@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/tenplay.py

@@ -0,0 +1,170 @@
+import base64
+import functools
+import itertools
+from datetime import datetime
+
+from .common import InfoExtractor
+from ..networking import HEADRequest
+from ..utils import int_or_none, traverse_obj, urlencode_postdata, urljoin
+
+
+class TenPlayIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?:[^/]+/)+(?P<id>tpv\d{6}[a-z]{5})'
+    _NETRC_MACHINE = '10play'
+    _TESTS = [{
+        'url': 'https://10play.com.au/neighbours/web-extras/season-39/nathan-borg-is-the-first-aussie-actor-with-a-cochlear-implant-to-join-neighbours/tpv210128qupwd',
+        'info_dict': {
+            'id': '6226844312001',
+            'ext': 'mp4',
+            'title': 'Nathan Borg Is The First Aussie Actor With A Cochlear Implant To Join Neighbours',
+            'alt_title': 'Nathan Borg Is The First Aussie Actor With A Cochlear Implant To Join Neighbours',
+            'description': 'md5:a02d0199c901c2dd4c796f1e7dd0de43',
+            'duration': 186,
+            'season': 'Season 39',
+            'season_number': 39,
+            'series': 'Neighbours',
+            'thumbnail': r're:https://.*\.jpg',
+            'uploader': 'Channel 10',
+            'age_limit': 15,
+            'timestamp': 1611810000,
+            'upload_date': '20210128',
+            'uploader_id': '2199827728001',
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'skip': 'Only available in Australia',
+    }, {
+        'url': 'https://10play.com.au/todd-sampsons-body-hack/episodes/season-4/episode-7/tpv200921kvngh',
+        'info_dict': {
+            'id': '6192880312001',
+            'ext': 'mp4',
+            'title': "Todd Sampson's Body Hack - S4 Ep. 2",
+            'description': 'md5:fa278820ad90f08ea187f9458316ac74',
+            'age_limit': 15,
+            'timestamp': 1600770600,
+            'upload_date': '20200922',
+            'uploader': 'Channel 10',
+            'uploader_id': '2199827728001'
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://10play.com.au/how-to-stay-married/web-extras/season-1/terrys-talks-ep-1-embracing-change/tpv190915ylupc',
+        'only_matching': True,
+    }]
+    _GEO_BYPASS = False
+
+    _AUS_AGES = {
+        'G': 0,
+        'PG': 15,
+        'M': 15,
+        'MA': 15,
+        'MA15+': 15,
+        'R': 18,
+        'X': 18
+    }
+
+    def _get_bearer_token(self, video_id):
+        username, password = self._get_login_info()
+        if username is None or password is None:
+            self.raise_login_required('Your 10play account\'s details must be provided with --username and --password.')
+        _timestamp = datetime.now().strftime('%Y%m%d000000')
+        _auth_header = base64.b64encode(_timestamp.encode('ascii')).decode('ascii')
+        data = self._download_json('https://10play.com.au/api/user/auth', video_id, 'Getting bearer token', headers={
+            'X-Network-Ten-Auth': _auth_header,
+        }, data=urlencode_postdata({
+            'email': username,
+            'password': password,
+        }))
+        return 'Bearer ' + data['jwt']['accessToken']
+
+    def _real_extract(self, url):
+        content_id = self._match_id(url)
+        data = self._download_json(
+            'https://10play.com.au/api/v1/videos/' + content_id, content_id)
+        headers = {}
+
+        if data.get('memberGated') is True:
