@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/craftsy.py

@@ -0,0 +1,75 @@
+import json
+
+from .brightcove import BrightcoveNewIE
+from .common import InfoExtractor
+from ..utils import (
+    extract_attributes,
+    get_element_html_by_class,
+    get_element_text_and_html_by_tag,
+)
+from ..utils.traversal import traverse_obj
+
+
+class CraftsyIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.craftsy\.com/class/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://www.craftsy.com/class/the-midnight-quilt-show-season-5/',
+        'info_dict': {
+            'id': 'the-midnight-quilt-show-season-5',
+            'title': 'The Midnight Quilt Show Season 5',
+            'description': 'md5:113eda818e985d1a566625fb2f833b7a',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'https://www.craftsy.com/class/sew-your-own-designer-handbag/',
+        'info_dict': {
+            'id': 'sew-your-own-designer-handbag',
+            'title': 'Sew Your Own Designer Handbag',
+            'description': 'md5:8270d0ef5427d3c895a27351aeaac276',
+        },
+        'playlist_mincount': 1,
+    }, {
+        'url': 'https://www.craftsy.com/class/all-access-estes-park-wool-market/',
+        'info_dict': {
+            'id': 'all-access-estes-park-wool-market',
+            'title': 'All Access: Estes Park Wool Market',
+            'description': 'md5:aded1bd8d38ae2fae4dae936c0ae01e7',
+        },
+        'playlist_count': 6,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        video_player = get_element_html_by_class('class-video-player', webpage)
+        video_data = traverse_obj(video_player, (
+            {extract_attributes}, 'wire:snapshot', {json.loads}, 'data', {dict})) or {}
+        video_js = traverse_obj(video_player, (
+            {lambda x: get_element_text_and_html_by_tag('video-js', x)}, 1, {extract_attributes})) or {}
+
+        has_access = video_data.get('userHasAccess')
+        lessons = traverse_obj(video_data, ('lessons', ..., ..., lambda _, v: v['video_id']))
+
+        preview_id = video_js.get('data-video-id')
+        if preview_id and preview_id not in traverse_obj(lessons, (..., 'video_id')):
+            if not lessons and not has_access:
+                self.report_warning(
+                    'Only extracting preview. For the full class, pass cookies '
+                    + f'from an account that has access. {self._login_hint()}')
+            lessons.append({'video_id': preview_id})
+
+        if not lessons and not has_access:
+            self.raise_login_required('You do not have access to this class')
+
+        account_id = video_data.get('accountId') or video_js['data-account']
+
+        def entries(lessons):
+            for lesson in lessons:
+                yield self.url_result(
+                    f'http://players.brightcove.net/{account_id}/default_default/index.html?videoId={lesson["video_id"]}',
+                    BrightcoveNewIE, lesson['video_id'], lesson.get('title'))
+
+        return self.playlist_result(
+            entries(lessons), video_id, self._html_search_meta(('og:title', 'twitter:title'), webpage),
+            self._html_search_meta(('og:description', 'description'), webpage, default=None))

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

@@ -0,0 +1,56 @@
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    qualities,
+)
+
+
+class CrooksAndLiarsIE(InfoExtractor):
+    _VALID_URL = r'https?://embed\.crooksandliars\.com/(?:embed|v)/(?P<id>[A-Za-z0-9]+)'
+    _EMBED_REGEX = [r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1']
+
+    _TESTS = [{
+        'url': 'https://embed.crooksandliars.com/embed/8RUoRhRi',
+        'info_dict': {
+            'id': '8RUoRhRi',
+            'ext': 'mp4',
+            'title': 'Fox & Friends Says Protecting Atheists From Discrimination Is Anti-Christian!',
+            'description': 'md5:e1a46ad1650e3a5ec7196d432799127f',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'timestamp': 1428207000,
+            'upload_date': '20150405',
+            'uploader': 'Heather',
+            'duration': 236,
+        }
+    }, {
+        'url': 'http://embed.crooksandliars.com/v/MTE3MjUtMzQ2MzA',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(
+            'http://embed.crooksandliars.com/embed/%s' % video_id, video_id)
+
+        manifest = self._search_json(r'var\s+manifest\s*=', webpage, 'manifest JSON', video_id)
+
+        quality = qualities(('webm_low', 'mp4_low', 'webm_high', 'mp4_high'))
+
+        formats = [{
+            'url': item['url'],
+            'format_id': item['type'],
+            'quality': quality(item['type']),
+        } for item in manifest['flavors'] if item['mime'].startswith('video/')]
+
+        return {
+            'url': url,
+            'id': video_id,
+            'title': manifest['title'],
+            'description': manifest.get('description'),
+            'thumbnail': self._proto_relative_url(manifest.get('poster')),
+            'timestamp': int_or_none(manifest.get('created')),
+            'uploader': manifest.get('author'),
+            'duration': int_or_none(manifest.get('duration')),
+            'formats': formats,
+        }

