@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/islamchannel.py

@@ -0,0 +1,81 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import traverse_obj, urljoin
+
+
+class IslamChannelIE(InfoExtractor):
+    _VALID_URL = r'https?://watch\.islamchannel\.tv/watch/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://watch.islamchannel.tv/watch/38604310',
+        'info_dict': {
+            'id': '38604310',
+            'title': 'Omar - Young Omar',
+            'description': 'md5:5cc7ddecef064ea7afe52eb5e0e33b55',
+            'thumbnail': r're:https?://.+',
+            'ext': 'mp4',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        thumbnail = self._search_regex(
+            r'data-poster="([^"]+)"', webpage, 'data poster', fatal=False) or \
+            self._html_search_meta(('og:image', 'twitter:image'), webpage)
+
+        headers = {
+            'Token': self._search_regex(r'data-token="([^"]+)"', webpage, 'data token'),
+            'Token-Expiry': self._search_regex(r'data-expiry="([^"]+)"', webpage, 'data expiry'),
+            'Uvid': video_id,
+        }
+        show_stream = self._download_json(
+            f'https://v2-streams-elb.simplestreamcdn.com/api/show/stream/{video_id}', video_id,
+            query={
+                'key': self._search_regex(r'data-key="([^"]+)"', webpage, 'data key'),
+                'platform': 'chrome',
+            }, headers=headers)
+        # TODO: show_stream['stream'] and show_stream['drm'] may contain something interesting
+        streams = self._download_json(
+            traverse_obj(show_stream, ('response', 'tokenization', 'url')), video_id,
+            headers=headers)
+        formats, subs = self._extract_m3u8_formats_and_subtitles(traverse_obj(streams, ('Streams', 'Adaptive')), video_id, 'mp4')
+
+        return {
+            'id': video_id,
+            'title': self._html_search_meta(('og:title', 'twitter:title'), webpage),
+            'description': self._html_search_meta(('og:description', 'twitter:description', 'description'), webpage),
+            'formats': formats,
+            'subtitles': subs,
+            'thumbnails': [{
+                'id': 'unscaled',
+                'url': thumbnail.split('?')[0],
+                'ext': 'jpg',
+                'preference': 2,
+            }, {
+                'id': 'orig',
+                'url': thumbnail,
+                'ext': 'jpg',
+                'preference': 1,
+            }] if thumbnail else None,
+        }
+
+
+class IslamChannelSeriesIE(InfoExtractor):
+    _VALID_URL = r'https?://watch\.islamchannel\.tv/series/(?P<id>[a-f\d-]+)'
+    _TESTS = [{
+        'url': 'https://watch.islamchannel.tv/series/a6cccef3-3ef1-11eb-bc19-06b69c2357cd',
+        'info_dict': {
+            'id': 'a6cccef3-3ef1-11eb-bc19-06b69c2357cd',
+        },
+        'playlist_mincount': 31,
+    }]
+
+    def _real_extract(self, url):
+        pl_id = self._match_id(url)
+        webpage = self._download_webpage(url, pl_id)
+
+        return self.playlist_from_matches(
+            re.finditer(r'<a\s+href="(/watch/\d+)"[^>]+?data-video-type="show">', webpage),
+            pl_id, getter=lambda x: urljoin(url, x.group(1)), ie=IslamChannelIE)

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

@@ -0,0 +1,50 @@
+from .common import InfoExtractor
+from ..utils import ExtractorError, traverse_obj
+
+
+class IsraelNationalNewsIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?israelnationalnews\.com/news/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://www.israelnationalnews.com/news/354520',
+        'info_dict': {
+            'id': '354520'
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'jA84wQhVvg8',
+                'title': 'Even CNN Host Is Shocked by How Bad Biden\'s Approval Ratings Have Gotten | DM CLIPS | Rubin Report',
+                'ext': 'mp4',
+                'description': 'md5:b7325a3d00c7596337dc3ae37e32d35c',
+                'channel': 'The Rubin Report',
+                'channel_follower_count': int,
+                'comment_count': int,
+                'categories': ['News & Politics'],
+                'like_count': int,
+                'uploader_url': 'http://www.youtube.com/user/RubinReport',
+                'uploader_id': 'RubinReport',
