@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/ixigua.py

@@ -0,0 +1,83 @@
+import base64
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    get_element_by_id,
+    int_or_none,
+    js_to_json,
+    str_or_none,
+    traverse_obj,
+)
+
+
+class IxiguaIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:\w+\.)?ixigua\.com/(?:video/)?(?P<id>\d+).+'
+    _TESTS = [{
+        'url': 'https://www.ixigua.com/6996881461559165471',
+        'info_dict': {
+            'id': '6996881461559165471',
+            'ext': 'mp4',
+            'title': '盲目涉水风险大，亲身示范高水位行车注意事项',
+            'description': 'md5:8c82f46186299add4a1c455430740229',
+            'tags': ['video_car'],
+            'like_count': int,
+            'dislike_count': int,
+            'view_count': int,
+            'uploader': '懂车帝原创',
+            'uploader_id': '6480145787',
+            'thumbnail': r're:^https?://.+\.(avif|webp)',
+            'timestamp': 1629088414,
+            'duration': 1030,
+        }
+    }]
+
+    def _get_json_data(self, webpage, video_id):
+        js_data = get_element_by_id('SSR_HYDRATED_DATA', webpage)
+        if not js_data:
+            if self._cookies_passed:
+                raise ExtractorError('Failed to get SSR_HYDRATED_DATA')
+            raise ExtractorError('Cookies (not necessarily logged in) are needed', expected=True)
+
+        return self._parse_json(
+            js_data.replace('window._SSR_HYDRATED_DATA=', ''), video_id, transform_source=js_to_json)
+
+    def _media_selector(self, json_data):
+        for path, override in (
+            (('video_list', ), {}),
+            (('dynamic_video', 'dynamic_video_list'), {'acodec': 'none'}),
+            (('dynamic_video', 'dynamic_audio_list'), {'vcodec': 'none', 'ext': 'm4a'}),
+        ):
+            for media in traverse_obj(json_data, (..., *path, lambda _, v: v['main_url'])):
+                yield {
+                    'url': base64.b64decode(media['main_url']).decode(),
+                    'width': int_or_none(media.get('vwidth')),
+                    'height': int_or_none(media.get('vheight')),
+                    'fps': int_or_none(media.get('fps')),
+                    'vcodec': media.get('codec_type'),
+                    'format_id': str_or_none(media.get('quality_type')),
+                    'filesize': int_or_none(media.get('size')),
+                    'ext': 'mp4',
+                    **override,
+                }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        json_data = self._get_json_data(webpage, video_id)['anyVideo']['gidInformation']['packerData']['video']
+
+        formats = list(self._media_selector(json_data.get('videoResource')))
+        return {
+            'id': video_id,
+            'title': json_data.get('title'),
+            'description': json_data.get('video_abstract'),
+            'formats': formats,
+            'like_count': json_data.get('video_like_count'),
+            'duration': int_or_none(json_data.get('duration')),
+            'tags': [json_data.get('tag')],
+            'uploader_id': traverse_obj(json_data, ('user_info', 'user_id')),
+            'uploader': traverse_obj(json_data, ('user_info', 'name')),
+            'view_count': json_data.get('video_watch_count'),
+            'dislike_count': json_data.get('video_unlike_count'),
+            'timestamp': int_or_none(json_data.get('video_publish_time')),
+        }

