@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/pladform.py

@@ -0,0 +1,135 @@
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    ExtractorError,
+    int_or_none,
+    parse_qs,
+    xpath_text,
+    qualities,
+)
+
+
+class PladformIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            (?:
+                                out\.pladform\.ru/player|
+                                static\.pladform\.ru/player\.swf
+                            )
+                            \?.*\bvideoid=|
+                            video\.pladform\.ru/catalog/video/videoid/
+                        )
+                        (?P<id>\d+)
+                    '''
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//out\.pladform\.ru/player\?.+?)\1']
+    _TESTS = [{
+        'url': 'http://out.pladform.ru/player?pl=18079&type=html5&videoid=100231282',
+        'info_dict': {
+            'id': '6216d548e755edae6e8280667d774791',
+            'ext': 'mp4',
+            'timestamp': 1406117012,
+            'title': 'Гарик Мартиросян и Гарик Харламов - Кастинг на концерт ко Дню милиции',
+            'age_limit': 0,
+            'upload_date': '20140723',
+            'thumbnail': str,
+            'view_count': int,
+            'description': str,
+            'uploader_id': '12082',
+            'uploader': 'Comedy Club',
+            'duration': 367,
+        },
+        'expected_warnings': ['HTTP Error 404: Not Found']
+    }, {
+        'url': 'https://out.pladform.ru/player?pl=64471&videoid=3777899&vk_puid15=0&vk_puid34=0',
+        'md5': '53362fac3a27352da20fa2803cc5cd6f',
+        'info_dict': {
+            'id': '3777899',
+            'ext': 'mp4',
+            'title': 'СТУДИЯ СОЮЗ • Шоу Студия Союз, 24 выпуск (01.02.2018) Нурлан Сабуров и Слава Комиссаренко',
+            'description': 'md5:05140e8bf1b7e2d46e7ba140be57fd95',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 3190,
+        },
+    }, {
+        'url': 'http://static.pladform.ru/player.swf?pl=21469&videoid=100183293&vkcid=0',
+        'only_matching': True,
+    }, {
+        'url': 'http://video.pladform.ru/catalog/video/videoid/100183293/vkcid/0',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        qs = parse_qs(url)
+        pl = qs.get('pl', ['1'])[0]
+
+        video = self._download_xml(
+            'http://out.pladform.ru/getVideo', video_id, query={
+                'pl': pl,
+                'videoid': video_id,
+            }, fatal=False)
+
+        def fail(text):
+            raise ExtractorError(
+                '%s returned error: %s' % (self.IE_NAME, text),
+                expected=True)
+
+        if not video:
+            targetUrl = self._request_webpage(url, video_id, note='Resolving final URL').url
+            if targetUrl == url:
+                raise ExtractorError('Can\'t parse page')
+            return self.url_result(targetUrl)
+
+        if video.tag == 'error':
+            fail(video.text)
+
+        quality = qualities(('ld', 'sd', 'hd'))
+
+        formats = []
+        for src in video.findall('./src'):
+            if src is None:
+                continue
+            format_url = src.text
+            if not format_url:
+                continue
+            if src.get('type') == 'hls' or determine_ext(format_url) == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            else:
+                formats.append({
+                    'url': src.text,
+                    'format_id': src.get('quality'),
+                    'quality': quality(src.get('quality')),
+                })
+
+        if not formats:
+            error = xpath_text(video, './cap', 'error', default=None)
+            if error:
+                fail(error)
+
+        webpage = self._download_webpage(
+            'http://video.pladform.ru/catalog/video/videoid/%s' % video_id,
+            video_id)
+
+        title = self._og_search_title(webpage, fatal=False) or xpath_text(
+            video, './/title', 'title', fatal=True)
+        description = self._search_regex(
+            r'</h3>\s*<p>([^<]+)</p>', webpage, 'description', fatal=False)
+        thumbnail = self._og_search_thumbnail(webpage) or xpath_text(
+            video, './/cover', 'cover')
+
+        duration = int_or_none(xpath_text(video, './/time', 'duration'))
+        age_limit = int_or_none(xpath_text(video, './/age18', 'age limit'))
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'duration': duration,
+            'age_limit': age_limit,
+            'formats': formats,
+        }

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

@@ -0,0 +1,71 @@
+from .common import InfoExtractor
+from ..utils import (