+                'availability': 'public',
+                'view_count': int,
+                'duration': 240,
+                'thumbnail': 'https://i.ytimg.com/vi_webp/jA84wQhVvg8/maxresdefault.webp',
+                'live_status': 'not_live',
+                'playable_in_embed': True,
+                'age_limit': 0,
+                'tags': 'count:29',
+                'channel_id': 'UCJdKr0Bgd_5saZYqLCa9mng',
+                'channel_url': 'https://www.youtube.com/channel/UCJdKr0Bgd_5saZYqLCa9mng',
+                'upload_date': '20220606',
+                'uploader': 'The Rubin Report',
+            }
+        }]
+    }]
+
+    def _real_extract(self, url):
+        news_article_id = self._match_id(url)
+        article_json = self._download_json(
+            f'https://www.israelnationalnews.com/Generic/NewAPI/Item?type=0&Item={news_article_id}', news_article_id)
+
+        urls = traverse_obj(article_json, ('Content2', ..., 'content', ..., 'attrs', 'src'))
+        if not urls:
+            raise ExtractorError('This article does not have any videos', expected=True)
+
+        return self.playlist_from_matches(urls, news_article_id, ie='Youtube')

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

@@ -0,0 +1,139 @@
+import re
+
+from .common import InfoExtractor
+
+from ..utils import (
+    int_or_none,
+    str_or_none,
+    traverse_obj,
+    urljoin
+)
+
+
+class ITProTVBaseIE(InfoExtractor):
+    _ENDPOINTS = {
+        'course': 'course?url={}&brand=00002560-0000-3fa9-0000-1d61000035f3',
+        'episode': 'brand/00002560-0000-3fa9-0000-1d61000035f3/episode?url={}'
+    }
+
+    def _call_api(self, ep, item_id, webpage):
+        return self._download_json(
+            f'https://api.itpro.tv/api/urza/v3/consumer-web/{self._ENDPOINTS[ep].format(item_id)}',
+            item_id, note=f'Fetching {ep} data API',
+            headers={'Authorization': f'Bearer {self._fetch_jwt(webpage)}'})[ep]
+
+    def _fetch_jwt(self, webpage):
+        return self._search_regex(r'{"passedToken":"([\w-]+\.[\w-]+\.[\w-]+)",', webpage, 'jwt')
+
+    def _check_if_logged_in(self, webpage):
+        if re.match(r'{\s*member\s*:\s*null', webpage):
+            self.raise_login_required()
+
+
+class ITProTVIE(ITProTVBaseIE):
+    _VALID_URL = r'https?://app\.itpro\.tv/course/(?P<course>[\w-]+)/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://app.itpro.tv/course/guided-tour/introductionitprotv',
+        'md5': 'bca4a28c2667fd1a63052e71a94bb88c',
+        'info_dict': {
+            'id': 'introductionitprotv',
+            'ext': 'mp4',
+            'title': 'An Introduction to ITProTV 101',
+            'thumbnail': 'https://itprotv-image-bucket.s3.amazonaws.com/getting-started/itprotv-101-introduction-PGM.11_39_56_02.Still001.png',
+            'description': 'md5:b175c2c3061ce35a4dd33865b2c1da4e',
+            'duration': 269,
+            'series': 'ITProTV 101',
+            'series_id': 'guided-tour',
+            'availability': 'needs_auth',
+            'chapter': 'ITProTV 101',
+            'chapter_number': 1,
+            'chapter_id': '5dbb3de426b46c0010b5d1b6'
+        },
+    },
+        {
+        'url': 'https://app.itpro.tv/course/beyond-tech/job-interview-tips',
+        'md5': '101a299b98c47ccf4c67f9f0951defa8',
+        'info_dict': {
+            'id': 'job-interview-tips',
+            'ext': 'mp4',
+            'title': 'Job Interview Tips',
+            'thumbnail': 'https://s3.amazonaws.com:443/production-itprotv-thumbnails/2f370bf5-294d-4bbe-ab80-c0b5781630ea.png',
+            'description': 'md5:30d8ba483febdf89ec85623aad3c3cb6',
+            'duration': 267,
+            'series': 'Beyond Tech',
+            'series_id': 'beyond-tech',
+            'availability': 'needs_auth',
+            'chapter': 'Job Development',
+            'chapter_number': 2,
+            'chapter_id': '5f7c78d424330c000edf04d9'
+        },
+    }]
+
+    def _real_extract(self, url):
+        episode_id, course_name = self._match_valid_url(url).group('id', 'course')
+        webpage = self._download_webpage(url, episode_id)
+        self._check_if_logged_in(webpage)
+        course = self._call_api('course', course_name, webpage)
+        episode = self._call_api('episode', episode_id, webpage)
+
+        chapter_number, chapter = next((