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

@@ -0,0 +1,109 @@
+import itertools
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    try_get,
+    unified_strdate,
+)
+
+
+class CrowdBunkerIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?crowdbunker\.com/v/(?P<id>[^/?#$&]+)'
+
+    _TESTS = [{
+        'url': 'https://crowdbunker.com/v/0z4Kms8pi8I',
+        'info_dict': {
+            'id': '0z4Kms8pi8I',
+            'ext': 'mp4',
+            'title': '117) Pass vax et solutions',
+            'description': 'md5:86bcb422c29475dbd2b5dcfa6ec3749c',
+            'view_count': int,
+            'duration': 5386,
+            'uploader': 'Jérémie Mercier',
+            'uploader_id': 'UCeN_qQV829NYf0pvPJhW5dQ',
+            'like_count': int,
+            'upload_date': '20211218',
+            'thumbnail': 'https://scw.divulg.org/cb-medias4/images/0z4Kms8pi8I/maxres.jpg'
+        },
+        'params': {'skip_download': True}
+    }]
+
+    def _real_extract(self, url):
+        id = self._match_id(url)
+        data_json = self._download_json(f'https://api.divulg.org/post/{id}/details',
+                                        id, headers={'accept': 'application/json, text/plain, */*'})
+        video_json = data_json['video']
+        formats, subtitles = [], {}
+        for sub in video_json.get('captions') or []:
+            sub_url = try_get(sub, lambda x: x['file']['url'])
+            if not sub_url:
+                continue
+            subtitles.setdefault(sub.get('languageCode', 'fr'), []).append({
+                'url': sub_url,
+            })
+
+        mpd_url = try_get(video_json, lambda x: x['dashManifest']['url'])
+        if mpd_url:
+            fmts, subs = self._extract_mpd_formats_and_subtitles(mpd_url, id)
+            formats.extend(fmts)
+            subtitles = self._merge_subtitles(subtitles, subs)
+        m3u8_url = try_get(video_json, lambda x: x['hlsManifest']['url'])
+        if m3u8_url:
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(mpd_url, id)
+            formats.extend(fmts)
+            subtitles = self._merge_subtitles(subtitles, subs)
+
+        thumbnails = [{
+            'url': image['url'],
+            'height': int_or_none(image.get('height')),
+            'width': int_or_none(image.get('width')),
+        } for image in video_json.get('thumbnails') or [] if image.get('url')]
+
+        return {
+            'id': id,
+            'title': video_json.get('title'),
+            'description': video_json.get('description'),
+            'view_count': video_json.get('viewCount'),
+            'duration': video_json.get('duration'),
+            'uploader': try_get(data_json, lambda x: x['channel']['name']),
+            'uploader_id': try_get(data_json, lambda x: x['channel']['id']),
+            'like_count': data_json.get('likesCount'),
+            'upload_date': unified_strdate(video_json.get('publishedAt') or video_json.get('createdAt')),
+            'thumbnails': thumbnails,
+            'formats': formats,
+            'subtitles': subtitles,
+        }
+
+
+class CrowdBunkerChannelIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?crowdbunker\.com/@(?P<id>[^/?#$&]+)'
+
+    _TESTS = [{
+        'url': 'https://crowdbunker.com/@Milan_UHRIN',
+        'playlist_mincount': 14,
+        'info_dict': {
+            'id': 'Milan_UHRIN',
+        },
+    }]
+
+    def _entries(self, id):
+        last = None
+
+        for page in itertools.count():
+            channel_json = self._download_json(
+                f'https://api.divulg.org/organization/{id}/posts', id, headers={'accept': 'application/json, text/plain, */*'},
+                query={'after': last} if last else {}, note=f'Downloading Page {page}')
+            for item in channel_json.get('items') or []:
+                v_id = item.get('uid')
+                if not v_id:
+                    continue
+                yield self.url_result(
+                    'https://crowdbunker.com/v/%s' % v_id, ie=CrowdBunkerIE.ie_key(), video_id=v_id)
+            last = channel_json.get('last')
+            if not last:
+                break
+
+    def _real_extract(self, url):
+        id = self._match_id(url)
+        return self.playlist_result(self._entries(id), playlist_id=id)

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

@@ -0,0 +1,53 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import make_archive_id, remove_end
+
+
+class CrtvgIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?crtvg\.es/tvg/a-carta/(?P<id>[^/#?]+)'
+    _TESTS = [{
+        'url': 'https://www.crtvg.es/tvg/a-carta/os-caimans-do-tea-5839623',
+        'md5': 'c0958d9ff90e4503a75544358758921d',
+        'info_dict': {
+            'id': 'os-caimans-do-tea-5839623',
+            'title': 'Os caimáns do Tea',
+            'ext': 'mp4',
+            'description': 'md5:f71cfba21ae564f0a6f415b31de1f842',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+            '_old_archive_ids': ['crtvg 5839623'],
+        },
+        'params': {'skip_download': 'm3u8'}
+    }, {
+        'url': 'https://www.crtvg.es/tvg/a-carta/a-parabolica-love-story',
+        'md5': '9a47b95a1749db7b7eb3214904624584',
+        'info_dict': {
+            'id': 'a-parabolica-love-story',
+            'title': 'A parabólica / Trabuco, o can mordedor / Love Story',
+            'ext': 'mp4',
+            'description': 'md5:f71cfba21ae564f0a6f415b31de1f842',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+        },
+        'params': {'skip_download': 'm3u8'}
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        video_url = self._search_regex(r'var\s+url\s*=\s*["\']([^"\']+)', webpage, 'video url')
+        formats = self._extract_m3u8_formats(video_url + '/playlist.m3u8', video_id, fatal=False)
+        formats.extend(self._extract_mpd_formats(video_url + '/manifest.mpd', video_id, fatal=False))
+
+        old_video_id = None
+        if mobj := re.fullmatch(r'[^/#?]+-(?P<old_id>\d{7})', video_id):
+            old_video_id = [make_archive_id(self, mobj.group('old_id'))]
+
+        return {
+            'id': video_id,
+            '_old_archive_ids': old_video_id,
+            'formats': formats,
+            'title': remove_end(self._html_search_meta(
+                ['og:title', 'twitter:title'], webpage, 'title', default=None), ' | CRTVG'),
+            'description': self._html_search_meta('description', webpage, 'description', default=None),
+            'thumbnail': self._html_search_meta(['og:image', 'twitter:image'], webpage, 'thumbnail', default=None),
+        }