@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/adobetv.py

@@ -1,286 +0,0 @@
-import functools
-import re
-
-from .common import InfoExtractor
-from ..compat import compat_str
-from ..utils import (
-    float_or_none,
-    int_or_none,
-    ISO639Utils,
-    join_nonempty,
-    OnDemandPagedList,
-    parse_duration,
-    str_or_none,
-    str_to_int,
-    unified_strdate,
-)
-
-
-class AdobeTVBaseIE(InfoExtractor):
-    def _call_api(self, path, video_id, query, note=None):
-        return self._download_json(
-            'http://tv.adobe.com/api/v4/' + path,
-            video_id, note, query=query)['data']
-
-    def _parse_subtitles(self, video_data, url_key):
-        subtitles = {}
-        for translation in video_data.get('translations', []):
-            vtt_path = translation.get(url_key)
-            if not vtt_path:
-                continue
-            lang = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
-            subtitles.setdefault(lang, []).append({
-                'ext': 'vtt',
-                'url': vtt_path,
-            })
-        return subtitles
-
-    def _parse_video_data(self, video_data):
-        video_id = compat_str(video_data['id'])
-        title = video_data['title']
-
-        s3_extracted = False
-        formats = []
-        for source in video_data.get('videos', []):
-            source_url = source.get('url')
-            if not source_url:
-                continue
-            f = {
-                'format_id': source.get('quality_level'),
-                'fps': int_or_none(source.get('frame_rate')),
-                'height': int_or_none(source.get('height')),
-                'tbr': int_or_none(source.get('video_data_rate')),
-                'width': int_or_none(source.get('width')),
-                'url': source_url,
-            }
-            original_filename = source.get('original_filename')
-            if original_filename:
-                if not (f.get('height') and f.get('width')):
-                    mobj = re.search(r'_(\d+)x(\d+)', original_filename)
-                    if mobj:
-                        f.update({
-                            'height': int(mobj.group(2)),
-                            'width': int(mobj.group(1)),
-                        })
-                if original_filename.startswith('s3://') and not s3_extracted:
-                    formats.append({
-                        'format_id': 'original',
-                        'quality': 1,
-                        'url': original_filename.replace('s3://', 'https://s3.amazonaws.com/'),
-                    })
-                    s3_extracted = True
-            formats.append(f)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': video_data.get('description'),
-            'thumbnail': video_data.get('thumbnail'),
-            'upload_date': unified_strdate(video_data.get('start_date')),
-            'duration': parse_duration(video_data.get('duration')),
-            'view_count': str_to_int(video_data.get('playcount')),
-            'formats': formats,
-            'subtitles': self._parse_subtitles(video_data, 'vtt'),
-        }
-
-
-class AdobeTVEmbedIE(AdobeTVBaseIE):
-    IE_NAME = 'adobetv:embed'
-    _VALID_URL = r'https?://tv\.adobe\.com/embed/\d+/(?P<id>\d+)'
-    _TEST = {
-        'url': 'https://tv.adobe.com/embed/22/4153',
-        'md5': 'c8c0461bf04d54574fc2b4d07ac6783a',
-        'info_dict': {
-            'id': '4153',
-            'ext': 'flv',
-            'title': 'Creating Graphics Optimized for BlackBerry',
-            'description': 'md5:eac6e8dced38bdaae51cd94447927459',
-            'thumbnail': r're:https?://.*\.jpg$',
-            'upload_date': '20091109',
-            'duration': 377,
-            'view_count': int,
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        video_data = self._call_api(
-            'episode/' + video_id, video_id, {'disclosure': 'standard'})[0]
-        return self._parse_video_data(video_data)
-
-
-class AdobeTVIE(AdobeTVBaseIE):
-    IE_NAME = 'adobetv'
-    _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?watch/(?P<show_urlname>[^/]+)/(?P<id>[^/]+)'
-
-    _TEST = {
-        'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
-        'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
-        'info_dict': {
-            'id': '10981',
-            'ext': 'mp4',
-            'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
-            'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