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

@@ -0,0 +1,113 @@
+from .common import InfoExtractor
+from ..compat import (
+    compat_str,
+    compat_urllib_parse_unquote,
+)
+from ..utils import (
+    determine_ext,
+    float_or_none,
+    get_element_by_id,
+    int_or_none,
+    parse_iso8601,
+    str_to_int,
+)
+
+
+class IzleseneIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+        https?://(?:(?:www|m)\.)?izlesene\.com/
+        (?:video|embedplayer)/(?:[^/]+/)?(?P<id>[0-9]+)
+        '''
+    _TESTS = [
+        {
+            'url': 'http://www.izlesene.com/video/sevincten-cildirtan-dogum-gunu-hediyesi/7599694',
+            'md5': '4384f9f0ea65086734b881085ee05ac2',
+            'info_dict': {
+                'id': '7599694',
+                'ext': 'mp4',
+                'title': 'Sevinçten Çıldırtan Doğum Günü Hediyesi',
+                'description': 'md5:253753e2655dde93f59f74b572454f6d',
+                'thumbnail': r're:^https?://.*\.jpg',
+                'uploader_id': 'pelikzzle',
+                'timestamp': int,
+                'upload_date': '20140702',
+                'duration': 95.395,
+                'age_limit': 0,
+            }
+        },
+        {
+            'url': 'http://www.izlesene.com/video/tarkan-dortmund-2006-konseri/17997',
+            'md5': '97f09b6872bffa284cb7fa4f6910cb72',
+            'info_dict': {
+                'id': '17997',
+                'ext': 'mp4',
+                'title': 'Tarkan Dortmund 2006 Konseri',
+                'thumbnail': r're:^https://.*\.jpg',
+                'uploader_id': 'parlayankiz',
+                'timestamp': int,
+                'upload_date': '20061112',
+                'duration': 253.666,
+                'age_limit': 0,
+            }
+        },
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage('http://www.izlesene.com/video/%s' % video_id, video_id)
+
+        video = self._parse_json(
+            self._search_regex(
+                r'videoObj\s*=\s*({.+?})\s*;\s*\n', webpage, 'streams'),
+            video_id)
+
+        title = video.get('videoTitle') or self._og_search_title(webpage)
+
+        formats = []
+        for stream in video['media']['level']:
+            source_url = stream.get('source')
+            if not source_url or not isinstance(source_url, compat_str):
+                continue
+            ext = determine_ext(url, 'mp4')
+            quality = stream.get('value')
+            height = int_or_none(quality)
+            formats.append({
+                'format_id': '%sp' % quality if quality else 'sd',
+                'url': compat_urllib_parse_unquote(source_url),
+                'ext': ext,
+                'height': height,
+            })
+
+        description = self._og_search_description(webpage, default=None)
+        thumbnail = video.get('posterURL') or self._proto_relative_url(
+            self._og_search_thumbnail(webpage), scheme='http:')
+
+        uploader = self._html_search_regex(
+            r"adduserUsername\s*=\s*'([^']+)';",
+            webpage, 'uploader', fatal=False)
+        timestamp = parse_iso8601(self._html_search_meta(
+            'uploadDate', webpage, 'upload date'))
+
+        duration = float_or_none(video.get('duration') or self._html_search_regex(
+            r'videoduration["\']?\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
+            webpage, 'duration', fatal=False, group='value'), scale=1000)
+
+        view_count = str_to_int(get_element_by_id('videoViewCount', webpage))
+        comment_count = self._html_search_regex(
+            r'comment_count\s*=\s*\'([^\']+)\';',
+            webpage, 'comment_count', fatal=False)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'uploader_id': uploader,
+            'timestamp': timestamp,
+            'duration': duration,
+            'view_count': int_or_none(view_count),
+            'comment_count': int_or_none(comment_count),
+            'age_limit': self._family_friendly_search(webpage),
+            'formats': formats,
+        }

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

@@ -0,0 +1,103 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    InAdvancePagedList,
+    int_or_none,
+    orderedSet,
+    unified_strdate,
+)
+
+
+class JableIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?jable\.tv/videos/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://jable.tv/videos/pppd-812/',
+        'md5': 'f1537283a9bc073c31ff86ca35d9b2a6',
+        'info_dict': {
+            'id': 'pppd-812',
+            'ext': 'mp4',
+            'title': 'PPPD-812 只要表現好巨乳女教師吉根柚莉愛就獎勵學生們在白虎穴內射出精液',
+            'description': 'md5:5b6d4199a854f62c5e56e26ccad19967',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'age_limit': 18,
+            'like_count': int,
+            'view_count': int,
+        },
+    }, {
+        'url': 'https://jable.tv/videos/apak-220/',
+        'md5': '71f9239d69ced58ab74a816908847cc1',
+        'info_dict': {
+            'id': 'apak-220',
+            'ext': 'mp4',
+            'title': 'md5:5c3861b7cf80112a6e2b70bccf170824',
+            'description': '',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'age_limit': 18,
+            'like_count': int,
+            'view_count': int,
+            'upload_date': '20220319',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        formats = self._extract_m3u8_formats(
+            self._search_regex(r'var\s+hlsUrl\s*=\s*\'([^\']+)', webpage, 'hls_url'), video_id, 'mp4', m3u8_id='hls')
+
+        return {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage, default=''),
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
+            'formats': formats,
+            'age_limit': 18,
+            'upload_date': unified_strdate(self._search_regex(
+                r'class="inactive-color">\D+\s+(\d{4}-\d+-\d+)', webpage, 'upload_date', default=None)),
+            'view_count': int_or_none(self._search_regex(
+                r'#icon-eye"></use></svg>\n*<span class="mr-3">([\d ]+)',
+                webpage, 'view_count', default='').replace(' ', '')),
+            'like_count': int_or_none(self._search_regex(
+                r'#icon-heart"></use></svg><span class="count">(\d+)', webpage, 'link_count', default=None)),
+        }
+
+
+class JablePlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?jable\.tv/(?:categories|models|tags)/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://jable.tv/models/kaede-karen/',
+        'info_dict': {
+            'id': 'kaede-karen',
+            'title': '楓カレン',
+        },
+        'playlist_count': 34,
+    }, {
+        'url': 'https://jable.tv/categories/roleplay/',
+        'only_matching': True,
+    }, {
+        'url': 'https://jable.tv/tags/girl/',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        def page_func(page_num):
+            return [
+                self.url_result(player_url, JableIE)
+                for player_url in orderedSet(re.findall(
+                    r'href="(https://jable.tv/videos/[\w-]+/?)"',
+                    self._download_webpage(url, playlist_id, query={
+                        'mode': 'async',
+                        'from': page_num + 1,
+                        'function': 'get_block',
+                        'block_id': 'list_videos_common_videos_list',
+                    }, note=f'Downloading page {page_num + 1}')))]
+
+        return self.playlist_result(
+            InAdvancePagedList(page_func, int_or_none(self._search_regex(
+                r'from:(\d+)">[^<]+\s*&raquo;', webpage, 'last page number', default=1)), 24),
+            playlist_id, self._search_regex(
+                r'<h2 class="h3-md mb-1">([^<]+)', webpage, 'playlist title', default=None))

