@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/playsuisse.py

@@ -0,0 +1,234 @@
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    parse_qs,
+    traverse_obj,
+    update_url_query,
+    urlencode_postdata,
+)
+
+
+class PlaySuisseIE(InfoExtractor):
+    _NETRC_MACHINE = 'playsuisse'
+    _VALID_URL = r'https?://(?:www\.)?playsuisse\.ch/(?:watch|detail)/(?:[^#]*[?&]episodeId=)?(?P<id>[0-9]+)'
+    _TESTS = [
+        {
+            # Old URL
+            'url': 'https://www.playsuisse.ch/watch/763211/0',
+            'only_matching': True,
+        },
+        {
+            # episode in a series
+            'url': 'https://www.playsuisse.ch/watch/763182?episodeId=763211',
+            'md5': '82df2a470b2dfa60c2d33772a8a60cf8',
+            'info_dict': {
+                'id': '763211',
+                'ext': 'mp4',
+                'title': 'Knochen',
+                'description': 'md5:8ea7a8076ba000cd9e8bc132fd0afdd8',
+                'duration': 3344,
+                'series': 'Wilder',
+                'season': 'Season 1',
+                'season_number': 1,
+                'episode': 'Knochen',
+                'episode_number': 1,
+                'thumbnail': 're:https://playsuisse-img.akamaized.net/',
+            }
+        }, {
+            # film
+            'url': 'https://www.playsuisse.ch/watch/808675',
+            'md5': '818b94c1d2d7c4beef953f12cb8f3e75',
+            'info_dict': {
+                'id': '808675',
+                'ext': 'mp4',
+                'title': 'Der Läufer',
+                'description': 'md5:9f61265c7e6dcc3e046137a792b275fd',
+                'duration': 5280,
+                'thumbnail': 're:https://playsuisse-img.akamaized.net/',
+            }
+        }, {
+            # series (treated as a playlist)
+            'url': 'https://www.playsuisse.ch/detail/1115687',
+            'info_dict': {
+                'description': 'md5:e4a2ae29a8895823045b5c3145a02aa3',
+                'id': '1115687',
+                'series': 'They all came out to Montreux',
+                'title': 'They all came out to Montreux',
+            },
+            'playlist': [{
+                'info_dict': {
+                    'description': 'md5:f2462744834b959a31adc6292380cda2',
+                    'duration': 3180,
+                    'episode': 'Folge 1',
+                    'episode_number': 1,
+                    'id': '1112663',
+                    'season': 'Season 1',
+                    'season_number': 1,
+                    'series': 'They all came out to Montreux',
+                    'thumbnail': 're:https://playsuisse-img.akamaized.net/',
+                    'title': 'Folge 1',
+                    'ext': 'mp4'
+                },
+            }, {
+                'info_dict': {
+                    'description': 'md5:9dfd308699fe850d3bce12dc1bad9b27',
+                    'duration': 2935,
+                    'episode': 'Folge 2',
+                    'episode_number': 2,
+                    'id': '1112661',
+                    'season': 'Season 1',
+                    'season_number': 1,
+                    'series': 'They all came out to Montreux',
+                    'thumbnail': 're:https://playsuisse-img.akamaized.net/',
+                    'title': 'Folge 2',
+                    'ext': 'mp4'
+                },
+            }, {
+                'info_dict': {
+                    'description': 'md5:14a93a3356b2492a8f786ab2227ef602',
+                    'duration': 2994,
+                    'episode': 'Folge 3',
+                    'episode_number': 3,
+                    'id': '1112664',
+                    'season': 'Season 1',
+                    'season_number': 1,
+                    'series': 'They all came out to Montreux',
+                    'thumbnail': 're:https://playsuisse-img.akamaized.net/',
+                    'title': 'Folge 3',
+                    'ext': 'mp4'
+                }
+            }],
+        }
+    ]
+
+    _GRAPHQL_QUERY = '''
+        query AssetWatch($assetId: ID!) {
+            assetV2(id: $assetId) {
+                ...Asset
+                episodes {
+                    ...Asset
+                }
+            }
+        }
+        fragment Asset on AssetV2 {
+            id
+            name
+            description
+            duration
+            episodeNumber
+            seasonNumber
+            seriesName
+            medias {
+                type
+                url
+            }
+            thumbnail16x9 {
+                ...ImageDetails
+            }
+            thumbnail2x3 {