+            (i, topic) for i, topic in enumerate(course.get('topics') or [], 1)
+            if traverse_obj(topic, 'id') == episode.get('topic')), {})
+
+        return {
+            'id': episode_id,
+            'title': episode.get('title'),
+            'description': episode.get('description'),
+            'thumbnail': episode.get('thumbnail'),
+            'formats': [
+                {'url': episode[f'jwVideo{h}Embed'], 'height': h}
+                for h in (320, 480, 720, 1080) if episode.get(f'jwVideo{h}Embed')
+            ],
+            'duration': int_or_none(episode.get('length')),
+            'series': course.get('name'),
+            'series_id': course.get('url'),
+            'chapter': str_or_none(chapter.get('title')),
+            'chapter_number': chapter_number,
+            'chapter_id': str_or_none(chapter.get('id')),
+            'subtitles': {
+                'en': [{'ext': 'vtt', 'data': episode['enCaptionData']}]
+            } if episode.get('enCaptionData') else None,
+        }
+
+
+class ITProTVCourseIE(ITProTVBaseIE):
+    _VALID_URL = r'https?://app\.itpro\.tv/course/(?P<id>[\w-]+)/?(?:$|[#?])'
+    _TESTS = [
+        {
+            'url': 'https://app.itpro.tv/course/guided-tour',
+            'info_dict': {
+                'id': 'guided-tour',
+                'description': 'md5:b175c2c3061ce35a4dd33865b2c1da4e',
+                'title': 'ITProTV 101',
+            },
+            'playlist_count': 6
+        },
+        {
+            'url': 'https://app.itpro.tv/course/beyond-tech',
+            'info_dict': {
+                'id': 'beyond-tech',
+                'description': 'md5:44cd99855e7f81a15ce1269bd0621fed',
+                'title': 'Beyond Tech'
+            },
+            'playlist_count': 15
+        },
+    ]
+
+    def _real_extract(self, url):
+        course_id = self._match_id(url)
+        webpage = self._download_webpage(url, course_id)
+        self._check_if_logged_in(webpage)
+        course = self._call_api('course', course_id, webpage)
+
+        entries = [self.url_result(
+            urljoin(url, f'{course_id}/{episode["url"]}'), ITProTVIE,
+            episode['url'], episode.get('title'), url_transparent=True)
+            for episode in course['episodes']]
+
+        return self.playlist_result(
+            entries, course_id, course.get('name'), course.get('description'))

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

@@ -0,0 +1,266 @@
+import json
+
+from .common import InfoExtractor
+from .brightcove import BrightcoveNewIE
+
+from ..compat import compat_str
+from ..utils import (
+    base_url,
+    clean_html,
+    determine_ext,
+    extract_attributes,
+    ExtractorError,
+    get_element_by_class,
+    JSON_LD_RE,
+    merge_dicts,
+    parse_duration,
+    smuggle_url,
+    try_get,
+    url_or_none,
+    url_basename,
+    urljoin,
+)
+
+
+class ITVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?itv\.com/hub/[^/]+/(?P<id>[0-9a-zA-Z]+)'
+    _GEO_COUNTRIES = ['GB']
+    _TESTS = [{
+        'url': 'https://www.itv.com/hub/plebs/2a1873a0002',
+        'info_dict': {
+            'id': '2a1873a0002',
+            'ext': 'mp4',
+            'title': 'Plebs - The Orgy',
+            'description': 'md5:4d7159af53ebd5b36e8b3ec82a41fdb4',
+            'series': 'Plebs',
+            'season_number': 1,
+            'episode_number': 1,
+            'thumbnail': r're:https?://hubimages\.itv\.com/episode/2_1873_0002'
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.itv.com/hub/the-jonathan-ross-show/2a1166a0209',
+        'info_dict': {
+            'id': '2a1166a0209',
+            'ext': 'mp4',
+            'title': 'The Jonathan Ross Show - Series 17 - Episode 8',
+            'description': 'md5:3023dcdd375db1bc9967186cdb3f1399',
+            'series': 'The Jonathan Ross Show',
+            'episode_number': 8,
+            'season_number': 17,
+            'thumbnail': r're:https?://hubimages\.itv\.com/episode/2_1873_0002'
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # unavailable via data-playlist-url
+        'url': 'https://www.itv.com/hub/through-the-keyhole/2a2271a0033',
+        'only_matching': True,
+    }, {
+        # InvalidVodcrid
+        'url': 'https://www.itv.com/hub/james-martins-saturday-morning/2a5159a0034',