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

@@ -0,0 +1,210 @@
+import hashlib
+import random
+
+from ..compat import compat_str
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    int_or_none,
+    try_get,
+)
+
+
+class JamendoIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            licensing\.jamendo\.com/[^/]+|
+                            (?:www\.)?jamendo\.com
+                        )
+                        /track/(?P<id>[0-9]+)(?:/(?P<display_id>[^/?#&]+))?
+                    '''
+    _TESTS = [{
+        'url': 'https://www.jamendo.com/track/196219/stories-from-emona-i',
+        'md5': '6e9e82ed6db98678f171c25a8ed09ffd',
+        'info_dict': {
+            'id': '196219',
+            'display_id': 'stories-from-emona-i',
+            'ext': 'flac',
+            # 'title': 'Maya Filipič - Stories from Emona I',
+            'title': 'Stories from Emona I',
+            'artist': 'Maya Filipič',
+            'album': 'Between two worlds',
+            'track': 'Stories from Emona I',
+            'duration': 210,
+            'thumbnail': 'https://usercontent.jamendo.com?type=album&id=29279&width=300&trackid=196219',
+            'timestamp': 1217438117,
+            'upload_date': '20080730',
+            'license': 'by-nc-nd',
+            'view_count': int,
+            'like_count': int,
+            'average_rating': int,
+            'tags': ['piano', 'peaceful', 'newage', 'strings', 'upbeat'],
+        }
+    }, {
+        'url': 'https://licensing.jamendo.com/en/track/1496667/energetic-rock',
+        'only_matching': True,
+    }]
+
+    def _call_api(self, resource, resource_id, fatal=True):
+        path = '/api/%ss' % resource
+        rand = compat_str(random.random())
+        return self._download_json(
+            'https://www.jamendo.com' + path, resource_id, fatal=fatal, query={
+                'id[]': resource_id,
+            }, headers={
+                'X-Jam-Call': '$%s*%s~' % (hashlib.sha1((path + rand).encode()).hexdigest(), rand)
+            })[0]
+
+    def _real_extract(self, url):
+        track_id, display_id = self._match_valid_url(url).groups()
+        # webpage = self._download_webpage(
+        #     'https://www.jamendo.com/track/' + track_id, track_id)
+        # models = self._parse_json(self._html_search_regex(
+        #     r"data-bundled-models='([^']+)",
+        #     webpage, 'bundled models'), track_id)
+        # track = models['track']['models'][0]
+        track = self._call_api('track', track_id)
+        title = track_name = track['name']
+        # get_model = lambda x: try_get(models, lambda y: y[x]['models'][0], dict) or {}
+        # artist = get_model('artist')
+        # artist_name = artist.get('name')
+        # if artist_name:
+        #     title = '%s - %s' % (artist_name, title)
+        # album = get_model('album')
+        artist = self._call_api("artist", track.get('artistId'), fatal=False)
+        album = self._call_api("album", track.get('albumId'), fatal=False)
+
+        formats = [{
+            'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
+                   % (sub_domain, track_id, format_id),
+            'format_id': format_id,
+            'ext': ext,
+            'quality': quality,
+        } for quality, (format_id, sub_domain, ext) in enumerate((
+            ('mp31', 'mp3l', 'mp3'),
+            ('mp32', 'mp3d', 'mp3'),
+            ('ogg1', 'ogg', 'ogg'),
+            ('flac', 'flac', 'flac'),
+        ))]
+
+        urls = []
+        thumbnails = []
+        for covers in (track.get('cover') or {}).values():
+            for cover_id, cover_url in covers.items():
+                if not cover_url or cover_url in urls:
+                    continue
+                urls.append(cover_url)
+                size = int_or_none(cover_id.lstrip('size'))
+                thumbnails.append({
+                    'id': cover_id,
+                    'url': cover_url,
+                    'width': size,
+                    'height': size,