+                ...ImageDetails
+            }
+            thumbnail16x9WithTitle {
+                ...ImageDetails
+            }
+            thumbnail2x3WithTitle {
+                ...ImageDetails
+            }
+        }
+        fragment ImageDetails on AssetImage {
+            id
+            url
+        }'''
+    _LOGIN_BASE_URL = 'https://login.srgssr.ch/srgssrlogin.onmicrosoft.com'
+    _LOGIN_PATH = 'B2C_1A__SignInV2'
+    _ID_TOKEN = None
+
+    def _perform_login(self, username, password):
+        login_page = self._download_webpage(
+            'https://www.playsuisse.ch/api/sso/login', None, note='Downloading login page',
+            query={'x': 'x', 'locale': 'de', 'redirectUrl': 'https://www.playsuisse.ch/'})
+        settings = self._search_json(r'var\s+SETTINGS\s*=', login_page, 'settings', None)
+
+        csrf_token = settings['csrf']
+        query = {'tx': settings['transId'], 'p': self._LOGIN_PATH}
+
+        status = traverse_obj(self._download_json(
+            f'{self._LOGIN_BASE_URL}/{self._LOGIN_PATH}/SelfAsserted', None, 'Logging in',
+            query=query, headers={'X-CSRF-TOKEN': csrf_token}, data=urlencode_postdata({
+                'request_type': 'RESPONSE',
+                'signInName': username,
+                'password': password
+            }), expected_status=400), ('status', {int_or_none}))
+        if status == 400:
+            raise ExtractorError('Invalid username or password', expected=True)
+
+        urlh = self._request_webpage(
+            f'{self._LOGIN_BASE_URL}/{self._LOGIN_PATH}/api/CombinedSigninAndSignup/confirmed',
+            None, 'Downloading ID token', query={
+                'rememberMe': 'false',
+                'csrf_token': csrf_token,
+                **query,
+                'diags': '',
+            })
+
+        self._ID_TOKEN = traverse_obj(parse_qs(urlh.url), ('id_token', 0))
+        if not self._ID_TOKEN:
+            raise ExtractorError('Login failed')
+
+    def _get_media_data(self, media_id):
+        # NOTE In the web app, the "locale" header is used to switch between languages,
+        # However this doesn't seem to take effect when passing the header here.
+        response = self._download_json(
+            'https://www.playsuisse.ch/api/graphql',
+            media_id, data=json.dumps({
+                'operationName': 'AssetWatch',
+                'query': self._GRAPHQL_QUERY,
+                'variables': {'assetId': media_id}
+            }).encode('utf-8'),
+            headers={'Content-Type': 'application/json', 'locale': 'de'})
+
+        return response['data']['assetV2']
+
+    def _real_extract(self, url):
+        if not self._ID_TOKEN:
+            self.raise_login_required(method='password')
+
+        media_id = self._match_id(url)
+        media_data = self._get_media_data(media_id)
+        info = self._extract_single(media_data)
+        if media_data.get('episodes'):
+            info.update({
+                '_type': 'playlist',
+                'entries': map(self._extract_single, media_data['episodes']),
+            })
+        return info
+
+    def _extract_single(self, media_data):
+        thumbnails = traverse_obj(media_data, lambda k, _: k.startswith('thumbnail'))
+
+        formats, subtitles = [], {}
+        for media in traverse_obj(media_data, 'medias', default=[]):
+            if not media.get('url') or media.get('type') != 'HLS':
+                continue
+            f, subs = self._extract_m3u8_formats_and_subtitles(
+                update_url_query(media['url'], {'id_token': self._ID_TOKEN}),
+                media_data['id'], 'mp4', m3u8_id='HLS', fatal=False)
+            formats.extend(f)
+            self._merge_subtitles(subs, target=subtitles)
+
+        return {
+            'id': media_data['id'],
+            'title': media_data.get('name'),
+            'description': media_data.get('description'),
+            'thumbnails': thumbnails,
+            'duration': int_or_none(media_data.get('duration')),
+            'formats': formats,
+            'subtitles': subtitles,
+            'series': media_data.get('seriesName'),
+            'season_number': int_or_none(media_data.get('seasonNumber')),
+            'episode': media_data.get('name') if media_data.get('episodeNumber') else None,
+            'episode_number': int_or_none(media_data.get('episodeNumber')),
+        }

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

@@ -0,0 +1,185 @@
+from .common import InfoExtractor
+from ..compat import (
+    compat_urlparse,
+    compat_urllib_parse_urlencode,