+            _token = self._get_bearer_token(content_id)
+            headers = {'Authorization': _token}
+
+        _video_url = self._download_json(
+            data.get('playbackApiEndpoint'), content_id, 'Downloading video JSON',
+            headers=headers).get('source')
+        m3u8_url = self._request_webpage(HEADRequest(
+            _video_url), content_id).url
+        if '10play-not-in-oz' in m3u8_url:
+            self.raise_geo_restricted(countries=['AU'])
+        formats = self._extract_m3u8_formats(m3u8_url, content_id, 'mp4')
+
+        return {
+            'formats': formats,
+            'subtitles': {'en': [{'url': data.get('captionUrl')}]} if data.get('captionUrl') else None,
+            'id': data.get('altId') or content_id,
+            'duration': data.get('duration'),
+            'title': data.get('subtitle'),
+            'alt_title': data.get('title'),
+            'description': data.get('description'),
+            'age_limit': self._AUS_AGES.get(data.get('classification')),
+            'series': data.get('tvShow'),
+            'season_number': int_or_none(data.get('season')),
+            'episode_number': int_or_none(data.get('episode')),
+            'timestamp': data.get('published'),
+            'thumbnail': data.get('imageUrl'),
+            'uploader': 'Channel 10',
+            'uploader_id': '2199827728001',
+        }
+
+
+class TenPlaySeasonIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?P<show>[^/?#]+)/episodes/(?P<season>[^/?#]+)/?(?:$|[?#])'
+    _TESTS = [{
+        'url': 'https://10play.com.au/masterchef/episodes/season-14',
+        'info_dict': {
+            'title': 'Season 14',
+            'id': 'MjMyOTIy',
+        },
+        'playlist_mincount': 64,
+    }, {
+        'url': 'https://10play.com.au/the-bold-and-the-beautiful-fast-tracked/episodes/season-2022',
+        'info_dict': {
+            'title': 'Season 2022',
+            'id': 'Mjc0OTIw',
+        },
+        'playlist_mincount': 256,
+    }]
+
+    def _entries(self, load_more_url, display_id=None):
+        skip_ids = []
+        for page in itertools.count(1):
+            episodes_carousel = self._download_json(
+                load_more_url, display_id, query={'skipIds[]': skip_ids},
+                note=f'Fetching episodes page {page}')
+
+            episodes_chunk = episodes_carousel['items']
+            skip_ids.extend(ep['id'] for ep in episodes_chunk)
+
+            for ep in episodes_chunk:
+                yield ep['cardLink']
+            if not episodes_carousel['hasMore']:
+                break
+
+    def _real_extract(self, url):
+        show, season = self._match_valid_url(url).group('show', 'season')
+        season_info = self._download_json(
+            f'https://10play.com.au/api/shows/{show}/episodes/{season}', f'{show}/{season}')
+
+        episodes_carousel = traverse_obj(season_info, (
+            'content', 0, 'components', (
+                lambda _, v: v['title'].lower() == 'episodes',
+                (..., {dict}),
+            )), get_all=False) or {}
+
+        playlist_id = episodes_carousel['tpId']
+
+        return self.playlist_from_matches(
+            self._entries(urljoin(url, episodes_carousel['loadMoreUrl']), playlist_id),
+            playlist_id, traverse_obj(season_info, ('content', 0, 'title', {str})),
+            getter=functools.partial(urljoin, url))

