
-                        https?://(?P<host>.+?\.media\.eagleplatform\.com)/index/player\?.*\brecord_id=
-                    )
-                    (?P<id>\d+)
-                '''
-    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//.+?\.media\.eagleplatform\.com/index/player\?.+?)\1']
-    _TESTS = [{
-        # http://lenta.ru/news/2015/03/06/navalny/
-        'url': 'http://lentaru.media.eagleplatform.com/index/player?player=new&record_id=227304&player_template_id=5201',
-        # Not checking MD5 as sometimes the direct HTTP link results in 404 and HLS is used
-        'info_dict': {
-            'id': '227304',
-            'ext': 'mp4',
-            'title': 'Навальный вышел на свободу',
-            'description': 'md5:d97861ac9ae77377f3f20eaf9d04b4f5',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'duration': 87,
-            'view_count': int,
-            'age_limit': 0,
-        },
-    }, {
-        # http://muz-tv.ru/play/7129/
-        # http://media.clipyou.ru/index/player?record_id=12820&width=730&height=415&autoplay=true
-        'url': 'eagleplatform:media.clipyou.ru:12820',
-        'md5': '358597369cf8ba56675c1df15e7af624',
-        'info_dict': {
-            'id': '12820',
-            'ext': 'mp4',
-            'title': "'O Sole Mio",
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'duration': 216,
-            'view_count': int,
-        },
-        'skip': 'Georestricted',
-    }, {
-        # referrer protected video (https://tvrain.ru/lite/teleshow/kak_vse_nachinalos/namin-418921/)
-        'url': 'eagleplatform:tvrainru.media.eagleplatform.com:582306',
-        'only_matching': True,
-    }]
-
-    @classmethod
-    def _extract_embed_urls(cls, url, webpage):
-        add_referer = functools.partial(smuggle_url, data={'referrer': url})
-
-        res = tuple(super()._extract_embed_urls(url, webpage))
-        if res:
-            return map(add_referer, res)
-
-        PLAYER_JS_RE = r'''
-                        <script[^>]+
-                            src=(?P<qjs>["\'])(?:https?:)?//(?P<host>(?:(?!(?P=qjs)).)+\.media\.eagleplatform\.com)/player/player\.js(?P=qjs)
-                        .+?
-                    '''
-        # "Basic usage" embedding (see http://dultonmedia.github.io/eplayer/)
-        mobj = re.search(
-            r'''(?xs)
-                    %s
-                    <div[^>]+
-                        class=(?P<qclass>["\'])eagleplayer(?P=qclass)[^>]+
-                        data-id=["\'](?P<id>\d+)
-            ''' % PLAYER_JS_RE, webpage)
-        if mobj is not None:
-            return [add_referer('eagleplatform:%(host)s:%(id)s' % mobj.groupdict())]
-        # Generalization of "Javascript code usage", "Combined usage" and
-        # "Usage without attaching to DOM" embeddings (see
-        # http://dultonmedia.github.io/eplayer/)
-        mobj = re.search(
-            r'''(?xs)
-                    %s
-                    <script>
-                    .+?
-                    new\s+EaglePlayer\(
-                        (?:[^,]+\s*,\s*)?
-                        {
-                            .+?
-                            \bid\s*:\s*["\']?(?P<id>\d+)
-                            .+?
-                        }
-                    \s*\)
-                    .+?
-                    </script>
-            ''' % PLAYER_JS_RE, webpage)
-        if mobj is not None:
-            return [add_referer('eagleplatform:%(host)s:%(id)s' % mobj.groupdict())]
-
-    @staticmethod
-    def _handle_error(response):
-        status = int_or_none(response.get('status', 200))
-        if status != 200:
-            raise ExtractorError(' '.join(response['errors']), expected=True)
-
-    def _download_json(self, url_or_request, video_id, *args, **kwargs):
-        try:
-            response = super(EaglePlatformIE, self)._download_json(
-                url_or_request, video_id, *args, **kwargs)
-        except ExtractorError as ee:
-            if isinstance(ee.cause, HTTPError):
-                response = self._parse_json(ee.cause.response.read().decode('utf-8'), video_id)
-                self._handle_error(response)
-            raise
-        return response
-
-    def _get_video_url(self, url_or_request, video_id, note='Downloading JSON metadata'):
-        return self._download_json(url_or_request, video_id, note)['data'][0]
-
-    def _real_extract(self, url):
-        url, smuggled_data = unsmuggle_url(url, {})
-
-        mobj = self._match_valid_url(url)
-        host, video_id = mobj.group('custom_host') or mobj.group('host'), mobj.group('id')
-
-        headers = {}
-        query = {
-            'id': video_id,
-        }
-
-        referrer = smuggled_data.get('referrer')
-        if referrer:
-            headers['Referer'] = referrer
-            query['referrer'] = referrer
-
-        player_data = self._download_json(
-            'http://%s/api/player_data' % host, video_id,
-            headers=headers, query=query)
-
-        media = player_data['data']['playlist']['viewports'][0]['medialist'][0]
-
-        title = media['title']
-        description = media.get('description')
-        thumbnail = self._proto_relative_url(media.get('snapshot'), 'http:')
-        duration = int_or_none(media.get('duration'))
-        view_count = int_or_none(media.get('views'))
-
-        age_restriction = media.get('age_restriction')
-        age_limit = None
-        if age_restriction:
-            age_limit = 0 if age_restriction == 'allow_all' else 18
-
-        secure_m3u8 = self._proto_relative_url(media['sources']['secure_m3u8']['auto'], 'http:')
-
-        formats = []
-
-        m3u8_url = self._get_video_url(secure_m3u8, video_id, 'Downloading m3u8 JSON')
-        m3u8_formats = self._extract_m3u8_formats(
-            m3u8_url, video_id, 'mp4', entry_protocol='m3u8_native',
-            m3u8_id='hls', fatal=False)
-        formats.extend(m3u8_formats)
-
-        m3u8_formats_dict = {}
-        for f in m3u8_formats:
-            if f.get('height') is not None:
-                m3u8_formats_dict[f['height']] = f
-
-        mp4_data = self._download_json(
-            # Secure mp4 URL is constructed according to Player.prototype.mp4 from
-            # http://lentaru.media.eagleplatform.com/player/player.js
-            re.sub(r'm3u8|hlsvod|hls|f4m', 'mp4s', secure_m3u8),
-            video_id, 'Downloading mp4 JSON', fatal=False)
-        if mp4_data:
-            for format_id, format_url in mp4_data.get('data', {}).items():
-                if not url_or_none(format_url):
-                    continue
-                height = int_or_none(format_id)
-                if height is not None and m3u8_formats_dict.get(height):
-                    f = m3u8_formats_dict[height].copy()
-                    f.update({
-                        'format_id': f['format_id'].replace('hls', 'http'),
-                        'protocol': 'http',
-                    })
-                else:
-                    f = {
-                        'format_id': 'http-%s' % format_id,
-                        'height': int_or_none(format_id),
-                    }
-                f['url'] = format_url
-                formats.append(f)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'duration': duration,
-            'view_count': view_count,
-            'age_limit': age_limit,
-            'formats': formats,
-        }
-
-
-class ClipYouEmbedIE(InfoExtractor):
-    _VALID_URL = False
-
-    @classmethod
-    def _extract_embed_urls(cls, url, webpage):
-        mobj = re.search(
-            r'<iframe[^>]+src="https?://(?P<host>media\.clipyou\.ru)/index/player\?.*\brecord_id=(?P<id>\d+).*"', webpage)
-        if mobj is not None:
-            yield smuggle_url('eagleplatform:%(host)s:%(id)s' % mobj.groupdict(), {'referrer': url})

