@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/iltalehti.py

@@ -0,0 +1,51 @@
+from .common import InfoExtractor
+from ..utils import js_to_json, traverse_obj
+
+
+class IltalehtiIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?iltalehti\.fi/[^/?#]+/a/(?P<id>[^/?#])'
+    _TESTS = [
+        # jwplatform embed main_media
+        {
+            'url': 'https://www.iltalehti.fi/ulkomaat/a/9fbd067f-94e4-46cd-8748-9d958eb4dae2',
+            'md5': 'af12d42c539f1f49f0b62d231fe72dcd',
+            'info_dict': {
+                'id': 'gYjjaf1L',
+                'ext': 'mp4',
+                'title': 'Sensuroimaton Päivärinta, jakso 227: Vieraana Suomen Venäjän ex-suurlähettiläs René Nyberg ja Kenraalimajuri evp Pekka Toveri',
+                'description': '',
+                'upload_date': '20220928',
+                'timestamp': 1664360878,
+                'duration': 2089,
+                'thumbnail': r're:^https?://.*\.jpg',
+            },
+        },
+        # jwplatform embed body
+        {
+            'url': 'https://www.iltalehti.fi/politiikka/a/1ce49d85-1670-428b-8db8-d2479b9950a4',
+            'md5': '9e50334b8f8330ce8828b567a82a3c65',
+            'info_dict': {
+                'id': '18R6zkLi',
+                'ext': 'mp4',
+                'title': 'Pekka Toverin arvio: Näin Nord Stream -kaasuputken räjäyttäminen on saatettu toteuttaa',
+                'description': 'md5:3d1302c9e17e7ffd564143ff58f8de35',
+                'upload_date': '20220929',
+                'timestamp': 1664435867,
+                'duration': 165.0,
+                'thumbnail': r're:^https?://.*\.jpg',
+            },
+        },
+    ]
+
+    def _real_extract(self, url):
+        article_id = self._match_id(url)
+        webpage = self._download_webpage(url, article_id)
+        info = self._search_json(
+            r'<script>\s*window.App\s*=', webpage, 'json', article_id,
+            transform_source=js_to_json)
+        props = traverse_obj(info, (
+            'state', 'articles', ..., 'items', (('main_media', 'properties'), ('body', ..., 'properties'))))
+        video_ids = traverse_obj(props, (lambda _, v: v['provider'] == 'jwplayer', 'id'))
+        return self.playlist_from_matches(
+            video_ids, article_id, ie='JWPlatform', getter=lambda id: f'jwplatform:{id}',
+            title=traverse_obj(info, ('state', 'articles', ..., 'items', 'canonical_title'), get_all=False))