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

@@ -0,0 +1,50 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import ExtractorError
+
+
+class TestURLIE(InfoExtractor):
+    """ Allows addressing of the test cases as test:yout.*be_1 """
+
+    IE_DESC = False  # Do not list
+    _VALID_URL = r'test(?:url)?:(?P<extractor>.*?)(?:_(?P<num>\d+|all))?$'
+
+    def _real_extract(self, url):
+        from . import gen_extractor_classes
+
+        extractor_id, num = self._match_valid_url(url).group('extractor', 'num')
+        if not extractor_id:
+            return {'id': ':test', 'title': '', 'url': url}
+
+        rex = re.compile(extractor_id, flags=re.IGNORECASE)
+        matching_extractors = [e for e in gen_extractor_classes() if rex.search(e.IE_NAME)]
+
+        if len(matching_extractors) == 0:
+            raise ExtractorError(f'No extractors matching {extractor_id!r} found', expected=True)
+        elif len(matching_extractors) > 1:
+            extractor = next((  # Check for exact match
+                ie for ie in matching_extractors if ie.IE_NAME.lower() == extractor_id.lower()
+            ), None) or next((  # Check for exact match without plugin suffix
+                ie for ie in matching_extractors if ie.IE_NAME.split('+')[0].lower() == extractor_id.lower()
+            ), None)
+            if not extractor:
+                raise ExtractorError(
+                    'Found multiple matching extractors: %s' % ' '.join(ie.IE_NAME for ie in matching_extractors),
+                    expected=True)
+        else:
+            extractor = matching_extractors[0]
+
+        testcases = tuple(extractor.get_testcases(True))
+        if num == 'all':
+            return self.playlist_result(
+                [self.url_result(tc['url'], extractor) for tc in testcases],
+                url, f'{extractor.IE_NAME} tests')
+        try:
+            tc = testcases[int(num or 0)]
+        except IndexError:
+            raise ExtractorError(
+                f'Test case {num or 0} not found, got only {len(testcases)} tests', expected=True)
+
+        self.to_screen(f'Test URL: {tc["url"]}')
+        return self.url_result(tc['url'], extractor)

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/yt_dlp/extractor/tf1.py

@@ -0,0 +1,101 @@
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    parse_iso8601,
+    try_get,
+)
+
+
+class TF1IE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?tf1\.fr/[^/]+/(?P<program_slug>[^/]+)/videos/(?P<id>[^/?&#]+)\.html'
+    _TESTS = [{
+        'url': 'https://www.tf1.fr/tmc/quotidien-avec-yann-barthes/videos/quotidien-premiere-partie-11-juin-2019.html',
+        'info_dict': {
+            'id': '13641379',
+            'ext': 'mp4',
+            'title': 'md5:f392bc52245dc5ad43771650c96fb620',
+            'description': 'md5:a02cdb217141fb2d469d6216339b052f',
+            'upload_date': '20190611',
+            'timestamp': 1560273989,
+            'duration': 1738,
+            'series': 'Quotidien avec Yann Barthès',
+            'tags': ['intégrale', 'quotidien', 'Replay'],
+        },
+        'params': {
+            # Sometimes wat serves the whole file with the --test option
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.tf1.fr/tmc/burger-quiz/videos/burger-quiz-du-19-aout-2023-s03-episode-21-85585666.html',
+        'info_dict': {
+            'id': '14010600',
+            'ext': 'mp4',
+            'title': 'Burger Quiz - S03 EP21 avec Eye Haidara, Anne Depétrini, Jonathan Zaccaï et Pio Marmaï',
+            'thumbnail': 'https://photos.tf1.fr/1280/720/burger-quiz-11-9adb79-0@1x.jpg',
+            'description': 'Manu Payet recevra Eye Haidara, Anne Depétrini, Jonathan Zaccaï et Pio Marmaï.',
+            'upload_date': '20230819',
+            'timestamp': 1692469471,
+            'season_number': 3,
+            'series': 'Burger Quiz',
+            'episode_number': 21,
+            'season': 'Season 3',
+            'tags': 'count:13',
+            'episode': 'Episode 21',
+            'duration': 2312
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'http://www.tf1.fr/tf1/koh-lanta/videos/replay-koh-lanta-22-mai-2015.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.tf1.fr/hd1/documentaire/videos/mylene-farmer-d-une-icone.html',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        program_slug, slug = self._match_valid_url(url).groups()
+        video = self._download_json(
+            'https://www.tf1.fr/graphql/web', slug, query={
+                'id': '9b80783950b85247541dd1d851f9cc7fa36574af015621f853ab111a679ce26f',
+                'variables': json.dumps({
+                    'programSlug': program_slug,
+                    'slug': slug,
+                })
+            })['data']['videoBySlug']
+        wat_id = video['streamId']
+
+        tags = []
+        for tag in (video.get('tags') or []):
+            label = tag.get('label')
+            if not label:
+                continue
+            tags.append(label)
+
+        decoration = video.get('decoration') or {}
+
+        thumbnails = []
+        for source in (try_get(decoration, lambda x: x['image']['sources'], list) or []):
+            source_url = source.get('url')
+            if not source_url:
+                continue
+            thumbnails.append({
+                'url': source_url,
+                'width': int_or_none(source.get('width')),
+            })
+
+        return {
+            '_type': 'url_transparent',
+            'id': wat_id,
+            'url': 'wat:' + wat_id,
+            'title': video.get('title'),
+            'thumbnails': thumbnails,
+            'description': decoration.get('description'),
+            'timestamp': parse_iso8601(video.get('date')),
+            'duration': int_or_none(try_get(video, lambda x: x['publicPlayingInfos']['duration'])),
+            'tags': tags,
+            'series': decoration.get('programLabel'),
+            'season_number': int_or_none(video.get('season')),
+            'episode_number': int_or_none(video.get('episode')),
+        }