-            'thumbnail': r're:https?://.*\.jpg$',
-            'upload_date': '20110914',
-            'duration': 60,
-            'view_count': int,
-        },
-    }
-
-    def _real_extract(self, url):
-        language, show_urlname, urlname = self._match_valid_url(url).groups()
-        if not language:
-            language = 'en'
-
-        video_data = self._call_api(
-            'episode/get', urlname, {
-                'disclosure': 'standard',
-                'language': language,
-                'show_urlname': show_urlname,
-                'urlname': urlname,
-            })[0]
-        return self._parse_video_data(video_data)
-
-
-class AdobeTVPlaylistBaseIE(AdobeTVBaseIE):
-    _PAGE_SIZE = 25
-
-    def _fetch_page(self, display_id, query, page):
-        page += 1
-        query['page'] = page
-        for element_data in self._call_api(
-                self._RESOURCE, display_id, query, 'Download Page %d' % page):
-            yield self._process_data(element_data)
-
-    def _extract_playlist_entries(self, display_id, query):
-        return OnDemandPagedList(functools.partial(
-            self._fetch_page, display_id, query), self._PAGE_SIZE)
-
-
-class AdobeTVShowIE(AdobeTVPlaylistBaseIE):
-    IE_NAME = 'adobetv:show'
-    _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?show/(?P<id>[^/]+)'
-
-    _TEST = {
-        'url': 'http://tv.adobe.com/show/the-complete-picture-with-julieanne-kost',
-        'info_dict': {
-            'id': '36',
-            'title': 'The Complete Picture with Julieanne Kost',
-            'description': 'md5:fa50867102dcd1aa0ddf2ab039311b27',
-        },
-        'playlist_mincount': 136,
-    }
-    _RESOURCE = 'episode'
-    _process_data = AdobeTVBaseIE._parse_video_data
-
-    def _real_extract(self, url):
-        language, show_urlname = self._match_valid_url(url).groups()
-        if not language:
-            language = 'en'
-        query = {
-            'disclosure': 'standard',
-            'language': language,
-            'show_urlname': show_urlname,
-        }
-
-        show_data = self._call_api(
-            'show/get', show_urlname, query)[0]
-
-        return self.playlist_result(
-            self._extract_playlist_entries(show_urlname, query),
-            str_or_none(show_data.get('id')),
-            show_data.get('show_name'),
-            show_data.get('show_description'))
-
-
-class AdobeTVChannelIE(AdobeTVPlaylistBaseIE):
-    IE_NAME = 'adobetv:channel'
-    _VALID_URL = r'https?://tv\.adobe\.com/(?:(?P<language>fr|de|es|jp)/)?channel/(?P<id>[^/]+)(?:/(?P<category_urlname>[^/]+))?'
-
-    _TEST = {
-        'url': 'http://tv.adobe.com/channel/development',
-        'info_dict': {
-            'id': 'development',
-        },
-        'playlist_mincount': 96,
-    }
-    _RESOURCE = 'show'
-
-    def _process_data(self, show_data):
-        return self.url_result(
-            show_data['url'], 'AdobeTVShow', str_or_none(show_data.get('id')))
-
-    def _real_extract(self, url):
-        language, channel_urlname, category_urlname = self._match_valid_url(url).groups()
-        if not language:
-            language = 'en'
-        query = {
-            'channel_urlname': channel_urlname,
-            'language': language,
-        }
-        if category_urlname:
-            query['category_urlname'] = category_urlname
-
-        return self.playlist_result(
-            self._extract_playlist_entries(channel_urlname, query),
-            channel_urlname)
-
-
-class AdobeTVVideoIE(AdobeTVBaseIE):
-    IE_NAME = 'adobetv:video'
-    _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
-    _EMBED_REGEX = [r'<iframe[^>]+src=[\'"](?P<url>(?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]']
-
-    _TEST = {
-        # From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners
-        'url': 'https://video.tv.adobe.com/v/2456/',
-        'md5': '43662b577c018ad707a63766462b1e87',
-        'info_dict': {
-            'id': '2456',
-            'ext': 'mp4',
-            'title': 'New experience with Acrobat DC',
-            'description': 'New experience with Acrobat DC',
-            'duration': 248.667,
-        },
-    }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
-
-        video_data = self._parse_json(self._search_regex(
-            r'var\s+bridge\s*=\s*([^;]+);', webpage, 'bridged data'), video_id)
-        title = video_data['title']
-
-        formats = []
-        sources = video_data.get('sources') or []
-        for source in sources:
