@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/aol.py

@@ -1,133 +0,0 @@
-import re
-
-from .yahoo import YahooIE
-from ..utils import (
-    ExtractorError,
-    int_or_none,
-    parse_qs,
-    url_or_none,
-)
-
-
-class AolIE(YahooIE):  # XXX: Do not subclass from concrete IE
-    _WORKING = False
-    IE_NAME = 'aol.com'
-    _VALID_URL = r'(?:aol-video:|https?://(?:www\.)?aol\.(?:com|ca|co\.uk|de|jp)/video/(?:[^/]+/)*)(?P<id>\d{9}|[0-9a-f]{24}|[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12})'
-
-    _TESTS = [{
-        # video with 5min ID
-        'url': 'https://www.aol.com/video/view/u-s--official-warns-of-largest-ever-irs-phone-scam/518167793/',
-        'md5': '18ef68f48740e86ae94b98da815eec42',
-        'info_dict': {
-            'id': '518167793',
-            'ext': 'mp4',
-            'title': 'U.S. Official Warns Of \'Largest Ever\' IRS Phone Scam',
-            'description': 'A major phone scam has cost thousands of taxpayers more than $1 million, with less than a month until income tax returns are due to the IRS.',
-            'timestamp': 1395405060,
-            'upload_date': '20140321',
-            'uploader': 'Newsy Studio',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        }
-    }, {
-        # video with vidible ID
-        'url': 'https://www.aol.com/video/view/netflix-is-raising-rates/5707d6b8e4b090497b04f706/',
-        'info_dict': {
-            'id': '5707d6b8e4b090497b04f706',
-            'ext': 'mp4',
-            'title': 'Netflix is Raising Rates',
-            'description': 'Netflix is rewarding millions of it’s long-standing members with an increase in cost. Veuer’s Carly Figueroa has more.',
-            'upload_date': '20160408',
-            'timestamp': 1460123280,
-            'uploader': 'Veuer',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        }
-    }, {
-        'url': 'https://www.aol.com/video/view/park-bench-season-2-trailer/559a1b9be4b0c3bfad3357a7/',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.aol.com/video/view/donald-trump-spokeswoman-tones-down-megyn-kelly-attacks/519442220/',
-        'only_matching': True,
-    }, {
-        'url': 'aol-video:5707d6b8e4b090497b04f706',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.aol.com/video/playlist/PL8245/5ca79d19d21f1a04035db606/',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.aol.ca/video/view/u-s-woman-s-family-arrested-for-murder-first-pinned-on-panhandler-police/5c7ccf45bc03931fa04b2fe1/',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.aol.co.uk/video/view/-one-dead-and-22-hurt-in-bus-crash-/5cb3a6f3d21f1a072b457347/',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.aol.de/video/view/eva-braun-privataufnahmen-von-hitlers-geliebter-werden-digitalisiert/5cb2d49de98ab54c113d3d5d/',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.aol.jp/video/playlist/5a28e936a1334d000137da0c/5a28f3151e642219fde19831/',
-        'only_matching': True,
-    }, {
-        # Yahoo video
-        'url': 'https://www.aol.com/video/play/991e6700-ac02-11ea-99ff-357400036f61/24bbc846-3e30-3c46-915e-fe8ccd7fcc46/',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        if '-' in video_id:
-            return self._extract_yahoo_video(video_id, 'us')
-
-        response = self._download_json(
-            'https://feedapi.b2c.on.aol.com/v1.0/app/videos/aolon/%s/details' % video_id,
-            video_id)['response']
-        if response['statusText'] != 'Ok':
-            raise ExtractorError('%s said: %s' % (self.IE_NAME, response['statusText']), expected=True)
-
-        video_data = response['data']
-        formats = []
-        m3u8_url = url_or_none(video_data.get('videoMasterPlaylist'))
-        if m3u8_url:
-            formats.extend(self._extract_m3u8_formats(
-                m3u8_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
-        for rendition in video_data.get('renditions', []):
-            video_url = url_or_none(rendition.get('url'))
-            if not video_url:
-                continue
-            ext = rendition.get('format')
-            if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    video_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
-            else:
-                f = {
-                    'url': video_url,
-                    'format_id': rendition.get('quality'),
-                }
-                mobj = re.search(r'(\d+)x(\d+)', video_url)
-                if mobj:
-                    f.update({
-                        'width': int(mobj.group(1)),
-                        'height': int(mobj.group(2)),
-                    })
-                else:
-                    qs = parse_qs(video_url)
-                    f.update({
-                        'width': int_or_none(qs.get('w', [None])[0]),
-                        'height': int_or_none(qs.get('h', [None])[0]),
-                    })
-                formats.append(f)
-
-        return {
-            'id': video_id,
-            'title': video_data['title'],
-            'duration': int_or_none(video_data.get('duration')),
-            'timestamp': int_or_none(video_data.get('publishDate')),
-            'view_count': int_or_none(video_data.get('views')),
-            'description': video_data.get('description'),
-            'uploader': video_data.get('videoOwner'),
-            'formats': formats,
-        }