+    try_get,
+    unified_strdate,
+)
+
+
+class PlanetMarathiIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?planetmarathi\.com/titles/(?P<id>[^/#&?$]+)'
+    _TESTS = [{
+        'url': 'https://www.planetmarathi.com/titles/ek-unad-divas',
+        'playlist_mincount': 2,
+        'info_dict': {
+            'id': 'ek-unad-divas',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'ASSETS-MOVIE-ASSET-01_ek-unad-divas',
+                'ext': 'mp4',
+                'title': 'ek unad divas',
+                'alt_title': 'चित्रपट',
+                'description': 'md5:41c7ed6b041c2fea9820a3f3125bd881',
+                'episode_number': 1,
+                'duration': 5539,
+                'upload_date': '20210829',
+            },
+        }]  # Trailer skipped
+    }, {
+        'url': 'https://www.planetmarathi.com/titles/baap-beep-baap-season-1',
+        'playlist_mincount': 10,
+        'info_dict': {
+            'id': 'baap-beep-baap-season-1',
+        },
+        'playlist': [{
+            'info_dict': {
+                'id': 'ASSETS-CHARACTER-PROFILE-SEASON-01-ASSET-01_baap-beep-baap-season-1',
+                'ext': 'mp4',
+                'title': 'Manohar Kanhere',
+                'alt_title': 'मनोहर कान्हेरे',
+                'description': 'md5:285ed45d5c0ab5522cac9a043354ebc6',
+                'season_number': 1,
+                'episode_number': 1,
+                'duration': 29,
+                'upload_date': '20210829',
+            },
+        }]  # Trailers, Episodes, other Character profiles skipped
+    }]
+
+    def _real_extract(self, url):
+        id = self._match_id(url)
+        entries = []
+        json_data = self._download_json(f'https://www.planetmarathi.com/api/v1/titles/{id}/assets', id)['assets']
+        for asset in json_data:
+            asset_title = asset['mediaAssetName']['en']
+            if asset_title == 'Movie':
+                asset_title = id.replace('-', ' ')
+            asset_id = f'{asset["sk"]}_{id}'.replace('#', '-')
+            formats, subtitles = self._extract_m3u8_formats_and_subtitles(asset['mediaAssetURL'], asset_id)
+            entries.append({
+                'id': asset_id,
+                'title': asset_title,
+                'alt_title': try_get(asset, lambda x: x['mediaAssetName']['mr']),
+                'description': try_get(asset, lambda x: x['mediaAssetDescription']['en']),
+                'season_number': asset.get('mediaAssetSeason'),
+                'episode_number': asset.get('mediaAssetIndexForAssetType'),
+                'duration': asset.get('mediaAssetDurationInSeconds'),
+                'upload_date': unified_strdate(asset.get('created')),
+                'formats': formats,
+                'subtitles': subtitles,
+            })
+        return self.playlist_result(entries, 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/platzi.py

@@ -0,0 +1,213 @@
+from .common import InfoExtractor
+from ..compat import (
+    compat_b64decode,
+    compat_str,
+)
+from ..utils import (
+    clean_html,
+    ExtractorError,
+    int_or_none,
+    str_or_none,
+    try_get,
+    url_or_none,
+    urlencode_postdata,
+    urljoin,
+)
+
+
+class PlatziBaseIE(InfoExtractor):
+    _LOGIN_URL = 'https://platzi.com/login/'
+    _NETRC_MACHINE = 'platzi'
+
+    def _perform_login(self, username, password):
+        login_page = self._download_webpage(
+            self._LOGIN_URL, None, 'Downloading login page')
+
+        login_form = self._hidden_inputs(login_page)
+
+        login_form.update({
+            'email': username,
+            'password': password,
+        })
+
+        urlh = self._request_webpage(
+            self._LOGIN_URL, None, 'Logging in',
+            data=urlencode_postdata(login_form),
+            headers={'Referer': self._LOGIN_URL})
+
+        # login succeeded
+        if 'platzi.com/login' not in urlh.url:
+            return
+
+        login_error = self._webpage_read_content(
+            urlh, self._LOGIN_URL, None, 'Downloading login error page')
+
+        login = self._parse_json(
+            self._search_regex(
+                r'login\s*=\s*({.+?})(?:\s*;|\s*</script)', login_error, 'login'),
+            None)
+
+        for kind in ('error', 'password', 'nonFields'):
+            error = str_or_none(login.get('%sError' % kind))
+            if error:
+                raise ExtractorError(
+                    'Unable to login: %s' % error, expected=True)
+        raise ExtractorError('Unable to log in')
+
+
+class PlatziIE(PlatziBaseIE):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            platzi\.com/clases|           # es version