-            source_src = source.get('src')
-            if not source_src:
-                continue
-            formats.append({
-                'filesize': int_or_none(source.get('kilobytes') or None, invscale=1000),
-                'format_id': join_nonempty(source.get('format'), source.get('label')),
-                'height': int_or_none(source.get('height') or None),
-                'tbr': int_or_none(source.get('bitrate') or None),
-                'width': int_or_none(source.get('width') or None),
-                'url': source_src,
-            })
-
-        # For both metadata and downloaded files the duration varies among
-        # formats. I just pick the max one
-        duration = max(filter(None, [
-            float_or_none(source.get('duration'), scale=1000)
-            for source in sources]))
-
-        return {
-            'id': video_id,
-            'formats': formats,
-            'title': title,
-            'description': video_data.get('description'),
-            'thumbnail': video_data.get('video', {}).get('poster'),
-            'duration': duration,
-            'subtitles': self._parse_subtitles(video_data, 'vttPath'),
-        }

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

@@ -1,198 +0,0 @@
-import json
-
-from .turner import TurnerBaseIE
-from ..utils import (
-    determine_ext,
-    float_or_none,
-    int_or_none,
-    mimetype2ext,
-    parse_age_limit,
-    parse_iso8601,
-    strip_or_none,
-    try_get,
-)
-
-
-class AdultSwimIE(TurnerBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?adultswim\.com/videos/(?P<show_path>[^/?#]+)(?:/(?P<episode_path>[^/?#]+))?'
-
-    _TESTS = [{
-        'url': 'http://adultswim.com/videos/rick-and-morty/pilot',
-        'info_dict': {
-            'id': 'rQxZvXQ4ROaSOqq-or2Mow',
-            'ext': 'mp4',
-            'title': 'Rick and Morty - Pilot',
-            'description': 'Rick moves in with his daughter\'s family and establishes himself as a bad influence on his grandson, Morty.',
-            'timestamp': 1543294800,
-            'upload_date': '20181127',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-        'expected_warnings': ['Unable to download f4m manifest'],
-    }, {
-        'url': 'http://www.adultswim.com/videos/tim-and-eric-awesome-show-great-job/dr-steve-brule-for-your-wine/',
-        'info_dict': {
-            'id': 'sY3cMUR_TbuE4YmdjzbIcQ',
-            'ext': 'mp4',
-            'title': 'Tim and Eric Awesome Show Great Job! - Dr. Steve Brule, For Your Wine',
-            'description': 'Dr. Brule reports live from Wine Country with a special report on wines.  \nWatch Tim and Eric Awesome Show Great Job! episode #20, "Embarrassed" on Adult Swim.',
-            'upload_date': '20080124',
-            'timestamp': 1201150800,
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-        'skip': '404 Not Found',
-    }, {
-        'url': 'http://www.adultswim.com/videos/decker/inside-decker-a-new-hero/',
-        'info_dict': {
-            'id': 'I0LQFQkaSUaFp8PnAWHhoQ',
-            'ext': 'mp4',
-            'title': 'Decker - Inside Decker: A New Hero',
-            'description': 'The guys recap the conclusion of the season. They announce a new hero, take a peek into the Victorville Film Archive and welcome back the talented James Dean.',
-            'timestamp': 1469480460,
-            'upload_date': '20160725',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-        'expected_warnings': ['Unable to download f4m manifest'],
-    }, {
-        'url': 'http://www.adultswim.com/videos/attack-on-titan',
-        'info_dict': {
-            'id': 'attack-on-titan',
-            'title': 'Attack on Titan',
-            'description': 'md5:41caa9416906d90711e31dc00cb7db7e',
-        },
-        'playlist_mincount': 12,
-    }, {
-        'url': 'http://www.adultswim.com/videos/streams/williams-stream',
-        'info_dict': {
-            'id': 'd8DEBj7QRfetLsRgFnGEyg',
-            'ext': 'mp4',
-            'title': r're:^Williams Stream \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
-            'description': 'original programming',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-        'skip': '404 Not Found',
-    }]
-
-    def _real_extract(self, url):
-        show_path, episode_path = self._match_valid_url(url).groups()
-        display_id = episode_path or show_path
-        query = '''query {
-  getShowBySlug(slug:"%s") {
-    %%s
-  }
-}''' % show_path
-        if episode_path:
-            query = query % '''title