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

@@ -1,31 +0,0 @@
-from .common import InfoExtractor
-
-
-class EbaumsWorldIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ebaumsworld\.com/videos/[^/]+/(?P<id>\d+)'
-
-    _TEST = {
-        'url': 'http://www.ebaumsworld.com/videos/a-giant-python-opens-the-door/83367677/',
-        'info_dict': {
-            'id': '83367677',
-            'ext': 'mp4',
-            'title': 'A Giant Python Opens The Door',
-            'description': 'This is how nightmares start...',
-            'uploader': 'jihadpizza',
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        config = self._download_xml(
-            'http://www.ebaumsworld.com/video/player/%s' % video_id, video_id)
-        video_url = config.find('file').text
-
-        return {
-            'id': video_id,
-            'title': config.find('title').text,
-            'url': video_url,
-            'description': config.find('description').text,
-            'thumbnail': config.find('image').text,
-            'uploader': config.find('username').text,
-        }

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

@@ -1,36 +0,0 @@
-from .common import InfoExtractor
-from ..utils import remove_end
-
-
-class EbayIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?ebay\.com/itm/(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://www.ebay.com/itm/194509326719',
-        'info_dict': {
-            'id': '194509326719',
-            'ext': 'mp4',
-            'title': 'WiFi internal antenna adhesive for wifi 2.4GHz wifi 5 wifi 6 wifi 6E full bands',
-        },
-        'params': {'skip_download': 'm3u8'}
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        video_json = self._search_json(r'"video":', webpage, 'video json', video_id)
-
-        formats = []
-        for key, url in video_json['playlistMap'].items():
-            if key == 'HLS':
-                formats.extend(self._extract_m3u8_formats(url, video_id, fatal=False))
-            elif key == 'DASH':
-                formats.extend(self._extract_mpd_formats(url, video_id, fatal=False))
-            else:
-                self.report_warning(f'Unsupported format {key}', video_id)
-
-        return {
-            'id': video_id,
-            'title': remove_end(self._html_extract_title(webpage), ' | eBay'),
-            'formats': formats
-        }