+                })
+
+        tags = []
+        for tag in (track.get('tags') or []):
+            tag_name = tag.get('name')
+            if not tag_name:
+                continue
+            tags.append(tag_name)
+
+        stats = track.get('stats') or {}
+        license = track.get('licenseCC') or []
+
+        return {
+            'id': track_id,
+            'display_id': display_id,
+            'thumbnails': thumbnails,
+            'title': title,
+            'description': track.get('description'),
+            'duration': int_or_none(track.get('duration')),
+            'artist': artist.get('name'),
+            'track': track_name,
+            'album': album.get('name'),
+            'formats': formats,
+            'license': '-'.join(license) if license else None,
+            'timestamp': int_or_none(track.get('dateCreated')),
+            'view_count': int_or_none(stats.get('listenedAll')),
+            'like_count': int_or_none(stats.get('favorited')),
+            'average_rating': int_or_none(stats.get('averageNote')),
+            'tags': tags,
+        }
+
+
+class JamendoAlbumIE(JamendoIE):  # XXX: Do not subclass from concrete IE
+    _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)'
+    _TESTS = [{
+        'url': 'https://www.jamendo.com/album/121486/duck-on-cover',
+        'info_dict': {
+            'id': '121486',
+            'title': 'Duck On Cover',
+            'description': 'md5:c2920eaeef07d7af5b96d7c64daf1239',
+        },
+        'playlist': [{
+            'md5': 'e1a2fcb42bda30dfac990212924149a8',
+            'info_dict': {
+                'id': '1032333',
+                'ext': 'flac',
+                'title': 'Warmachine',
+                'artist': 'Shearer',
+                'track': 'Warmachine',
+                'timestamp': 1368089771,
+                'upload_date': '20130509',
+                'view_count': int,
+                'thumbnail': 'https://usercontent.jamendo.com?type=album&id=121486&width=300&trackid=1032333',
+                'duration': 190,
+                'license': 'by',
+                'album': 'Duck On Cover',
+                'average_rating': 4,
+                'tags': ['rock', 'drums', 'bass', 'world', 'punk', 'neutral'],
+                'like_count': int,
+            }
+        }, {
+            'md5': '1f358d7b2f98edfe90fd55dac0799d50',
+            'info_dict': {
+                'id': '1032330',
+                'ext': 'flac',
+                'title': 'Without Your Ghost',
+                'artist': 'Shearer',
+                'track': 'Without Your Ghost',
+                'timestamp': 1368089771,
+                'upload_date': '20130509',
+                'duration': 192,
+                'tags': ['rock', 'drums', 'bass', 'world', 'punk'],
+                'album': 'Duck On Cover',
+                'thumbnail': 'https://usercontent.jamendo.com?type=album&id=121486&width=300&trackid=1032330',
+                'view_count': int,
+                'average_rating': 4,
+                'license': 'by',
+                'like_count': int,
+            }
+        }],
+        'params': {
+            'playlistend': 2
+        }
+    }]
+
+    def _real_extract(self, url):
+        album_id = self._match_id(url)
+        album = self._call_api('album', album_id)
+        album_name = album.get('name')
+
+        entries = []
+        for track in (album.get('tracks') or []):
+            track_id = track.get('id')
+            if not track_id:
+                continue
+            track_id = compat_str(track_id)
+            entries.append({
+                '_type': 'url_transparent',
+                'url': 'https://www.jamendo.com/track/' + track_id,
+                'ie_key': JamendoIE.ie_key(),
+                'id': track_id,
+                'album': album_name,
+            })
+
+        return self.playlist_result(
+            entries, album_id, album_name,
+            clean_html(try_get(album, lambda x: x['description']['en'], compat_str)))