-    getVideoBySlug(slug:"%s") {
-      _id
-      auth
-      description
-      duration
-      episodeNumber
-      launchDate
-      mediaID
-      seasonNumber
-      poster
-      title
-      tvRating
-    }''' % episode_path
-        else:
-            query = query % '''metaDescription
-    title
-    videos(first:1000,sort:["episode_number"]) {
-      edges {
-        node {
-           _id
-           slug
-        }
-      }
-    }'''
-        show_data = self._download_json(
-            'https://www.adultswim.com/api/search', display_id,
-            data=json.dumps({'query': query}).encode(),
-            headers={'Content-Type': 'application/json'})['data']['getShowBySlug']
-        if episode_path:
-            video_data = show_data['getVideoBySlug']
-            video_id = video_data['_id']
-            episode_title = title = video_data['title']
-            series = show_data.get('title')
-            if series:
-                title = '%s - %s' % (series, title)
-            info = {
-                'id': video_id,
-                'title': title,
-                'description': strip_or_none(video_data.get('description')),
-                'duration': float_or_none(video_data.get('duration')),
-                'formats': [],
-                'subtitles': {},
-                'age_limit': parse_age_limit(video_data.get('tvRating')),
-                'thumbnail': video_data.get('poster'),
-                'timestamp': parse_iso8601(video_data.get('launchDate')),
-                'series': series,
-                'season_number': int_or_none(video_data.get('seasonNumber')),
-                'episode': episode_title,
-                'episode_number': int_or_none(video_data.get('episodeNumber')),
-            }
-
-            auth = video_data.get('auth')
-            media_id = video_data.get('mediaID')
-            if media_id:
-                info.update(self._extract_ngtv_info(media_id, {
-                    # CDN_TOKEN_APP_ID from:
-                    # https://d2gg02c3xr550i.cloudfront.net/assets/asvp.e9c8bef24322d060ef87.bundle.js
-                    'appId': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJhcHBJZCI6ImFzLXR2ZS1kZXNrdG9wLXB0enQ2bSIsInByb2R1Y3QiOiJ0dmUiLCJuZXR3b3JrIjoiYXMiLCJwbGF0Zm9ybSI6ImRlc2t0b3AiLCJpYXQiOjE1MzI3MDIyNzl9.BzSCk-WYOZ2GMCIaeVb8zWnzhlgnXuJTCu0jGp_VaZE',
-                }, {
-                    'url': url,
-                    'site_name': 'AdultSwim',
-                    'auth_required': auth,
-                }))
-
-            if not auth:
-                extract_data = self._download_json(
-                    'https://www.adultswim.com/api/shows/v1/videos/' + video_id,
-                    video_id, query={'fields': 'stream'}, fatal=False) or {}
-                assets = try_get(extract_data, lambda x: x['data']['video']['stream']['assets'], list) or []
-                for asset in assets:
-                    asset_url = asset.get('url')
-                    if not asset_url:
-                        continue
-                    ext = determine_ext(asset_url, mimetype2ext(asset.get('mime_type')))
-                    if ext == 'm3u8':
-                        fmts, subs = self._extract_m3u8_formats_and_subtitles(
-                            asset_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
-                        info['formats'].extend(fmts)
-                        self._merge_subtitles(subs, target=info['subtitles'])
-                    elif ext == 'f4m':
-                        continue
-                        # info['formats'].extend(self._extract_f4m_formats(
-                        #     asset_url, video_id, f4m_id='hds', fatal=False))
-                    elif ext in ('scc', 'ttml', 'vtt'):
-                        info['subtitles'].setdefault('en', []).append({
-                            'url': asset_url,
-                        })
-
-            return info
-        else:
-            entries = []
-            for edge in show_data.get('videos', {}).get('edges', []):
-                video = edge.get('node') or {}
-                slug = video.get('slug')
-                if not slug:
-                    continue
-                entries.append(self.url_result(
-                    'http://adultswim.com/videos/%s/%s' % (show_path, slug),
-                    'AdultSwim', video.get('_id')))
-            return self.playlist_result(
-                entries, show_path, show_data.get('title'),
-                strip_or_none(show_data.get('metaDescription')))