+                            courses\.platzi\.com/classes  # en version
+                        )/[^/]+/(?P<id>\d+)-[^/?\#&]+
+                    '''
+
+    _TESTS = [{
+        'url': 'https://platzi.com/clases/1311-next-js/12074-creando-nuestra-primera-pagina/',
+        'md5': '8f56448241005b561c10f11a595b37e3',
+        'info_dict': {
+            'id': '12074',
+            'ext': 'mp4',
+            'title': 'Creando nuestra primera página',
+            'description': 'md5:4c866e45034fc76412fbf6e60ae008bc',
+            'duration': 420,
+        },
+        'skip': 'Requires platzi account credentials',
+    }, {
+        'url': 'https://courses.platzi.com/classes/1367-communication-codestream/13430-background/',
+        'info_dict': {
+            'id': '13430',
+            'ext': 'mp4',
+            'title': 'Background',
+            'description': 'md5:49c83c09404b15e6e71defaf87f6b305',
+            'duration': 360,
+        },
+        'skip': 'Requires platzi account credentials',
+        'params': {
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        lecture_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, lecture_id)
+
+        data = self._parse_json(
+            self._search_regex(
+                # client_data may contain "};" so that we have to try more
+                # strict regex first
+                (r'client_data\s*=\s*({.+?})\s*;\s*\n',
+                 r'client_data\s*=\s*({.+?})\s*;'),
+                webpage, 'client data'),
+            lecture_id)
+
+        material = data['initialState']['material']
+        desc = material['description']
+        title = desc['title']
+
+        formats = []
+        for server_id, server in material['videos'].items():
+            if not isinstance(server, dict):
+                continue
+            for format_id in ('hls', 'dash'):
+                format_url = url_or_none(server.get(format_id))
+                if not format_url:
+                    continue
+                if format_id == 'hls':
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, lecture_id, 'mp4',
+                        entry_protocol='m3u8_native', m3u8_id=format_id,
+                        note='Downloading %s m3u8 information' % server_id,
+                        fatal=False))
+                elif format_id == 'dash':
+                    formats.extend(self._extract_mpd_formats(
+                        format_url, lecture_id, mpd_id=format_id,
+                        note='Downloading %s MPD manifest' % server_id,
+                        fatal=False))
+
+        content = str_or_none(desc.get('content'))
+        description = (clean_html(compat_b64decode(content).decode('utf-8'))
+                       if content else None)
+        duration = int_or_none(material.get('duration'), invscale=60)
+
+        return {
+            'id': lecture_id,
+            'title': title,
+            'description': description,
+            'duration': duration,
+            'formats': formats,
+        }
+
+
+class PlatziCourseIE(PlatziBaseIE):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:
+                            platzi\.com/clases|           # es version
+                            courses\.platzi\.com/classes  # en version
+                        )/(?P<id>[^/?\#&]+)
+                    '''
+    _TESTS = [{
+        'url': 'https://platzi.com/clases/next-js/',
+        'info_dict': {
+            'id': '1311',
+            'title': 'Curso de Next.js',
+        },
+        'playlist_count': 22,
+    }, {
+        'url': 'https://courses.platzi.com/classes/communication-codestream/',
+        'info_dict': {
+            'id': '1367',
+            'title': 'Codestream Course',
+        },
+        'playlist_count': 14,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if PlatziIE.suitable(url) else super(PlatziCourseIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        course_name = self._match_id(url)
+
+        webpage = self._download_webpage(url, course_name)
+
+        props = self._parse_json(
+            self._search_regex(r'data\s*=\s*({.+?})\s*;', webpage, 'data'),
+            course_name)['initialProps']
+
+        entries = []
+        for chapter_num, chapter in enumerate(props['concepts'], 1):
+            if not isinstance(chapter, dict):
+                continue
+            materials = chapter.get('materials')
+            if not materials or not isinstance(materials, list):
+                continue
+            chapter_title = chapter.get('title')
+            chapter_id = str_or_none(chapter.get('id'))
+            for material in materials:
+                if not isinstance(material, dict):