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

@@ -0,0 +1,48 @@
+import json
+
+from .common import InfoExtractor
+from ..networking import HEADRequest
+from ..utils import ExtractorError, clean_html, int_or_none
+
+
+class TFOIE(InfoExtractor):
+    _GEO_COUNTRIES = ['CA']
+    _VALID_URL = r'https?://(?:www\.)?tfo\.org/(?:en|fr)/(?:[^/]+/){2}(?P<id>\d+)'
+    _TEST = {
+        'url': 'http://www.tfo.org/en/universe/tfo-247/100463871/video-game-hackathon',
+        'md5': 'cafbe4f47a8dae0ca0159937878100d6',
+        'info_dict': {
+            'id': '7da3d50e495c406b8fc0b997659cc075',
+            'ext': 'mp4',
+            'title': 'Video Game Hackathon',
+            'description': 'md5:558afeba217c6c8d96c60e5421795c07',
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        self._request_webpage(HEADRequest('http://www.tfo.org/'), video_id)
+        infos = self._download_json(
+            'http://www.tfo.org/api/web/video/get_infos', video_id, data=json.dumps({
+                'product_id': video_id,
+            }).encode(), headers={
+                'X-tfo-session': self._get_cookies('http://www.tfo.org/')['tfo-session'].value,
+            })
+        if infos.get('success') == 0:
+            if infos.get('code') == 'ErrGeoBlocked':
+                self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
+            raise ExtractorError('%s said: %s' % (self.IE_NAME, clean_html(infos['msg'])), expected=True)
+        video_data = infos['data']
+
+        return {
+            '_type': 'url_transparent',
+            'id': video_id,
+            'url': 'limelight:media:' + video_data['llid'],
+            'title': video_data['title'],
+            'description': video_data.get('description'),
+            'series': video_data.get('collection'),
+            'season_number': int_or_none(video_data.get('season')),
+            'episode_number': int_or_none(video_data.get('episode')),
+            'duration': int_or_none(video_data.get('duration')),
+            'ie_key': 'LimelightMedia',
+        }