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

@@ -1,82 +0,0 @@
-from .common import InfoExtractor
-from ..utils import (
-    determine_ext,
-    int_or_none,
-    url_or_none,
-)
-
-
-class APAIE(InfoExtractor):
-    _VALID_URL = r'(?P<base_url>https?://[^/]+\.apa\.at)/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
-    _EMBED_REGEX = [r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//[^/]+\.apa\.at/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}.*?)\1']
-    _TESTS = [{
-        'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
-        'md5': '2b12292faeb0a7d930c778c7a5b4759b',
-        'info_dict': {
-            'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
-            'ext': 'mp4',
-            'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
-            'thumbnail': r're:^https?://.*\.jpg$',
-        },
-    }, {
-        'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
-        'only_matching': True,
-    }, {
-        'url': 'http://uvp-rma.sf.apa.at/embed/70404cca-2f47-4855-bbb8-20b1fae58f76',
-        'only_matching': True,
-    }, {
-        'url': 'http://uvp-kleinezeitung.sf.apa.at/embed/f1c44979-dba2-4ebf-b021-e4cf2cac3c81',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        mobj = self._match_valid_url(url)
-        video_id, base_url = mobj.group('id', 'base_url')
-
-        webpage = self._download_webpage(
-            '%s/player/%s' % (base_url, video_id), video_id)
-
-        jwplatform_id = self._search_regex(
-            r'media[iI]d\s*:\s*["\'](?P<id>[a-zA-Z0-9]{8})', webpage,
-            'jwplatform id', default=None)
-
-        if jwplatform_id:
-            return self.url_result(
-                'jwplatform:' + jwplatform_id, ie='JWPlatform',
-                video_id=video_id)
-
-        def extract(field, name=None):
-            return self._search_regex(
-                r'\b%s["\']\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1' % field,
-                webpage, name or field, default=None, group='value')
-
-        title = extract('title') or video_id
-        description = extract('description')
-        thumbnail = extract('poster', 'thumbnail')
-
-        formats = []
-        for format_id in ('hls', 'progressive'):
-            source_url = url_or_none(extract(format_id))
-            if not source_url:
-                continue
-            ext = determine_ext(source_url)
-            if ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    source_url, video_id, 'mp4', entry_protocol='m3u8_native',
-                    m3u8_id='hls', fatal=False))
-            else:
-                height = int_or_none(self._search_regex(
-                    r'(\d+)\.mp4', source_url, 'height', default=None))
-                formats.append({
-                    'url': source_url,
-                    'format_id': format_id,
-                    'height': height,
-                })
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'formats': formats,
-        }