+)
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    parse_iso8601,
+    qualities,
+)
+
+
+class PlaytvakIE(InfoExtractor):
+    IE_DESC = 'Playtvak.cz, iDNES.cz and Lidovky.cz'
+    _VALID_URL = r'https?://(?:.+?\.)?(?:playtvak|idnes|lidovky|metro)\.cz/.*\?(?:c|idvideo)=(?P<id>[^&]+)'
+    _TESTS = [{
+        'url': 'http://www.playtvak.cz/vyzente-vosy-a-srsne-ze-zahrady-dn5-/hodinovy-manzel.aspx?c=A150730_150323_hodinovy-manzel_kuko',
+        'md5': '4525ae312c324b4be2f4603cc78ceb4a',
+        'info_dict': {
+            'id': 'A150730_150323_hodinovy-manzel_kuko',
+            'ext': 'mp4',
+            'title': 'Vyžeňte vosy a sršně ze zahrady',
+            'description': 'md5:4436e61b7df227a093778efb7e373571',
+            'thumbnail': r're:(?i)^https?://.*\.(?:jpg|png)$',
+            'duration': 279,
+            'timestamp': 1438732860,
+            'upload_date': '20150805',
+            'is_live': False,
+        }
+    }, {  # live video test
+        'url': 'http://slowtv.playtvak.cz/planespotting-0pr-/planespotting.aspx?c=A150624_164934_planespotting_cat',
+        'info_dict': {
+            'id': 'A150624_164934_planespotting_cat',
+            'ext': 'flv',
+            'title': 're:^Planespotting [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'description': 'Sledujte provoz na ranveji Letiště Václava Havla v Praze',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,  # requires rtmpdump
+        },
+    }, {  # another live stream, this one without Misc.videoFLV
+        'url': 'https://slowtv.playtvak.cz/zive-sledujte-vlaky-v-primem-prenosu-dwi-/hlavni-nadrazi.aspx?c=A151218_145728_hlavni-nadrazi_plap',
+        'info_dict': {
+            'id': 'A151218_145728_hlavni-nadrazi_plap',
+            'ext': 'flv',
+            'title': 're:^Hlavní nádraží [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': True,  # requires rtmpdump
+        },
+    }, {  # idnes.cz
+        'url': 'http://zpravy.idnes.cz/pes-zavreny-v-aute-rozbijeni-okynek-v-aute-fj5-/domaci.aspx?c=A150809_104116_domaci_pku',
+        'md5': '819832ba33cd7016e58a6658577fe289',
+        'info_dict': {
+            'id': 'A150809_104116_domaci_pku',
+            'ext': 'mp4',
+            'title': 'Zavřeli jsme mraženou pizzu do auta. Upekla se',
+            'description': 'md5:01e73f02329e2e5760bd5eed4d42e3c2',
+            'thumbnail': r're:(?i)^https?://.*\.(?:jpg|png)$',
+            'duration': 39,
+            'timestamp': 1438969140,
+            'upload_date': '20150807',
+            'is_live': False,
+        }
+    }, {  # lidovky.cz
+        'url': 'http://www.lidovky.cz/dalsi-demonstrace-v-praze-o-migraci-duq-/video.aspx?c=A150808_214044_ln-video_ELE',
+        'md5': 'c7209ac4ba9d234d4ad5bab7485bcee8',
+        'info_dict': {
+            'id': 'A150808_214044_ln-video_ELE',
+            'ext': 'mp4',
+            'title': 'Táhni! Demonstrace proti imigrantům budila emoce',
+            'description': 'md5:97c81d589a9491fbfa323c9fa3cca72c',
+            'thumbnail': r're:(?i)^https?://.*\.(?:jpg|png)$',
+            'timestamp': 1439052180,
+            'upload_date': '20150808',
+            'is_live': False,
+        }
+    }, {  # metro.cz
+        'url': 'http://www.metro.cz/video-pod-billboardem-se-na-vltavske-roztocil-kolotoc-deti-vozil-jen-par-hodin-1hx-/metro-extra.aspx?c=A141111_173251_metro-extra_row',
+        'md5': '84fc1deedcac37b7d4a6ccae7c716668',
+        'info_dict': {
+            'id': 'A141111_173251_metro-extra_row',
+            'ext': 'mp4',
+            'title': 'Recesisté udělali z billboardu kolotoč',
+            'description': 'md5:7369926049588c3989a66c9c1a043c4c',
+            'thumbnail': r're:(?i)^https?://.*\.(?:jpg|png)$',
+            'timestamp': 1415725500,
+            'upload_date': '20141111',
+            'is_live': False,
+        }
+    }, {
+        'url': 'http://www.playtvak.cz/embed.aspx?idvideo=V150729_141549_play-porad_kuko',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        info_url = self._html_search_regex(
+            r'Misc\.video(?:FLV)?\(\s*{\s*data\s*:\s*"([^"]+)"', webpage, 'info url')
+
+        parsed_url = compat_urlparse.urlparse(info_url)
+
+        qs = compat_urlparse.parse_qs(parsed_url.query)
+        qs.update({
+            'reklama': ['0'],
+            'type': ['js'],
+        })
+
+        info_url = compat_urlparse.urlunparse(
+            parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
+
+        json_info = self._download_json(
+            info_url, video_id,
+            transform_source=lambda s: s[s.index('{'):s.rindex('}') + 1])