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

@@ -0,0 +1,135 @@
+import itertools
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    extract_attributes,
+    get_element_by_class,
+    get_element_html_by_class,
+    get_elements_html_by_class,
+    parse_qs,
+    traverse_obj,
+    unified_strdate,
+    urljoin
+)
+
+
+class TheGuardianPodcastIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?theguardian\.com/\w+/audio/\d{4}/\w{3}/\d{1,2}/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://www.theguardian.com/news/audio/2023/nov/03/we-are-just-getting-started-the-plastic-eating-bacteria-that-could-change-the-world-podcast',
+        'md5': 'd1771744681789b4cd7da2a08e487702',
+        'info_dict': {
+            'id': 'we-are-just-getting-started-the-plastic-eating-bacteria-that-could-change-the-world-podcast',
+            'ext': 'mp3',
+            'title': '‘We are just getting started’: the plastic-eating bacteria that could change the world – podcast',
+            'description': 'md5:cfd3df2791d394d2ab62cd571d5207ee',
+            'creator': 'Stephen Buranyi',
+            'thumbnail': 'md5:73c12558fcb3b0e2a59422bfb33b3f79',
+            'release_date': '20231103'
+        }
+    }, {
+        'url': 'https://www.theguardian.com/news/audio/2023/oct/30/the-trials-of-robert-habeck-is-the-worlds-most-powerful-green-politician-doomed-to-fail-podcast',
+        'md5': 'd1771744681789b4cd7da2a08e487702',
+        'info_dict': {
+            'id': 'the-trials-of-robert-habeck-is-the-worlds-most-powerful-green-politician-doomed-to-fail-podcast',
+            'ext': 'mp3',
+            'title': 'The trials of Robert Habeck: is the world’s most powerful green politician doomed to fail? – podcast',
+            'description': 'md5:1b5cf6582d1771c6b7077784b5456994',
+            'creator': 'Philip Oltermann',
+            'thumbnail': 'md5:6e5c5ec43843e956e20be793722e9080',
+            'release_date': '20231030'
+        }
+    }, {
+        'url': 'https://www.theguardian.com/football/audio/2023/nov/06/arsenal-feel-hard-done-by-and-luton-hold-liverpool-football-weekly',
+        'md5': 'a2fcff6f8e060a95b1483295273dc35e',
+        'info_dict': {
+            'id': 'arsenal-feel-hard-done-by-and-luton-hold-liverpool-football-weekly',
+            'ext': 'mp3',
+            'title': 'Arsenal feel hard done by and Luton hold Liverpool – Football Weekly',
+            'description': 'md5:286a9fbddaeb7c83cc65d1c4a5330b2a',
+            'creator': 'Max Rushden',
+            'thumbnail': 'md5:93eb7d6440f1bb94eb3a6cad63f48afd',
+            'release_date': '20231106'
+        }
+    }, {
+        'url': 'https://www.theguardian.com/politics/audio/2023/nov/02/the-covid-inquiry-politics-weekly-uk-podcast',
+        'md5': '06a0f7e9701a80c8064a5d35690481ec',
+        'info_dict': {
+            'id': 'the-covid-inquiry-politics-weekly-uk-podcast',
+            'ext': 'mp3',
+            'title': 'The Covid inquiry | Politics Weekly UK - podcast',
+            'description': 'md5:207c98859c14903582b17d25b014046e',
+            'creator': 'Gaby Hinsliff',
+            'thumbnail': 'md5:28932a7b5a25b057be330d2ed70ea7f3',
+            'release_date': '20231102'
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage) or get_element_by_class('content__headline', webpage),
+            'description': self._og_search_description(webpage),
+            'creator': self._html_search_meta('author', webpage),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'release_date': unified_strdate(self._html_search_meta('article:published_time', webpage)),
+            'url': extract_attributes(get_element_html_by_class(
+                'podcast__player', webpage) or '').get('data-source'),
+        }
+
+
+class TheGuardianPodcastPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?theguardian\.com/\w+/series/(?P<id>[\w-]+)(?:\?page=\d+)?'
+    _TESTS = [{
+        'url': 'https://www.theguardian.com/football/series/theguardianswomensfootballweekly',
+        'info_dict': {
+            'id': 'theguardianswomensfootballweekly',
+            'title': "The Guardian's Women's Football Weekly",
+            'description': 'md5:e2cc021311e582d29935a73614a43f51'
+        },
+        'playlist_mincount': 69
+    }, {
+        'url': 'https://www.theguardian.com/news/series/todayinfocus?page=2',
+        'info_dict': {
+            'id': 'todayinfocus',
+            'title': 'Today in Focus',
+            'description': 'md5:0f097764fc0d359e0b6eb537be0387e2'
+        },
+        'playlist_mincount': 1261
+    }, {
+        'url': 'https://www.theguardian.com/news/series/the-audio-long-read',
+        'info_dict': {
+            'id': 'the-audio-long-read',
+            'title': 'The Audio Long Read',
+            'description': 'md5:5462994a27527309562b25b6defc4ef3'
+        },
+        'playlist_mincount': 996
+    }]
+
+    def _entries(self, url, playlist_id):
+        for page in itertools.count(1):
+            webpage, urlh = self._download_webpage_handle(
+                url, playlist_id, f'Downloading page {page}', query={'page': page})
+            if 'page' not in parse_qs(urlh.url):
+                break
+
+            episodes = get_elements_html_by_class('fc-item--type-media', webpage)
+            for url_path in traverse_obj(episodes, (..., {extract_attributes}, 'data-id')):
+                yield url_path
+
+    def _real_extract(self, url):
+        podcast_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, podcast_id)
+
+        title = clean_html(get_element_by_class(
+            'index-page-header__title', webpage) or get_element_by_class('flagship-audio__title', webpage))
+        description = self._og_search_description(webpage) or self._html_search_meta(
+            'description', webpage)
+
+        return self.playlist_from_matches(
+            self._entries(url, podcast_id), podcast_id, title, description=description,
+            ie=TheGuardianPodcastIE, getter=lambda x: urljoin('https://www.theguardian.com', x))