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

@@ -1,134 +0,0 @@
-from .common import InfoExtractor
-from ..compat import compat_str
-from ..utils import (
-    determine_ext,
-    int_or_none,
-    try_get,
-    unified_timestamp,
-    url_or_none,
-)
-
-
-class EggheadBaseIE(InfoExtractor):
-    def _call_api(self, path, video_id, resource, fatal=True):
-        return self._download_json(
-            'https://app.egghead.io/api/v1/' + path,
-            video_id, 'Downloading %s JSON' % resource, fatal=fatal)
-
-
-class EggheadCourseIE(EggheadBaseIE):
-    IE_DESC = 'egghead.io course'
-    IE_NAME = 'egghead:course'
-    _VALID_URL = r'https?://(?:app\.)?egghead\.io/(?:course|playlist)s/(?P<id>[^/?#&]+)'
-    _TESTS = [{
-        'url': 'https://egghead.io/courses/professor-frisby-introduces-composable-functional-javascript',
-        'playlist_count': 29,
-        'info_dict': {
-            'id': '432655',
-            'title': 'Professor Frisby Introduces Composable Functional JavaScript',
-            'description': 're:(?s)^This course teaches the ubiquitous.*You\'ll start composing functionality before you know it.$',
-        },
-    }, {
-        'url': 'https://app.egghead.io/playlists/professor-frisby-introduces-composable-functional-javascript',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        playlist_id = self._match_id(url)
-        series_path = 'series/' + playlist_id
-        lessons = self._call_api(
-            series_path + '/lessons', playlist_id, 'course lessons')
-
-        entries = []
-        for lesson in lessons:
-            lesson_url = url_or_none(lesson.get('http_url'))
-            if not lesson_url:
-                continue
-            lesson_id = lesson.get('id')
-            if lesson_id:
-                lesson_id = compat_str(lesson_id)
-            entries.append(self.url_result(
-                lesson_url, ie=EggheadLessonIE.ie_key(), video_id=lesson_id))
-
-        course = self._call_api(
-            series_path, playlist_id, 'course', False) or {}
-
-        playlist_id = course.get('id')
-        if playlist_id:
-            playlist_id = compat_str(playlist_id)
-
-        return self.playlist_result(
-            entries, playlist_id, course.get('title'),
-            course.get('description'))
-
-
-class EggheadLessonIE(EggheadBaseIE):
-    IE_DESC = 'egghead.io lesson'
-    IE_NAME = 'egghead:lesson'
-    _VALID_URL = r'https?://(?:app\.)?egghead\.io/(?:api/v1/)?lessons/(?P<id>[^/?#&]+)'
-    _TESTS = [{
-        'url': 'https://egghead.io/lessons/javascript-linear-data-flow-with-container-style-types-box',
-        'info_dict': {
-            'id': '1196',
-            'display_id': 'javascript-linear-data-flow-with-container-style-types-box',
-            'ext': 'mp4',
-            'title': 'Create linear data flow with container style types (Box)',
-            'description': 'md5:9aa2cdb6f9878ed4c39ec09e85a8150e',
-            'thumbnail': r're:^https?:.*\.jpg$',
-            'timestamp': 1481296768,
-            'upload_date': '20161209',
-            'duration': 304,
-            'view_count': 0,
-            'tags': 'count:2',
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        'url': 'https://egghead.io/api/v1/lessons/react-add-redux-to-a-react-application',
-        'only_matching': True,
-    }, {
-        'url': 'https://app.egghead.io/lessons/javascript-linear-data-flow-with-container-style-types-box',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-
-        lesson = self._call_api(
-            'lessons/' + display_id, display_id, 'lesson')
-
-        lesson_id = compat_str(lesson['id'])
-        title = lesson['title']
-
-        formats = []
-        for _, format_url in lesson['media_urls'].items():
-            format_url = url_or_none(format_url)
-            if not format_url:
-                continue
-            ext = determine_ext(format_url)
-            if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    format_url, lesson_id, 'mp4', m3u8_id='hls', fatal=False))
-            elif ext == 'mpd':
-                formats.extend(self._extract_mpd_formats(
-                    format_url, lesson_id, mpd_id='dash', fatal=False))
-            else:
-                formats.append({
-                    'url': format_url,
-                })
-
-        return {
-            'id': lesson_id,
-            'display_id': display_id,
-            'title': title,
-            'description': lesson.get('summary'),
-            'thumbnail': lesson.get('thumb_nail'),
-            'timestamp': unified_timestamp(lesson.get('published_at')),
-            'duration': int_or_none(lesson.get('duration')),
-            'view_count': int_or_none(lesson.get('plays_count')),
-            'tags': try_get(lesson, lambda x: x['tag_list'], list),
-            'series': try_get(
-                lesson, lambda x: x['series']['title'], compat_str),
-            'formats': formats,
-        }