+
+        item = None
+        for i in json_info['items']:
+            if i.get('type') == 'video' or i.get('type') == 'stream':
+                item = i
+                break
+        if not item:
+            raise ExtractorError('No suitable stream found')
+
+        quality = qualities(('low', 'middle', 'high'))
+
+        formats = []
+        for fmt in item['video']:
+            video_url = fmt.get('file')
+            if not video_url:
+                continue
+
+            format_ = fmt['format']
+            format_id = '%s_%s' % (format_, fmt['quality'])
+            preference = None
+
+            if format_ in ('mp4', 'webm'):
+                ext = format_
+            elif format_ == 'rtmp':
+                ext = 'flv'
+            elif format_ == 'apple':
+                ext = 'mp4'
+                # Some streams have mp3 audio which does not play
+                # well with ffmpeg filter aac_adtstoasc
+                preference = -10
+            elif format_ == 'adobe':  # f4m manifest fails with 404 in 80% of requests
+                continue
+            else:  # Other formats not supported yet
+                continue
+
+            formats.append({
+                'url': video_url,
+                'ext': ext,
+                'format_id': format_id,
+                'quality': quality(fmt.get('quality')),
+                'preference': preference,
+            })
+
+        title = item['title']
+        is_live = item['type'] == 'stream'
+        description = self._og_search_description(webpage, default=None) or self._html_search_meta(
+            'description', webpage, 'description', default=None)
+        timestamp = None
+        duration = None
+        if not is_live:
+            duration = int_or_none(item.get('length'))
+            timestamp = item.get('published')
+            if timestamp:
+                timestamp = parse_iso8601(timestamp[:-5])
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': item.get('image'),
+            'duration': duration,
+            'timestamp': timestamp,
+            'is_live': is_live,
+            'formats': formats,
+        }

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

@@ -0,0 +1,72 @@
+from .common import InfoExtractor
+from ..utils import (
+    dict_get,
+    float_or_none,
+)
+
+
+class PlaywireIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:config|cdn)\.playwire\.com(?:/v2)?/(?P<publisher_id>\d+)/(?:videos/v2|embed|config)/(?P<id>\d+)'
+    _EMBED_REGEX = [r'<script[^>]+data-config=(["\'])(?P<url>(?:https?:)?//config\.playwire\.com/.+?)\1']
+
+    _TESTS = [{
+        'url': 'http://config.playwire.com/14907/videos/v2/3353705/player.json',
+        'md5': 'e6398701e3595888125729eaa2329ed9',
+        'info_dict': {
+            'id': '3353705',
+            'ext': 'mp4',
+            'title': 'S04_RM_UCL_Rus',
+            'thumbnail': r're:^https?://.*\.png$',
+            'duration': 145.94,
+        },
+    }, {
+        # m3u8 in f4m
+        'url': 'http://config.playwire.com/21772/videos/v2/4840492/zeus.json',
+        'info_dict': {
+            'id': '4840492',
+            'ext': 'mp4',
+            'title': 'ITV EL SHOW FULL',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
+        # Multiple resolutions while bitrates missing
+        'url': 'http://cdn.playwire.com/11625/embed/85228.html',
+        'only_matching': True,
+    }, {
+        'url': 'http://config.playwire.com/12421/videos/v2/3389892/zeus.json',
+        'only_matching': True,
+    }, {
+        'url': 'http://cdn.playwire.com/v2/12342/config/1532636.json',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        mobj = self._match_valid_url(url)
+        publisher_id, video_id = mobj.group('publisher_id'), mobj.group('id')
+
+        player = self._download_json(
+            'http://config.playwire.com/%s/videos/v2/%s/zeus.json' % (publisher_id, video_id),
+            video_id)
+
+        title = player['settings']['title']
+        duration = float_or_none(player.get('duration'), 1000)
+
+        content = player['content']
+        thumbnail = content.get('poster')
+        src = content['media']['f4m']
+
+        formats = self._extract_f4m_formats(src, video_id, m3u8_id='hls')
+        for a_format in formats:
+            if not dict_get(a_format, ['tbr', 'width', 'height']):
+                a_format['quality'] = 1 if '-hd.' in a_format['url'] else 0
+
+        return {
+            'id': video_id,
+            'title': title,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'formats': formats,
+        }