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

@@ -0,0 +1,35 @@
+from .common import InfoExtractor
+from ..utils import extract_attributes, remove_end
+
+
+class TheHoleTvIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?the-hole\.tv/episodes/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://the-hole.tv/episodes/gromkii-vopros-sergey-orlov',
+        'md5': 'fea6682f47786f3ae5a6cbd635ec4bf9',
+        'info_dict': {
+            'id': 'gromkii-vopros-sergey-orlov',
+            'ext': 'mp4',
+            'title': 'Сергей Орлов — Громкий вопрос',
+            'thumbnail': 'https://assets-cdn.the-hole.tv/images/t8gan4n6zn627e7wni11b2uemqts',
+            'description': 'md5:45741a9202331f995d9fb76996759379'
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        player_attrs = extract_attributes(self._search_regex(
+            r'(<div[^>]*\bdata-controller="player"[^>]*>)', webpage, 'video player'))
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            player_attrs['data-player-source-value'], video_id, 'mp4')
+
+        return {
+            'id': video_id,
+            'title': remove_end(self._html_extract_title(webpage), ' — The Hole'),
+            'description': self._og_search_description(webpage),
+            'thumbnail': player_attrs.get('data-player-poster-value'),
+            '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/theintercept.py

@@ -0,0 +1,46 @@
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    parse_iso8601,
+    int_or_none,
+    ExtractorError,
+)
+
+
+class TheInterceptIE(InfoExtractor):
+    _VALID_URL = r'https?://theintercept\.com/fieldofvision/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://theintercept.com/fieldofvision/thisisacoup-episode-four-surrender-or-die/',
+        'md5': '145f28b41d44aab2f87c0a4ac8ec95bd',
+        'info_dict': {
+            'id': '46214',
+            'ext': 'mp4',
+            'title': '#ThisIsACoup – Episode Four: Surrender or Die',
+            'description': 'md5:74dd27f0e2fbd50817829f97eaa33140',
+            'timestamp': 1450429239,
+            'upload_date': '20151218',
+            'comment_count': int,
+        }
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        json_data = self._parse_json(self._search_regex(
+            r'initialStoreTree\s*=\s*(?P<json_data>{.+})', webpage,
+            'initialStoreTree'), display_id)
+
+        for post in json_data['resources']['posts'].values():
+            if post['slug'] == display_id:
+                return {
+                    '_type': 'url_transparent',
+                    'url': 'jwplatform:%s' % post['fov_videoid'],
+                    'id': compat_str(post['ID']),
+                    'display_id': display_id,
+                    'title': post['title'],
+                    'description': post.get('excerpt'),
+                    'timestamp': parse_iso8601(post.get('date')),
+                    'comment_count': int_or_none(post.get('comments_number')),
+                }
+        raise ExtractorError('Unable to find the current post')