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

@@ -0,0 +1,144 @@
+import base64
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    mimetype2ext,
+    qualities,
+    traverse_obj,
+    try_get,
+    url_or_none,
+)
+
+
+class ImdbIE(InfoExtractor):
+    IE_NAME = 'imdb'
+    IE_DESC = 'Internet Movie Database trailers'
+    _VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title|list).*?[/-]vi(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'http://www.imdb.com/video/imdb/vi2524815897',
+        'info_dict': {
+            'id': '2524815897',
+            'ext': 'mp4',
+            'title': 'No. 2',
+            'description': 'md5:87bd0bdc61e351f21f20d2d7441cb4e7',
+            'duration': 152,
+            'thumbnail': r're:^https?://.+\.jpg',
+        }
+    }, {
+        'url': 'https://www.imdb.com/video/vi3516832537',
+        'info_dict': {
+            'id': '3516832537',
+            'ext': 'mp4',
+            'title': 'Paul: U.S. Trailer #1',
+            'description': 'md5:17fcc4fe11ec29b4399be9d4c5ef126c',
+            'duration': 153,
+            'thumbnail': r're:^https?://.+\.jpg',
+        }
+    }, {
+        'url': 'http://www.imdb.com/video/_/vi2524815897',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.imdb.com/title/tt1667889/?ref_=ext_shr_eml_vi#lb-vi2524815897',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.imdb.com/title/tt1667889/#lb-vi2524815897',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.imdb.com/videoplayer/vi1562949145',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.imdb.com/title/tt4218696/videoplayer/vi2608641561',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.imdb.com/list/ls009921623/videoplayer/vi260482329',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(f'https://www.imdb.com/video/vi{video_id}', video_id)
+        info = self._search_nextjs_data(webpage, video_id)
+        video_info = traverse_obj(info, ('props', 'pageProps', 'videoPlaybackData', 'video'), default={})
+        title = (traverse_obj(video_info, ('name', 'value'), ('primaryTitle', 'titleText', 'text'))
+                 or self._html_search_meta(('og:title', 'twitter:title'), webpage, default=None)
+                 or self._html_extract_title(webpage))
+        data = video_info.get('playbackURLs') or try_get(self._download_json(
+            'https://www.imdb.com/ve/data/VIDEO_PLAYBACK_DATA', video_id,
+            query={
+                'key': base64.b64encode(json.dumps({
+                    'type': 'VIDEO_PLAYER',
+                    'subType': 'FORCE_LEGACY',
+                    'id': 'vi%s' % video_id,
+                }).encode()).decode(),
+            }), lambda x: x[0]['videoLegacyEncodings'])
+        quality = qualities(('SD', '480p', '720p', '1080p'))
+        formats, subtitles = [], {}
+        for encoding in data:
+            if not encoding or not isinstance(encoding, dict):
+                continue
+            video_url = url_or_none(encoding.get('url'))
+            if not video_url:
+                continue
+            ext = mimetype2ext(encoding.get(
+                'mimeType')) or determine_ext(video_url)
+            if ext == 'm3u8':
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                    video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    preference=1, m3u8_id='hls', fatal=False)
+                subtitles = self._merge_subtitles(subtitles, subs)
+                formats.extend(fmts)
+                continue
+            format_id = traverse_obj(encoding, ('displayName', 'value'), 'definition')
+            formats.append({
+                'format_id': format_id,
+                'url': video_url,
+                'ext': ext,
+                'quality': quality(format_id),
+            })
+
+        return {
+            'id': video_id,
+            'title': title,
+            'alt_title': info.get('videoSubTitle'),
+            'formats': formats,
+            'description': try_get(video_info, lambda x: x['description']['value']),
+            'thumbnail': url_or_none(try_get(video_info, lambda x: x['thumbnail']['url'])),
+            'duration': int_or_none(try_get(video_info, lambda x: x['runtime']['value'])),
+            'subtitles': subtitles,
+        }
+
+
+class ImdbListIE(InfoExtractor):
+    IE_NAME = 'imdb:list'
+    IE_DESC = 'Internet Movie Database lists'
+    _VALID_URL = r'https?://(?:www\.)?imdb\.com/list/ls(?P<id>\d{9})(?!/videoplayer/vi\d+)'
+    _TEST = {
+        'url': 'https://www.imdb.com/list/ls009921623/',
+        'info_dict': {
+            'id': '009921623',
+            'title': 'The Bourne Legacy',
+            'description': 'A list of trailers, clips, and more from The Bourne Legacy, starring Jeremy Renner and Rachel Weisz.',
+        },
+        'playlist_count': 8,
+    }
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+        webpage = self._download_webpage(url, list_id)
+        entries = [
+            self.url_result('http://www.imdb.com' + m, 'Imdb')
+            for m in re.findall(r'href="(/list/ls%s/videoplayer/vi[^"]+)"' % list_id, webpage)]
+
+        list_title = self._html_search_regex(
+            r'<h1[^>]+class="[^"]*header[^"]*"[^>]*>(.*?)</h1>',
+            webpage, 'list title')
+        list_description = self._html_search_regex(
+            r'<div[^>]+class="[^"]*list-description[^"]*"[^>]*><p>(.*?)</p>',
+            webpage, 'list description')
+
+        return self.playlist_result(entries, list_id, list_title, list_description)