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

@@ -1,88 +0,0 @@
-from .common import InfoExtractor
-from ..utils import (
-    get_element_by_id,
-    int_or_none,
-    merge_dicts,
-    mimetype2ext,
-    url_or_none,
-)
-
-
-class AparatIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
-    _EMBED_REGEX = [r'<iframe .*?src="(?P<url>http://www\.aparat\.com/video/[^"]+)"']
-
-    _TESTS = [{
-        'url': 'http://www.aparat.com/v/wP8On',
-        'md5': '131aca2e14fe7c4dcb3c4877ba300c89',
-        'info_dict': {
-            'id': 'wP8On',
-            'ext': 'mp4',
-            'title': 'تیم گلکسی 11 - زومیت',
-            'description': 'md5:096bdabcdcc4569f2b8a5e903a3b3028',
-            'duration': 231,
-            'timestamp': 1387394859,
-            'upload_date': '20131218',
-            'view_count': int,
-        },
-    }, {
-        # multiple formats
-        'url': 'https://www.aparat.com/v/8dflw/',
-        'only_matching': True,
-    }]
-
-    def _parse_options(self, webpage, video_id, fatal=True):
-        return self._parse_json(self._search_regex(
-            r'options\s*=\s*({.+?})\s*;', webpage, 'options', default='{}'), video_id)
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        # If available, provides more metadata
-        webpage = self._download_webpage(url, video_id, fatal=False)
-        options = self._parse_options(webpage, video_id, fatal=False)
-
-        if not options:
-            webpage = self._download_webpage(
-                'http://www.aparat.com/video/video/embed/vt/frame/showvideo/yes/videohash/' + video_id,
-                video_id, 'Downloading embed webpage')
-            options = self._parse_options(webpage, video_id)
-
-        formats = []
-        for sources in (options.get('multiSRC') or []):
-            for item in sources:
-                if not isinstance(item, dict):
-                    continue
-                file_url = url_or_none(item.get('src'))
-                if not file_url:
-                    continue
-                item_type = item.get('type')
-                if item_type == 'application/vnd.apple.mpegurl':
-                    formats.extend(self._extract_m3u8_formats(
-                        file_url, video_id, 'mp4',
-                        entry_protocol='m3u8_native', m3u8_id='hls',
-                        fatal=False))
-                else:
-                    ext = mimetype2ext(item.get('type'))
-                    label = item.get('label')
-                    formats.append({
-                        'url': file_url,
-                        'ext': ext,
-                        'format_id': 'http-%s' % (label or ext),
-                        'height': int_or_none(self._search_regex(
-                            r'(\d+)[pP]', label or '', 'height',
-                            default=None)),
-                    })
-
-        info = self._search_json_ld(webpage, video_id, default={})
-
-        if not info.get('title'):
-            info['title'] = get_element_by_id('videoTitle', webpage) or \
-                self._html_search_meta(['og:title', 'twitter:title', 'DC.Title', 'title'], webpage, fatal=True)
-
-        return merge_dicts(info, {
-            'id': video_id,
-            'thumbnail': url_or_none(options.get('poster')),
-            'duration': int_or_none(options.get('duration')),
-            'formats': formats,
-        })

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

@@ -1,50 +0,0 @@
-from .common import InfoExtractor
-from ..utils import (
-    str_to_int,
-    ExtractorError
-)
-
-
-class AppleConnectIE(InfoExtractor):
-    _VALID_URL = r'https?://itunes\.apple\.com/\w{0,2}/?post/(?:id)?sa\.(?P<id>[\w-]+)'
-    _TESTS = [{
-        'url': 'https://itunes.apple.com/us/post/idsa.4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
-        'md5': 'c1d41f72c8bcaf222e089434619316e4',
-        'info_dict': {
-            'id': '4ab17a39-2720-11e5-96c5-a5b38f6c42d3',
-            'ext': 'm4v',
-            'title': 'Energy',
-            'uploader': 'Drake',
-            'thumbnail': r're:^https?://.*\.jpg$',
-            'upload_date': '20150710',
-            'timestamp': 1436545535,
-        },
-    }, {
-        'url': 'https://itunes.apple.com/us/post/sa.0fe0229f-2457-11e5-9f40-1bb645f2d5d9',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        try:
-            video_json = self._html_search_regex(
-                r'class="auc-video-data">(\{.*?\})', webpage, 'json')
-        except ExtractorError:
-            raise ExtractorError('This post doesn\'t contain a video', expected=True)
-
-        video_data = self._parse_json(video_json, video_id)
-        timestamp = str_to_int(self._html_search_regex(r'data-timestamp="(\d+)"', webpage, 'timestamp'))
-        like_count = str_to_int(self._html_search_regex(r'(\d+) Loves', webpage, 'like count', default=None))
-
-        return {
-            'id': video_id,
-            'url': video_data['sslSrc'],
-            'title': video_data['title'],
-            'description': video_data['description'],
-            'uploader': video_data['artistName'],
-            'thumbnail': video_data['artworkUrl'],
-            'timestamp': timestamp,
-            'like_count': like_count,
-        }