+        'only_matching': True,
+    }, {
+        # ContentUnavailable
+        'url': 'https://www.itv.com/hub/whos-doing-the-dishes/2a2898a0024',
+        'only_matching': True,
+    }]
+
+    def _generate_api_headers(self, hmac):
+        return merge_dicts({
+            'Accept': 'application/vnd.itv.vod.playlist.v2+json',
+            'Content-Type': 'application/json',
+            'hmac': hmac.upper(),
+        }, self.geo_verification_headers())
+
+    def _call_api(self, video_id, playlist_url, headers, platform_tag, featureset, fatal=True):
+        return self._download_json(
+            playlist_url, video_id, data=json.dumps({
+                'user': {
+                    'itvUserId': '',
+                    'entitlements': [],
+                    'token': ''
+                },
+                'device': {
+                    'manufacturer': 'Safari',
+                    'model': '5',
+                    'os': {
+                        'name': 'Windows NT',
+                        'version': '6.1',
+                        'type': 'desktop'
+                    }
+                },
+                'client': {
+                    'version': '4.1',
+                    'id': 'browser'
+                },
+                'variantAvailability': {
+                    'featureset': {
+                        'min': featureset,
+                        'max': featureset
+                    },
+                    'platformTag': platform_tag
+                }
+            }).encode(), headers=headers, fatal=fatal)
+
+    def _get_subtitles(self, video_id, variants, ios_playlist_url, headers, *args, **kwargs):
+        subtitles = {}
+        # Prefer last matching featureset
+        # See: https://github.com/yt-dlp/yt-dlp/issues/986
+        platform_tag_subs, featureset_subs = next(
+            ((platform_tag, featureset)
+             for platform_tag, featuresets in reversed(list(variants.items())) for featureset in featuresets
+             if try_get(featureset, lambda x: x[2]) == 'outband-webvtt'),
+            (None, None))
+
+        if platform_tag_subs and featureset_subs:
+            subs_playlist = self._call_api(
+                video_id, ios_playlist_url, headers, platform_tag_subs, featureset_subs, fatal=False)
+            subs = try_get(subs_playlist, lambda x: x['Playlist']['Video']['Subtitles'], list) or []
+            for sub in subs:
+                if not isinstance(sub, dict):
+                    continue
+                href = url_or_none(sub.get('Href'))
+                if not href:
+                    continue
+                subtitles.setdefault('en', []).append({'url': href})
+        return subtitles
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        params = extract_attributes(self._search_regex(
+            r'(?s)(<[^>]+id="video"[^>]*>)', webpage, 'params'))
+        variants = self._parse_json(
+            try_get(params, lambda x: x['data-video-variants'], compat_str) or '{}',
+            video_id, fatal=False)
+        # Prefer last matching featureset
+        # See: https://github.com/yt-dlp/yt-dlp/issues/986
+        platform_tag_video, featureset_video = next(
+            ((platform_tag, featureset)
+             for platform_tag, featuresets in reversed(list(variants.items())) for featureset in featuresets
+             if set(try_get(featureset, lambda x: x[:2]) or []) == {'aes', 'hls'}),
+            (None, None))
+        if not platform_tag_video or not featureset_video:
+            raise ExtractorError('No downloads available', expected=True, video_id=video_id)
+
+        ios_playlist_url = params.get('data-video-playlist') or params['data-video-id']
+        headers = self._generate_api_headers(params['data-video-hmac'])
+        ios_playlist = self._call_api(
+            video_id, ios_playlist_url, headers, platform_tag_video, featureset_video)
+
+        video_data = try_get(ios_playlist, lambda x: x['Playlist']['Video'], dict) or {}
+        ios_base_url = video_data.get('Base')
+        formats = []
+        for media_file in (video_data.get('MediaFiles') or []):
+            href = media_file.get('Href')
+            if not href:
+                continue
+            if ios_base_url:
+                href = ios_base_url + href