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

@@ -0,0 +1,126 @@
+import json
+
+from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    str_or_none,
+    try_get,
+)
+
+
+class ImgGamingBaseIE(InfoExtractor):
+    _API_BASE = 'https://dce-frontoffice.imggaming.com/api/v2/'
+    _API_KEY = '857a1e5d-e35e-4fdf-805b-a87b6f8364bf'
+    _HEADERS = None
+    _MANIFEST_HEADERS = {'Accept-Encoding': 'identity'}
+    _REALM = None
+    _VALID_URL_TEMPL = r'https?://(?P<domain>%s)/(?P<type>live|playlist|video)/(?P<id>\d+)(?:\?.*?\bplaylistId=(?P<playlist_id>\d+))?'
+
+    def _initialize_pre_login(self):
+        self._HEADERS = {
+            'Realm': 'dce.' + self._REALM,
+            'x-api-key': self._API_KEY,
+        }
+
+    def _perform_login(self, username, password):
+        p_headers = self._HEADERS.copy()
+        p_headers['Content-Type'] = 'application/json'
+        self._HEADERS['Authorization'] = 'Bearer ' + self._download_json(
+            self._API_BASE + 'login',
+            None, 'Logging in', data=json.dumps({
+                'id': username,
+                'secret': password,
+            }).encode(), headers=p_headers)['authorisationToken']
+
+    def _real_initialize(self):
+        if not self._HEADERS.get('Authorization'):
+            self.raise_login_required(method='password')
+
+    def _call_api(self, path, media_id):
+        return self._download_json(
+            self._API_BASE + path + media_id, media_id, headers=self._HEADERS)
+
+    def _extract_dve_api_url(self, media_id, media_type):
+        stream_path = 'stream'
+        if media_type == 'video':
+            stream_path += '/vod/'
+        else:
+            stream_path += '?eventId='
+        try:
+            return self._call_api(
+                stream_path, media_id)['playerUrlCallback']
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 403:
+                raise ExtractorError(
+                    self._parse_json(e.cause.response.read().decode(), media_id)['messages'][0],
+                    expected=True)
+            raise
+
+    def _real_extract(self, url):
+        domain, media_type, media_id, playlist_id = self._match_valid_url(url).groups()
+
+        if playlist_id:
+            if self._yes_playlist(playlist_id, media_id):
+                media_type, media_id = 'playlist', playlist_id
+
+        if media_type == 'playlist':
+            playlist = self._call_api('vod/playlist/', media_id)
+            entries = []
+            for video in try_get(playlist, lambda x: x['videos']['vods']) or []:
+                video_id = str_or_none(video.get('id'))
+                if not video_id:
+                    continue
+                entries.append(self.url_result(
+                    'https://%s/video/%s' % (domain, video_id),
+                    self.ie_key(), video_id))
+            return self.playlist_result(
+                entries, media_id, playlist.get('title'),
+                playlist.get('description'))
+
+        dve_api_url = self._extract_dve_api_url(media_id, media_type)
+        video_data = self._download_json(dve_api_url, media_id)
+        is_live = media_type == 'live'
+        if is_live:
+            title = self._call_api('event/', media_id)['title']
+        else:
+            title = video_data['name']
+
+        formats = []
+        for proto in ('hls', 'dash'):
+            media_url = video_data.get(proto + 'Url') or try_get(video_data, lambda x: x[proto]['url'])
+            if not media_url:
+                continue
+            if proto == 'hls':
+                m3u8_formats = self._extract_m3u8_formats(
+                    media_url, media_id, 'mp4', live=is_live,
+                    m3u8_id='hls', fatal=False, headers=self._MANIFEST_HEADERS)
+                for f in m3u8_formats:
+                    f.setdefault('http_headers', {}).update(self._MANIFEST_HEADERS)
+                    formats.append(f)
+            else:
+                formats.extend(self._extract_mpd_formats(
+                    media_url, media_id, mpd_id='dash', fatal=False,
+                    headers=self._MANIFEST_HEADERS))
+
+        subtitles = {}
+        for subtitle in video_data.get('subtitles', []):
+            subtitle_url = subtitle.get('url')
+            if not subtitle_url:
+                continue
+            subtitles.setdefault(subtitle.get('lang', 'en_US'), []).append({
+                'url': subtitle_url,
+            })
+
+        return {
+            'id': media_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': video_data.get('thumbnailUrl'),
+            'description': video_data.get('description'),
+            'duration': int_or_none(video_data.get('duration')),
+            'tags': video_data.get('tags'),
+            'is_live': is_live,
+            'subtitles': subtitles,
+        }