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

@@ -1,85 +0,0 @@
-from .common import InfoExtractor
-from ..utils import (
-    clean_html,
-    clean_podcast_url,
-    get_element_by_class,
-    int_or_none,
-    parse_iso8601,
-    try_get,
-)
-
-
-class ApplePodcastsIE(InfoExtractor):
-    _VALID_URL = r'https?://podcasts\.apple\.com/(?:[^/]+/)?podcast(?:/[^/]+){1,2}.*?\bi=(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'https://podcasts.apple.com/us/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
-        'md5': '41dc31cd650143e530d9423b6b5a344f',
-        'info_dict': {
-            'id': '1000482637777',
-            'ext': 'mp3',
-            'title': '207 - Whitney Webb Returns',
-            'description': 'md5:75ef4316031df7b41ced4e7b987f79c6',
-            'upload_date': '20200705',
-            'timestamp': 1593932400,
-            'duration': 6454,
-            'series': 'The Tim Dillon Show',
-            'thumbnail': 're:.+[.](png|jpe?g|webp)',
-        }
-    }, {
-        'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
-        'only_matching': True,
-    }, {
-        'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns?i=1000482637777',
-        'only_matching': True,
-    }, {
-        'url': 'https://podcasts.apple.com/podcast/id1135137367?i=1000482637777',
-        'only_matching': True,
-    }]
-
-    def _real_extract(self, url):
-        episode_id = self._match_id(url)
-        webpage = self._download_webpage(url, episode_id)
-        episode_data = {}
-        ember_data = {}
-        # new page type 2021-11
-        amp_data = self._parse_json(self._search_regex(
-            r'(?s)id="shoebox-media-api-cache-amp-podcasts"[^>]*>\s*({.+?})\s*<',
-            webpage, 'AMP data', default='{}'), episode_id, fatal=False) or {}
-        amp_data = try_get(amp_data,
-                           lambda a: self._parse_json(
-                               next(a[x] for x in iter(a) if episode_id in x),
-                               episode_id),
-                           dict) or {}
-        amp_data = amp_data.get('d') or []
-        episode_data = try_get(
-            amp_data,
-            lambda a: next(x for x in a
-                           if x['type'] == 'podcast-episodes' and x['id'] == episode_id),
-            dict)
-        if not episode_data:
-            # try pre 2021-11 page type: TODO: consider deleting if no longer used
-            ember_data = self._parse_json(self._search_regex(
-                r'(?s)id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
-                webpage, 'ember data'), episode_id) or {}
-            ember_data = ember_data.get(episode_id) or ember_data
-            episode_data = try_get(ember_data, lambda x: x['data'], dict)
-        episode = episode_data['attributes']
-        description = episode.get('description') or {}
-
-        series = None
-        for inc in (amp_data or ember_data.get('included') or []):
-            if inc.get('type') == 'media/podcast':
-                series = try_get(inc, lambda x: x['attributes']['name'])
-        series = series or clean_html(get_element_by_class('podcast-header__identity', webpage))
-
-        return {
-            'id': episode_id,
-            'title': episode.get('name'),
-            'url': clean_podcast_url(episode['assetUrl']),
-            'description': description.get('standard') or description.get('short'),
-            'timestamp': parse_iso8601(episode.get('releaseDateTime')),
-            'duration': int_or_none(episode.get('durationInMilliseconds'), 1000),
-            'series': series,
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'vcodec': 'none',
-        }