+            ext = determine_ext(href)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    href, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            else:
+                formats.append({
+                    'url': href,
+                })
+        info = self._search_json_ld(webpage, video_id, default={})
+        if not info:
+            json_ld = self._parse_json(self._search_regex(
+                JSON_LD_RE, webpage, 'JSON-LD', '{}',
+                group='json_ld'), video_id, fatal=False)
+            if json_ld and json_ld.get('@type') == 'BreadcrumbList':
+                for ile in (json_ld.get('itemListElement:') or []):
+                    item = ile.get('item:') or {}
+                    if item.get('@type') == 'TVEpisode':
+                        item['@context'] = 'http://schema.org'
+                        info = self._json_ld(item, video_id, fatal=False) or {}
+                        break
+
+        thumbnails = []
+        thumbnail_url = try_get(params, lambda x: x['data-video-posterframe'], compat_str)
+        if thumbnail_url:
+            thumbnails.extend([{
+                'url': thumbnail_url.format(width=1920, height=1080, quality=100, blur=0, bg='false'),
+                'width': 1920,
+                'height': 1080,
+            }, {
+                'url': urljoin(base_url(thumbnail_url), url_basename(thumbnail_url)),
+                'preference': -2
+            }])
+
+        thumbnail_url = self._html_search_meta(['og:image', 'twitter:image'], webpage, default=None)
+        if thumbnail_url:
+            thumbnails.append({
+                'url': thumbnail_url,
+            })
+        self._remove_duplicate_formats(thumbnails)
+
+        return merge_dicts({
+            'id': video_id,
+            'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
+            'formats': formats,
+            'subtitles': self.extract_subtitles(video_id, variants, ios_playlist_url, headers),
+            'duration': parse_duration(video_data.get('Duration')),
+            'description': clean_html(get_element_by_class('episode-info__synopsis', webpage)),
+            'thumbnails': thumbnails
+        }, info)
+
+
+class ITVBTCCIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?itv\.com/(?:news|btcc)/(?:[^/]+/)*(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.itv.com/btcc/articles/btcc-2019-brands-hatch-gp-race-action',
+        'info_dict': {
+            'id': 'btcc-2019-brands-hatch-gp-race-action',
+            'title': 'BTCC 2019: Brands Hatch GP race action',
+        },
+        'playlist_count': 12,
+    }, {
+        'url': 'https://www.itv.com/news/2021-10-27/i-have-to-protect-the-country-says-rishi-sunak-as-uk-faces-interest-rate-hike',
+        'info_dict': {
+            'id': 'i-have-to-protect-the-country-says-rishi-sunak-as-uk-faces-interest-rate-hike',
+            'title': 'md5:6ef054dd9f069330db3dcc66cb772d32'
+        },
+        'playlist_count': 4
+    }]
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_default/index.html?videoId=%s'
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        json_map = try_get(
+            self._search_nextjs_data(webpage, playlist_id),
+            lambda x: x['props']['pageProps']['article']['body']['content']) or []
+
+        entries = []
+        for video in json_map:
+            if not any(video['data'].get(attr) == 'Brightcove' for attr in ('name', 'type')):
+                continue
+            video_id = video['data']['id']
+            account_id = video['data']['accountId']
+            player_id = video['data']['playerId']
+            entries.append(self.url_result(
+                smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % (account_id, player_id, video_id), {
+                    # ITV does not like some GB IP ranges, so here are some
+                    # IP blocks it accepts
+                    'geo_ip_blocks': [
+                        '193.113.0.0/16', '54.36.162.0/23', '159.65.16.0/21'
+                    ],
+                    'referrer': url,
+                }),
+                ie=BrightcoveNewIE.ie_key(), video_id=video_id))
+
+        title = self._og_search_title(webpage, fatal=False)
+
+        return self.playlist_result(entries, playlist_id, title)