+                    continue
+                if material.get('material_type') != 'video':
+                    continue
+                video_url = urljoin(url, material.get('url'))
+                if not video_url:
+                    continue
+                entries.append({
+                    '_type': 'url_transparent',
+                    'url': video_url,
+                    'title': str_or_none(material.get('name')),
+                    'id': str_or_none(material.get('id')),
+                    'ie_key': PlatziIE.ie_key(),
+                    'chapter': chapter_title,
+                    'chapter_number': chapter_num,
+                    'chapter_id': chapter_id,
+                })
+
+        course_id = compat_str(try_get(props, lambda x: x['course']['id']))
+        course_title = try_get(props, lambda x: x['course']['name'], compat_str)
+
+        return self.playlist_result(entries, course_id, course_title)

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

@@ -0,0 +1,100 @@
+import json
+
+from .common import InfoExtractor
+from ..networking import PUTRequest
+from ..networking.exceptions import HTTPError
+from ..utils import ExtractorError, clean_html, int_or_none
+
+
+class PlayPlusTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?playplus\.(?:com|tv)/VOD/(?P<project_id>[0-9]+)/(?P<id>[0-9a-f]{32})'
+    _TEST = {
+        'url': 'https://www.playplus.tv/VOD/7572/db8d274a5163424e967f35a30ddafb8e',
+        'md5': 'd078cb89d7ab6b9df37ce23c647aef72',
+        'info_dict': {
+            'id': 'db8d274a5163424e967f35a30ddafb8e',
+            'ext': 'mp4',
+            'title': 'Capítulo 179 - Final',
+            'description': 'md5:01085d62d8033a1e34121d3c3cabc838',
+            'timestamp': 1529992740,
+            'upload_date': '20180626',
+        },
+        'skip': 'Requires account credential',
+    }
+    _NETRC_MACHINE = 'playplustv'
+    _GEO_COUNTRIES = ['BR']
+    _token = None
+    _profile_id = None
+
+    def _call_api(self, resource, video_id=None, query=None):
+        return self._download_json('https://api.playplus.tv/api/media/v2/get' + resource, video_id, headers={
+            'Authorization': 'Bearer ' + self._token,
+        }, query=query)
+
+    def _perform_login(self, username, password):
+        req = PUTRequest(
+            'https://api.playplus.tv/api/web/login', json.dumps({
+                'email': username,
+                'password': password,
+            }).encode(), {
+                'Content-Type': 'application/json; charset=utf-8',
+            })
+
+        try:
+            self._token = self._download_json(req, None)['token']
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 401:
+                raise ExtractorError(self._parse_json(
+                    e.cause.response.read(), None)['errorMessage'], expected=True)
+            raise
+
+        self._profile = self._call_api('Profiles')['list'][0]['_id']
+
+    def _real_initialize(self):
+        if not self._token:
+            self.raise_login_required(method='password')
+
+    def _real_extract(self, url):
+        project_id, media_id = self._match_valid_url(url).groups()
+        media = self._call_api(
+            'Media', media_id, {
+                'profileId': self._profile,
+                'projectId': project_id,
+                'mediaId': media_id,
+            })['obj']
+        title = media['title']
+
+        formats = []
+        for f in media.get('files', []):
+            f_url = f.get('url')
+            if not f_url:
+                continue
+            file_info = f.get('fileInfo') or {}
+            formats.append({
+                'url': f_url,
+                'width': int_or_none(file_info.get('width')),
+                'height': int_or_none(file_info.get('height')),
+            })
+
+        thumbnails = []
+        for thumb in media.get('thumbs', []):
+            thumb_url = thumb.get('url')
+            if not thumb_url:
+                continue
+            thumbnails.append({
+                'url': thumb_url,
+                'width': int_or_none(thumb.get('width')),
+                'height': int_or_none(thumb.get('height')),
+            })
+
+        return {
+            'id': media_id,
+            'title': title,
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'description': clean_html(media.get('description')) or media.get('shortDescription'),
+            'timestamp': int_or_none(media.get('publishDate'), 1000),
+            'view_count': int_or_none(media.get('numberOfViews')),
+            'comment_count': int_or_none(media.get('numberOfComments')),
+            'tags': media.get('tags'),
+        }